US20070036370A1 - Method and apparatus for multi-sensory speech enhancement on a mobile device - Google Patents

Abstract

A mobile device includes an air conduction microphone and an alternative sensor that provides an alternative sensor signal indicative of speech. A communication interface permits the mobile device to communicate directly with other mobile devices.

Description

REFERENCE TO RELATED APPLICATIONS
• This application is a divisional of and claims priority from U.S. patent application Ser. No. 10/962,954, filed on Oct. 12, 2004.
BACKGROUND OF THE INVENTION
• The present invention relates to mobile devices. In particular, the present invention relates to multi-sensory mobile devices.
• Mobile hand-held devices such as mobile phones and personal digital assistants that provide phone functions or accept speech input are often used in adverse noise environments such as busy streets, restaurants, airports, and cars. The strong ambient noise in these environments can obscure the user's speech and make it difficult to understand what the person is saying. In addition, it severely degrades speech recognition accuracy.
• While noise filtering systems have been developed that attempt to remove noise based on a model of the noise, these systems have not been able to remove all of the noise. In particular, many of these systems have found it difficult to remove noise that consists of other people speaking in the background. One reason for this is that it is extremely difficult, if not impossible, for these systems to determine that a speech signal received by a microphone came from someone other than the person using the mobile device.
• For phone headsets, which are kept in position on the user's head by looping the headset over the user's head or ear, systems have been developed that provide more robust noise filtering by relying on additional types of sensors in the headset. In one example, a bone conduction sensor is placed on one end of the head set and is pressed into contact with the skin covering the users skull, ear, or mandible by the resilience of the headset. The bone conduction sensor detects vibrations in the skull, ear or mandible that are created when the user speaks. Using the signal from the bone conduction sensor, this system is able to better identify when the user is speaking and as a result is better able to filter noise in the speech signal.
• Although such systems work well for headsets, headsets have been limited to communicating along a wired connection to a phone. As such, their use in broader communication applications is limited. In addition, a headset is visually unattractive (big and bulky) as well as uncomfortable to wear for all day and as a result, users are unlikely to want to leave them in place during the day. This makes headsets cumbersome to use.
SUMMARY OF THE INVENTION
• A mobile device is provided that includes an air conduction microphone and an alternative sensor that provides an alternative sensor signal indicative of speech. A communication interface permits the mobile device to communicate directly with other mobile devices.
BRIEF DESCRIPTION OF THE DRAWINGS
• FIG. 1 is a perspective view of one embodiment of the present invention.
• FIG. 2 shows the phone ofFIG. 1 in position on the left side of a user's head.
• FIG. 3 shows the phone ofFIG. 1 in position on the right side of a user's head.
• FIG. 4 is a block diagram of a bone conduction microphone.
• FIG. 5 is a perspective view of an alternative embodiment of the present invention.
• FIG. 6 is a cross-section of an alternative bone-conduction microphone under one embodiment of the present invention.
• FIG. 7 is a front view of a necklace embodiment of a mobile device of the present invention.
• FIG. 8 is a back view of the necklace embodiment ofFIG. 7.
• FIG. 9 shows the necklace embodiment ofFIG. 7 positioned on a user.
• FIG. 10 provides a perspective view of a bracelet/watch embodiment of a mobile device of the present invention.
• FIG. 11 is block diagram of a mobile device under one embodiment of the present invention.
• FIG. 12 is a block diagram of a general speech processing system of the present invention.
• FIG. 13 is a block diagram showing possible communication connection of mobile devices of the present invention.
• FIG. 14 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate a meeting.
• FIG. 15 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate dispatching work orders.
• FIG. 16 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate group communication and to aid in a rescue.
• FIG. 17 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate gaming.
• FIG. 18 is a block diagram showing the ability to store, organize and review video and audio using a mobile device of the present invention.
• FIG. 19 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate locating and communicating with children/elderly.
• FIG. 20 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate meetings that need translation of speech.
• FIG. 21 is a block diagram showing a plurality of communication connections with a mobile device of the present invention to facilitate meetings that need translation of speech.
• FIG. 22 is a block diagram showing a plurality of peer-to-peer communication connections between a mobile device of the present invention and other devices.
DETAILED DESCRIPTION OF ILLUSTRATIVE EMBODIMENTS
• Embodiments of the present invention provide mobile devices that contain both an air conduction microphone and an alternative sensor that can be used in speech detection and noise filtering. Examples of mobile devices of the present invention include cellular phones, personal digital assistants, jewelry, and watches.FIG. 1 provides an example embodiment in which the mobile device is amobile phone100.Mobile phone100 includes akey pad102, adisplay104, acursor control106, anair conduction microphone108, aspeaker110, two bone-conduction microphones112 and114, and optionally aproximity sensor116.Mobile phone100 also includes a power source such as a battery, a processor, a global positioning satellite signal detector and processor, which are not visible from the exterior of the phone. Optionally,mobile phone100 may also include a pulse sensor, an oximetry sensor, a temperature sensor, and a video camera.
• Touchpad102 allows the user to enter numbers and letters into the mobile phone. In other embodiments,touchpad102 is combined withdisplay104 in the form of a touch screen.Cursor control106 allows the user to highlight and select information ondisplay104 and to scroll through images and pages that are larger thandisplay104.
• As shown inFIGS. 2 and 3, whenmobile phone100 is put in the standard position for conversing over the phone,speaker110 is positioned near the user'sleft ear200 orright ear300, andair conduction microphone108 is positioned near the user'smouth202. When the phone is positioned near the user's left ear, as inFIG. 2,bone conduction microphone114 contacts the user's skull or ear and produces an alternative sensor signal that provides information about speech can be used to remove noise from the speech signal received byair conduction microphone108. For example, the information provided in the alternative sensor signal can include whether the user is speaking as well as low frequency information related to the user's speech. When the phone is positioned near the user's right ear, as inFIG. 3,bone conduction microphone112 contacts the user's skull or ear and produces an alternative sensor signal that can be used to remove noise from the speech signal.
• Theoptional proximity sensor116 indicates how close the phone is to the user. As discussed further below, this information is used to weight the contribution of the bone conduction microphones in producing the clean speech value. In general, if the proximity detector detects that the phone is next to the user, the bone conduction microphone signals are weighted more heavily than if the phone is some distance from the user. This adjustment reflects the fact that the bone conduction microphone signal is more indicative of the user speaking when it is in contact with the user. When it is apart from the user, it is more susceptible to ambient noise. The proximity sensor is used in embodiments of the present invention because users do not always hold the phone pressed to their heads.
• FIG. 4 shows one embodiment of abone conduction sensor400 of the present invention. Insensor400, asoft elastomer bridge402 is adhered to adiaphragm404 of a normalair conduction microphone406. Thissoft bridge402 conducts vibrations fromskin contact408 of the user directly to thediaphragm404 ofmicrophone406. The movement ofdiaphragm404 is converted into an electrical signal by atransducer410 inmicrophone406.
• FIG. 5 provides an alternativemobile phone embodiment500 of the hand-held mobile device of the present invention.Mobile phone500 includes akey pad502, adisplay504, acursor control506, anair conduction microphone508, aspeaker510, and a combination bone-conduction microphone andproximity sensor512.
• As shown in the cross-section ofFIG. 6, combination of bone-conduction microphone andproximity sensor512 consists of a soft, medium-filled (with fluid or elastomer)pad600 that has anouter surface602 designed to contact the user when the user places the phone against their ear.Pad600 forms a ring around an opening that provides a passageway for sound fromspeaker510, which is located in the opening or directly below the opening withinphone500.Pad600 is not limited to this shape and any shape for the pad may be used. In general, however, it is preferred ifpad600 includes portions to the left and right ofspeaker510 so that at least one part ofpad600 is in contact with the user regardless of which ear the user places the phone against. The portions of the pad may be externally continuous or may be externally separate but fluidly connected to each other within the phone.
• Anelectronic pressure transducer604 is hydraulically connected to the fluid or elastomer inpad600 and converts the pressure of the fluid inpad600 into an electrical signal onconductor606. Examples ofelectronic pressure transducer604 include MEMS-based transducers. In general,pressure transducer604 should have a high frequency response.
• The electrical signal onconductor606 includes two components, a DC component and an AC component. The DC component provides a proximity sensor signal because the static pressure withinpad600 will by higher when the phone is pressed against the user's ear than when the phone is some distance from the user's ear. The AC component of the electrical signal provides a bone-conduction microphone signal because vibrations in the bones of the user's skull, jaw or ear create fluctuations in pressure inpad600 that are converted into an AC electrical signal bypressure transducer604. Under one embodiment, a filter is applied to the electrical signal to allow the DC component of the signal and AC components above a minimum frequency to pass.
• Although two examples of bone conduction sensors have been described above, other forms for the bone conduction sensor are within the scope of the present invention.
• FIGS. 7 and 8 show a front view and a back view of an alternative embodiment of a mobile device under the present invention. InFIGS. 7 and 8,mobile device700 consists of a necklace orchoker702 and anear bud704.Necklace702 includes a decorative/ornamental disk orpendant706 that is suspended from aneck engaging piece708, such as a string or a wire. The neck engaging piece supports the mobile device on the user and is designed to be attached around a user's neck.Decorative disk706 includes amicrophone opening708 and avideo opening710.
• As shown from the back view ofFIG. 8,mobile device700 includes abattery710, which powers anair conduction microphone712, analternative sensor714, avideo camera716, a processing chip set718, and a global positioning satellite (GPS)receiver720. Processing chip set718 is connected toair conduction microphone712,alternative sensor714,video camera716, andGPS receiver720. Processing chip set718 includes a processor, memory storage, and input/output interface and a communication interface. The communication interface allows the processor to communicate with a processor withinear bud704, allowing the processor in processing chip set718 to transmit electrical signals representing acoustic information toear bud704. The communication interface of processing chip set718 may also wirelessly communicate with a collection of other devices, including a video display, a personal computer, a router, and other mobile devices. The protocol used for these communications can include any known protocol, including any variations of the 802.11 protocol.
• Ear bud704 includesouter portion730,ear canal portion732, andspeaker opening734.Ear bud704 receives a signal from processing chip set718 and converts that signal into an auditory signal through a speaker that is internal toear bud704. This auditory signal exits through speaker opening734 into the user's ear.Ear bud704 includes a battery (not shown) and a communication interface that allows it to communicate with the communication interface of processing chip set718.
• As shown inFIG. 9,neck engaging piece708 goes around a user'sneck900 to placependant706 in contact with the front of the user's neck slightly below the thyroid cartilage of the larynx, commonly referred to as the “Adam's Apple.”Ear bud704 is placed in the user's ear such thatexterior portion730 extends between thetragus900 and theanti-tragus902 of the outer ear.
• FIG. 10 provides a pictorial diagram of another embodiment of a mobile device under the present invention. InFIG. 10, the mobile device includes a watch orbracelet1000 and anear bud1002.Watch1000 includes anenclosure1001, which is mounted on awrist engaging piece1006, such as a band, designed to be secured around the user's wrist.Enclosure1001 has an interior that holds a set of electronic device, which includes a battery, a processor, memory, a communication interface, an. input/output interface, a Global Positioning Satellite receiver, a video camera, speaker, air conduction microphone, pulse sensor, oximetry sensor and temperature sensor. These devices are described in more detail inFIG. 11. The communication interface allows the processor to communicate with a processor inear bud1002 and thereby transmit acoustic information toear bud1002 and receive data from analternative sensor1018 inear bud1002. In addition, the communication interface allows for wireless communication with one or more of a router, a personal computer, and other mobile devices.Enclosure1001 includes openings corresponding to some of the electronic devices in the enclosure including pulse andoximetry meter1008,air conduction microphone1010, andvideo camera1012. Pulse andoximetry meter1008 measures the user's pulse when the user places their finger over the meter and also measures the oxygen content of the user's blood using a light source and a light sensor. The exterior of one side ofenclosure1001 also includes adisplay1004.
• Ear bud1002 includes anear portion1014 designed to be placed in a user's ear canal and aspeaker opening1016. In addition,ear bud1002 includes analternative sensor1018, which rests against the user's jaw when theear bud1002 is in the user's ear canal.
• FIG. 11 is a block diagram of amobile device1100, under several embodiments of the present invention.Mobile device1100 includes apower supply1152,microprocessor1102,memory1104, input/output (I/O)interface1106, and acommunication interface1108 for communicating with remote computers, communication networks, or other mobile devices. In one embodiment, the afore-mentioned components are coupled for communication with one another over asuitable bus1110. In addition, all of the components that require power are connected topower supply1152, which is typically a battery. InFIG. 11, the connections betweenpower supply1152 and the remaining components are not shown to avoid unnecessarily complicating the figure.
• Memory1104 may be implemented as non-volatile electronic memory such as random access memory (RAM) with a battery back-up module (not shown) such that information stored inmemory1104 is not lost when the general power tomobile device1100 is shut down. Alternatively, all or portions ofmemory1104 may be volatile or non-volatile removable memory. A portion ofmemory1104 is preferably allocated as addressable memory for program execution, while another portion ofmemory1104 is preferably used for storage, such as to simulate storage on a disk drive.
• Memory1104 includes an operating system1112,application programs1114 as well as anobject store1116. During operation, operating system1112 is preferably executed byprocessor1102 frommemory1104. Operating system1112, in one, preferred embodiment, is a WINDOWS® CE brand operating system commercially available from Microsoft Corporation. Operating system1112 is preferably designed for mobile devices, and implements database features that can be utilized byapplications1114 through a set of exposed application programming interfaces and methods. The objects inobject store1116 are maintained byapplications1114 and operating system1112, at least partially in response to calls to the exposed application programming interfaces and methods.
• Communication interface1108 represents numerous devices and technologies that allowmobile device1100 to send and receive information. In some embodiments,communication interface1108 includes a cellular phone network interface that interacts with a cellular phone network to allow calls to be placed and received. Other interfaces include a PBX telephone interface, a wireless protocol interface such as802.11 and its variants, satellite receivers and broadcast tuners to name a few.Mobile device1100 can also be directly connected to a computer to exchange data therewith. In such cases,communication interface1108 can be an infrared transceiver or a serial or parallel communication connection, all of which are capable of transmitting streaming information.
• Communication interface1108 allowsmobile device1100 to communicate withexternal servers1154 andremote device1156, including direct communication to other mobile devices.
• The computer-executable instructions that are executed byprocessor1102 to implement the present invention may be stored inmemory1104 or received acrosscommunication interface1108. These instructions are found in a computer readable medium, which, without limitation, can include computer storage media and communication media.
• Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data. Computer storage media includes, but is not limited to, RAM, ROM, EEPROM, flash memory or other memory technology, CD-ROM, digital versatile disks (DVD) or other optical disk storage, magnetic cassettes, magnetic tape, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to store the desired information and which can be accessed.
• Communication media typically embodies computer readable instructions, data structures, program modules or other data in a modulated data signal such as a carrier wave or other transport mechanism and includes any information delivery media. The term “modulated data signal” means a signal that has one or more of its characteristics set or changed in such a manner as to encode information in the signal. By way of example, and not limitation, communication media includes wired media such as a wired network or direct-wired connection, and wireless media such as acoustic, RF, infrared and other wireless media. Combinations of any of the above should also be included within the scope of computer readable media.
• Input/output interface1106 represents interfaces to a collection of input and output devices including Global Positioning Satellite (GPS)receiver1148,video camera1150,speaker1130, digit input1132 (such as one or a set of buttons, a touch screen, a trackball, a mouse pad, a roller, or a combination of these components that can be manipulated by a user's thumb or finger),display1134,air conduction microphone1136,alternative sensor1138,pulse sensor1142,oximetry sensor1144 andtemperature sensor1146. Under one embodiment,alternative sensors1138 is a bone conduction or throat conduction microphone. The devices listed above are by way of example and need not all be present onmobile device1100. In addition, other input/output devices may be attached to or found withmobile device1100 within the scope of the present invention.
• By using an air conduction microphone and an alternative sensor, embodiments of the present invention are able to provide an enhanced speech signal.FIG. 12 provides a basic block diagram of a speech processing system of embodiments of the present invention that provides the enhanced speech signal.
• InFIG. 12, aspeaker1200 generates aspeech signal1202 that is detected by anair conduction microphone1204 and analternative sensor1206. One example of an alternative sensor is a bone conduction sensor that is located on or adjacent a facial or skull bone of the user (such as the jaw bone) or on the ear of the user and that senses vibrations of the ear, skull or jaw that correspond to speech generated by the user. Another example of an alternative sensor is an infrared sensor that is pointed at and detects the motion of the user's mouth. A further example of an alternative sensor is a throat sensor that senses vibrations in the user's throat that correspond to speech generated by the user.Air conduction microphone1204 is the type of microphone that is used commonly to convert audio air-waves into electrical signals.
• Air conduction microphone1204 also receivesnoise1208 generated by one ormore noise sources1210. Depending on the type of alternative sensor and the level of the noise,noise1208 may also be detected byalternative sensor1206. However, under most embodiments of the present invention,alternative sensor1206 is typically less sensitive to ambient noise thanair conduction microphone1204. Thus, thealternative sensor signal1212 generated byalternative sensor1206 generally includes less noise than airconduction microphone signal1214 generated byair conduction microphone1204.
• Alternative sensor signal1212 and airconduction microphone signal1214 are provided to aclean signal estimator1216, which estimates aclean speech signal1218 fromalternative sensor signal1212 and airconduction microphone signal1214.Clean signal estimate1218 is provided to aspeech process1220.Clean speech signal1218 may either be a filtered time-domain signal or a feature domain vector. Ifclean signal estimate1218 is a time-domain signal,speech process1220 may take the form of a listener, a cellular phone transmitter, a speech coding system, or a speech recognition system. Ifclean speech signal1218 is a feature domain vector,speech process1220 will typically be a speech recognition system.
• The present invention utilizes several methods and systems for estimating clean speech using airconduction microphone signal1214 andalternative sensor signal1212. One system uses stereo training data to train correction vectors for the alternative sensor signal. When these correction vectors are later added to a test alternative sensor vector, they provide an estimate of a clean signal vector. One further extension of this system is to first track time-varying distortions and then to incorporate this information into the computation of the correction vectors and into the estimation of the clean speech.
• A second system provides an interpolation between the clean signal estimate generated by the correction vectors and an estimate formed by subtracting an estimate of the current noise in the air conduction test signal from the air conduction signal. A third system uses the alternative sensor signal to estimate the pitch of the speech signal and then uses the estimated pitch to identify an estimate for the clean speech signal. A fourth system uses direct filtering, in which the alternative sensor signal and the air conduction signal are used to determine one or more channel responses of the alternative sensor. The channel response(s) are then used to estimate the clean speech signal.
• Usingcommunication interfaces1108, the mobile device of the present invention is able to communicate with a large number of other devices through a large number of different networks as shown in the block diagram ofFIG. 13. InFIG. 13, threemobile devices1300,1302, and1304 are shown. These mobile devices are able to communicate with each other throughcommunication interface1108. Under one particular embodiment, an 802.11 communication protocol is used to communicate between the mobile devices. The mobile devices may communicate with each other on a one-to-one basis, such as having justmobile device1300 and1302 communicate without communicating withmobile device1304. The mobile devices may also communicate in a one-to-many configuration in which one of the mobile devices communicates to all of the other mobile devices, but the other mobile device do not communicate with each other. For example,mobile device1300 would communicate withmobile devices1302 and1304, butmobile device1302 would not communicate withmobile device1304. The mobile devices may also communicate on a many-to-many basis in which all of the mobile devices can communicate with each other.
• Each mobile device may also communicate with one or more of a plurality of networks, such ascell phone network1306,PBx phone network1308, and local area network/wide area network (LAN/WAN)1310. To communicate withcell phone network1306, the mobile devices may use a direct link to a cell phone tower throughcommunication interface1108, or may communicate with a cellular telephone using a local protocol such as 802.11. The cell phone would then relay the mobile device communications to the cell phone tower of thecell phone network1306.
• Mobile devices1300,1302, and1304 can communicate withPBx phone network1308 through a PBx hub that converts a wireless signal into a wire line signal for the PBx phone network. Any suitable protocols for such a hub may be used under the present invention. The mobile devices can communicate with LAN/WAN1310 through a wireless connection to a laptop computer, a personal computer, or a wireless router that is part of the LAN/WAN.
• Throughnetworks1306,1308, and1310, the mobile devices may communicate with other devices such asdevices1312 and1314. These other devices may comprise lap top computers, personal computers, or servers that provide services to the mobile device. Such servers include, under some embodiments, a speech recognition server that identifies text from a speech signal and/or a translation server that translates text in one language into text or audio in another language. The servers may also include a live communication server that allows for instant messaging, keeps track of presence information such as whether the user is available for meetings, and coordinates communications to allow for real time collaboration on documents during live meetings that include both audio and video communications. The servers may also include a location-based server that provides location information about the mobile device such as maps indicating the location of the mobile device relative to other points of interest.
• Because the mobile device of the present invention uses both an air conduction microphone and an alternative sensor to sense speech signals, it provides an enhanced speech signal that enables improved performance in a number of applications. Further, the combination of these microphones and alternative sensors with other devices, such as a GPS receiver, a video camera, and health sensor such as a pulse sensor, oximetry sensor and temperature sensor, allow the mobile device of the present invention to be used with multiple servers to provide integrated solutions to ease communication between multiple parties.
• FIG. 14 provides a block diagram of connections between servers and a mobile device that provide the ability to locate a person carrying a mobile device, send an instant message to the mobile device to request a meeting, and utilize a live communication server to hold the meeting.
• InFIG. 14,mobile device1300 is equipped with a GPS receiver. Using the information from the GPS receiver, mobile device1400 periodically communicates its location to a location-basedserver1402 through anetwork connection1404 such as a cell phone network or a LAN/WAN. This allows a remote user to use a locateperson application1408 on the remote user'scomputing device1406 to obtain location information about mobile device1400 from location-basedserver1402 through anetwork connection1410. This location information can include an address or a graphical representation of the location of the mobile device such as showing the location on a map.
• Throughnetwork connection1404, which may be the same network connection used to connect to location-basedserver1402 or a different network connection, mobile device1400 is also able to communicate with alive communication server1412. Through this connection, a user holding mobile device1400 is able to indicate whether they are available and on-line, and whether they are in the office or out of the office. In general, this is known as “presence” information.
• In addition, mobile device1400 is able to send and receive instant messages throughlive communication server1412. These messages pass to and fromremote user device1406, which uses aninstant message application1414 to send and receive the messages. This would, for example, allow a remote user to request that the user of mobile device1400 join a live meeting.
• The remote user may establish a live meeting using alive meeting application1418, which uses the services provided bylive communication server1412 to allow multiple clients to communicate with audio and video signals and to manipulate shared documents such that changes to the document made on mobile device1400 appear in real time on the display of the remote user'scomputing device1406.
• Using a wireless connection, mobile device1400 is able to communicate with alaptop computer1420. Using the enhanced speech signal provided by having both an air conduction microphone signal and an alternative sensor signal, mobile device1400 is able to send speech signals representing commands tolaptop1420. A command/control application1422 inlaptop1420 forwards the speech signals to aspeech recognition server1424 through anetwork connection1426.Speech recognition server1424 converts the speech signal into text and returns the text to command/control application1422. Based on the recognized command, command/control application1422 initiates one or more applications1428 and controls their operation.
• One of the applications initiated through command/control unit1422 can include a live meeting application that allows the user of the mobile device to join the live meeting generated by theremote user1406.Laptop1420 can communicate withlive communication server1412 through anetwork connection1430. The user may interact with the live meeting directly onlaptop1420 or by issuing speech commands through mobile device1400 tolaptop1420. In addition,laptop1420 can relay speech signals produced by mobile device1400 throughlive communication server1412 toremote user device1406 thereby providing the audio portion of the live meeting. Using the live meeting application, the user of the mobile device is able to share audio, video and documents with the remote user. This includes the ability for both the user of the mobile device and the remote user to manipulate the same document in real time.
• Thus, using the block diagram ofFIG. 14, a remote user is able to determine that the person wearing mobile device1400 has not boarded a plane yet but is still in an airport. The remote user can then send an instant message to the wearer of the mobile device1400 asking the wearer of the mobile device to join a live meeting. When the wearer of the mobile device is able to join the meeting, they can turn on theirlaptop1420, issue commands through mobile device1400 and join the live meeting established byremote user1406. During the meeting, the user may speak through mobile device1400 to provide audio input for the live meeting. Because the speech is enhanced in mobile device1400, the commands provided tolaptop1420 operate more efficiently and reliably, and the speech provided by mobile device1400 is more intelligible during the live meeting.
• FIG. 15 provides an alternative embodiment in which the mobile device of the present invention is used by a dispatcher to assign jobs to one or more workers, and to interact with the workers to provide them information necessary to perform the jobs. In particular, a dispatcher wears amobile device1500 inFIG. 15. The dispatcher receives phone calls from customers over aPBx phone network1504, which communicates withmobile device1500 through aPBx base station1502. In particular,PBx base station1502 provides a wireless connection tomobile device1500 and converts communications along the wireless connection into an analog signal that can be carried onPBx phone network1504.
• After receiving the job request, the dispatcher determines which of a plurality of field workers is available and is closest to the job site. To determine which workers are available, the dispatcher speaks intomobile device1500 to generate speech commands that are provided to a command/control unit1506.Command control unit1506 may be present withinmobile device1500 or may be in a separate device such as a laptop or a personal computer. Command/control until1506 converts the speech signal into one or more commands. Under one embodiment, command/control unit1506 performs this conversion by passing the speech signal to aspeech recognition server1508 through anetwork1510.Speech recognition server1508 converts the speech signal into text representing the command and returns to the text to command/control unit1506.
• To determine whether a worker is available, the command provided tocommand control unit1506 would be a commanded to check the “presence” status of each worker using apresence application1512. The presence application communicates with alive communication server1514 through anetwork connection1516. The live communication server stores and updates the presence status of each worker. Specifically, each worker has a mobile device, such asmobile devices1518,1520, and1522, which are connected to thelive communication server1514 through anetwork connection1524. Note that although asingle network connection1524 is shown inFIG. 15, each mobile device may be connected through different network connections and even different types of network connections. Throughnetwork connection1524,mobile devices1518,1520, and1522 are able to update the presence status of each of the workers associated with the mobile devices.
• For those workers that are available, the dispatcher usesmobile device1500 to find the current location of each worker by issuing a speech command to command/control1506 to open a locateperson application1530. Locateperson application1530 communicates throughnetwork connection1532 to a location-basedserver1534. Location-basedserver1534 keeps track of the location ofmobile devices1518,1520, and1522 by receiving location information through anetwork1536.Network1536 can include a cell phone network, in which the location of the mobile device is determined by which tower in the cell phone network the mobile device is communicating through. In other embodiments, eachmobile device1518,1520, and1522 can include a GPS receiver and the position information determined by the GPS receivers can be communicated throughnetwork1536 to location-basedserver1534.
• In response to the request by locateperson application1530, location-basedserver1534 can provide location information for each of the mobile devices. This location information may be in the form of an address or in the form of a graphical representation in which the location of each of the mobile devices is shown on a map.
• Based on the location of each of the workers, the dispatcher selects one of the workers to assign the job to. Under one embodiment, the dispatcher sends an instant message to that worker by issuing a speech command through command/control1506 to initiate aninstant message application1538 and to create an instant message that is routed throughnetwork1516,live communication server1514,network1524 to reach one of themobile devices1518,1520, and1522. In another embodiment, the dispatcher issues a command throughmobile device1500 and command/control1506 to initiate anassistant application1540, which accesses acontacts database1542 to locate the phone number of the mobile device associated with the worker. Using this phone number,mobile device1500 connects to the mobile device of the worker through acell phone network1544. Using this cellular phone connection, the dispatcher instructs the worker to proceed to the job site.
• If the worker needs directions to the job site, the dispatcher issues a voice command throughmobile device1500 to instantiate adirections application1546, which uses location-basedserver1534 to provide directions to one of the workers throughmobile device1518,1520, and152. In particular, location-basedserver1534 uses the location of the mobile device and the location of the job as provided throughmobile device1500 by the dispatcher, to generate a map and driving directions for reaching the location of the job site from the worker's current location.
• Once the worker has arrived at the location, he can use his mobile device, such asmobile devices1518,1520, and1522 to establish a live meeting with the dispatcher to receive specifications for the job. This can be achieved by having the dispatcher usemobile device1500 to invoke a live meeting application, which communicates to livecommunication server1514 to allow for real time collaboration and the sharing of documents such as order forms and plans for the projects.
• Under other embodiments of the present invention, the mobile device is capable of switching between various modes of communication. For example, inFIG. 16, amobile device1600 may initially broadcast information directly to othermobile devices1602 and1604 on a one-to-many basis. For example,mobile device1600 could be providing information such as audio, video, GPS position information, and health information such as pulse, oximetry and temperature tomobile devices1602 and1604. During this communication mode,mobile device1604 can use the position information frommobile device1600 to obtain a graphical representation of the position of the wearer ofmobile device1600. In one specific embodiment,mobile device1604 can provide the location information frommobile device1600 to a location-basedserver1608 through a wireless connection tonetwork1610. Location-basedserver1608 would then use the position information to generate a map that is returned tomobile device1604. In such an embodiment, the wireless connection tonetwork1610 can be made through a router, a personal computer, or a laptop computer.
• Mobile device1600 can switch from the peer-to-peer communication described above to communication with one or more servers through anetwork connection1612. For example, if the wearer ofmobile device1600 encounters an injured party during a workout, the wearer can switchmobile device1600 from the one-to-many communications with the mobile devices to a communication throughnetwork1612. Using the network connection, the wearer ofmobile device1600 can access web pages stored on aweb server1614, which is connected tonetwork1612, to locate and communicate with arescue team1616.
• Oncerescue team1616 has been contacted, it can initiate arescue application1620 to collect information frommobile device1600 to help in the rescue of the injured party. This information can include GPS position information provided bymobile device1600 to a location-basedserver1618 throughnetwork1612.Rescue application1620 can send a request to location-basedserver1618 to obtain a graphical representation of the position ofmobile device1600, thereby making it easier forrescue team1616 to locate the wearer of the mobile device.Rescue application1620 can also use alive communication server1622 to share information with the wearer ofmobile device1600, such as the current position of the rescue team, and the expected time of arrival, as well as instructions for caring for the injured person. These instructions can include videos indicating the manner of treating the injured person as well as video captured bymobile device1600 of the injured person.
• If the injured person is also wearing a mobile device, such asmobile device1624, that mobile device can be included in the meeting throughlive communication server1622 so that the mobile device can provide health information about the injured party.
• If the injuries appear to be serious, the rescue team can ask a health care team at ahospital1626 to join the live meeting using aremote emergency application1628. This remote emergency application can collect the health status information provided bymobile device1624 and allow the health care team to provide audio and visual instructions to therescue team1616.Remote emergency application1628, can also allow the health care team to begin scheduling needed resources within the hospital to care for the patient such as diagnostic equipment and operating rooms.
• The mobile device of the present invention can also be used in a gaming context to allow a user to communicate with team members and opponents in a game. As shown inFIG. 17, players, such asplayers1700 and1702 wearing respectivemobile devices1704 and1706 interact with agaming base station1708.
• Under one embodiment, aremote player1710 determines thatplayer1700 is available by accessing aplayer list application1712, which connects to alive communication server1714 through anetwork connection1713 to determine the presence, or availability, ofplayer1700 through a connection betweenmobile device1704 andlive communication server1714 over anetwork1716. Iflive communication server1714 indicates thatplayer1700 is available,player1710 may send an instant message throughlive communication server1714 tomobile device1704 to request that the player join in a game. Under one embodiment, this game is controlled by agame server1718 which is connected togaming base station1708 through anetwork1720 and toplayer1710 throughnetwork1722.
• During gaming, audio and video fromplayers1700 and1702 is captured bymobile devices1704 and1706, respectively, and provided to gaming base station/PC1708 through a wireless connection. This audio and/or video is provided throughnetwork connection1720 togame server1718 and is forwarded toplayer1710 bygame server1718.
• Under one embodiment, to reduce the bandwidth of the audio information distributed throughnetwork1720,mobile devices1704 and1706 filter out all sounds that do not occur while the player associated with the mobile device is speaking. In particular, by using the alternative sensor in the mobile device, the mobile device is able to determine when the player is actually speaking. When the player is not speaking, the mobile device does not transmit any audio data. As a result, speech signals from the other player who is present in the room or speech signals generated by the gaming station through aspeaker1724 are not output as audio data bymobile devices1704 and1706. This reduces the amount of information that is sent togaming base station1708 and thus reduces the amount of information that is passed throughnetwork1720. By reducing the amount of information output bymobile devices1704 and1706, the present invention reduces the power consumption ofmobile devices1704 and1706 by not requiring the mobile devices to filter and broadcast unwanted audio data. Another more direct way of saving power consumption is to turn off the processing (within the microphone) when the user is not speaking.
• The mobile device of the present invention also allows for recording and storing better quality audio, especially speech signals, which can later be reviewed.FIG. 18 provides a block diagram of a system that allows for storage and review of audio and video data.
• InFIG. 18,mobile device1800 stores audio and video data locally in an audio/video memory storage1802. Using a wireless connection to a personal computer1804, the audio and video data stored inmemory storage1802 can be downloaded to PC1804 to becomedownloaded data1806. When the audio and video data is stored in audio/video storage1802,mobile device1800 includes a time stamp indicating the time and date when the audio and video was captured as well as a position stamp indicating the position ofmobile device1800 when the audio and video data was collected. Under one embodiment, the time stamp is generated from aclock1801 and the position stamp is generated by a GlobalPositioning Satellite receiver1803. The time stamps and position stamps are downloaded with the respective audio and video clips into downloadeddata1806.
• Using the time stamps, a time-basedorganizer1808 is able to organize the data based on the time to form time-organizeddata1810. A location-basedorganizer1812 organizes the audio and video data based on the position stamp associated with the data to form location-organizeddata1814. The user can then use the display of personal computer1804 to review the time-organizeddata1810 or the location-organizeddata1814.
• The audio data in downloadeddata1806 may also be transcribed by atranscription application1816. To transcribe the audio data,transcription application1816 may use aspeech recognition server1818, which may be found locally on personal computer1804 or may be connected to personal computer1804 through anetwork connection1820.Transcription application1816 sends the audio data representing the audio signal tospeech recognition server1818, which converts the audio data into text. The text is then returned totranscription application1816, which uses the text to produce atranscript1822. Becausemobile device1800 uses an alternative sensor and an air conduction microphone to collect speech data, the recognition performed byspeech recognition server1818 is much improved, and thetranscript1822 better reflects the actual speech collected bymobile device1800.
• Once thetranscripts1822 have been formed, the user can invoke asearch application1824 that can search thetranscripts1822 for keywords to locate particular conversations.
• Mobile devices of the present invention may also be used to locate and communicate with children and elderly persons who are wearing a mobile device. For example, inFIG. 19,mobile device1900 is worn by a child or an elderly person. The mobile device provides GPS position information through anetwork1902 to a location-basedserver1904. Using apersonal computer1906, another user may contact location-basedserver1904 to obtain position information for the wearer ofmobile device1900. This position information can be provided in the form of an address or a graphical representation of a map indicating the location of the wearer within the map. The other user may also contact the wearer of the mobile device using aphone1908 through aphone network1910 that communicates tomobile device1900. An example of such a phone network would be a cellular phone network. By using an alternative sensor and an air conduction microphone sensor,mobile device1900 provides a better speech signal for communicating throughphone network1910. This is especially important when the wearer ofmobile device1900 is a child or an elderly person, since the speech signals for children and the elderly tend to have lower amplitudes, and thus are harder to discern in noisy environments.
• The mobile device of the present invention can also be used to improve automatic translation services. For example, inFIG. 20, amobile device2000 receives speech input from a wearer of themobile device2002 and aforeign speaker2004. Because mobile device is worn bywearer2002,mobile device2000 can distinguish between speech produced bywearer2002 and speech produced byforeign speaker2004. The speech produced byforeign speaker2004 can thus be automatically routed bymobile device2000 to atranslation server2006 through anetwork connection2008.Translation server2006 can then return either translated audio or translated text of the speech produced byforeign speaker2004. Using a display onmobile device2000 or a speaker onmobile device2000,wearer2002 can thus understand the content of the speech offoreign speaker2004. Becausemobile device2000 is able to automatically separate the two speech signals, the translation is more easily obtained.
• Mobile device2000 could also share the foreign speech, the translated speech or translated text, and a video of the foreign speaker captured bymobile device2000 with aremote user2010. Under one embodiment, this information is shared through alive communication server2012, which is connected toremote user2010 through anetwork connection2014 and tomobile device2000 through anetwork connection2008. Using the connection throughlive communication server2012,remote user2010 is able to speak withforeign speaker2004 and is able to provide video data toforeign speaker2004 through a display onmobile device2000. Speech provided byremote user2010 may be routed bymobile device2000 totranslation server2006 to be translated into the language of the foreign speaker. An audio signal based on this translation is then provided to the foreign speaker through a speaker inmobile device2000.
• FIG. 21 provides an alternative embodiment of the present invention for improving automatic translation services. InFIG. 21, amobile device2100 receives speech input from a wearer of themobile device2102 and aforeign speaker2104. Because mobile device is worn bywearer2102,mobile device2100 can distinguish between speech produced bywearer2102 and speech produced byforeign speaker2104. The speech produced byforeign speaker2104 can thus be identified in communications betweenmobile device2100 and anothermobile device2105.Mobile device2105 can take the speech data that has been identified as coming from a foreign speaker bymobile device2100 and provide it to atranslation server2106 through anetwork connection2108.Translation server2106 can then return either translated audio or translated text of the speech produced byforeign speaker2104. Using a display onmobile device2100 or a speaker onmobile device2100,wearer2102 can thus understand the content of the speech offoreign speaker2104. Becausemobile device2100 is able to automatically separate the two speech signals, the translation is more easily obtained.
• Mobile device2105 could also share the foreign speech, the translated speech or translated text, and a video of the foreign speaker captured bymobile device2100 with a plurality ofremote users2110,2120, and2130. Under one embodiment, this information is shared through alive communication server2112, which is connected toremote users2110,2120, and2130 through anetwork connection2114 and tomobile device2105 through anetwork connection2108. Using the connection throughlive communication server2112,remote users2110,2120, and2130 are able to speak withforeign speaker2104 and are able to provide video data toforeign speaker2104 through a display onmobile device2100. Speech provided byremote users2110,2120, and2130 may be routed bymobile device2105 totranslation server2106 to be translated into the language of the foreign speaker. An audio signal based on this translation is then provided to the foreign speaker through a speaker inmobile device2100.
• Mobile devices of the present invention may also communicate in a peer-to-peer mode with other devices such as printers, appliances, media recorders, media players, and automobiles.FIG. 22 provides a diagram showing amobile device2200 in communication with other devices such asdevices2202,2204, and2206.
• Under one particular embodiment, an 802.11 communication protocol is used to communicate between the mobile device and the other devices. The mobile device may communicate with the other devices on a one-to-one basis, such as havingmobile device2200 communicate withdevice2202 without communicating withdevices2204 and2206. The mobile device may also communicate in a one-to-many configuration in which the mobile device or one of the other devices communicates to the mobile device and all of the other devices, but the other devices do not communicate with each other. For example,mobile device2200 would communicate withdevices2202 and2204, butdevice2202 would not communicate withdevice2204. The devices may also communicate on a many-to-many basis in which all of the devices and the mobile device can communicate with each other.
• Although the present invention has been described with reference to particular embodiments, workers skilled in the art will recognize that changes may be made in form and detail without departing from the spirit and scope of the invention.

Claims (20)

1. A mobile device comprising:

an air conduction microphone that converts acoustic waves representative of a portion of speech into an electric microphone signal;

an alternative sensor that detects information representative of the portion of speech separate from the electronic microphone signal and provides an electric alternative sensor signal comprising information representative of the portion of speech; and

a communication interface that permits the mobile device to communicate directly with other mobile devices.

2. The mobile device ofclaim 1 wherein the communication interface permits multiple types of communication with other mobile devices.

3. The mobile device ofclaim 2 wherein one of the multiple types of communication comprises one-to-one communication with one other mobile device even when more than one other mobile device is available for communication.

4. The mobile device ofclaim 2 wherein one of the multiple types of communication comprises one-to-many communication with a plurality of other mobile devices.

5. The mobile device ofclaim 2 wherein one of the multiple types of communication comprises many-to-many communication.

6. The mobile device ofclaim 1 wherein the communication interface further permits communication to a network.

7. The mobile device ofclaim 6 wherein the communication interface further permits communication with a server on the network.

8. The mobile device ofclaim 7 wherein the communication with the server comprises audio and video.

9. The mobile device ofclaim 8 wherein communication with the server further comprises data corresponding to an image of a document that is shared with another computing device.

10. The mobile device ofclaim 7 wherein the mobile device further comprises a global positioning satellite receiver that is capable of generating a position value indicative of the position of the mobile device.

11. The mobile device ofclaim 10 wherein communication with a server comprises providing the position value to the server.

12. The mobile device ofclaim 7 wherein the server hosts a speech recognition program and wherein communicating with the server comprises providing audio data to the server and receiving recognized text from the server.

13. The mobile device ofclaim 7 wherein the server hosts a translation program and wherein communicating with the server comprises providing content in one language to the server and receiving a translation in another language from the server.

14. A method in a mobile device, the method comprising:

receiving an air conduction microphone signal that comprises information representative of a frame of speech;

receiving an alternative sensor signal that comprises information representative of the frame of speech;

estimating an enhanced clean speech value based on the air conduction microphone signal for the frame of speech and the alternative sensor signal for the frame of speech; and

providing the enhanced clean speech value directly to another mobile device.

15. The method ofclaim 14 wherein providing the enhanced clean speech value directly to another mobile device comprises providing the enhanced clean speech value during a one-to-one communication between the mobile device and the other mobile device.

16. The method ofclaim 14 wherein providing the enhanced clean speech value directly to another mobile device comprises providing the enhanced clean speech value during a one-to-many communication between the mobile device and a plurality of other mobile devices.

17. The method ofclaim 14 wherein providing the enhanced clean speech value directly to another mobile device comprises providing the enhanced clean speech value during a many-to-many communication between a plurality of mobile devices.

18. The method ofclaim 14 further comprising determining a position for the mobile device and communicating the position of the mobile device from the mobile device to a server.

19. The method ofclaim 18 further comprising using the position of the mobile device to generate a map and communicating the map from the server to another computing device.

20. The method ofclaim 14 further comprising using a translation service on a server to translate text from one language to another language based on data sent from the mobile device to the server and returning text from the server to the mobile device, the text representing the translation of the text.

Images