US20110184740A1 - Integration of Embedded and Network Speech Recognizers - Google Patents

Abstract

A method, computer program product, and system are provided for performing a voice command on a client device. The method can include translating, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command and generating a first query result using the first machine-readable voice command to query a client database. In addition, the audio stream can be transmitted to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer. Further, the method can include receiving a second query result from the remote server device, where the second query result is generated by the remote server device using the second machine-readable voice command and displaying the first query result and the second query result on the client device.

Description

CROSS REFERENCE TO RELATED APPLICATION
• This application claims the benefit of U.S. Provisional Application No. 61/298,251 (SKGF Ref. No. 2525.2310000), filed Jan. 26, 2010, titled “Integration of Embedded and Network Speech Recognizers,” which is incorporated herein by reference in its entirety.
BACKGROUND
• 1. Field
• This description generally relates to the field of speech recognition.
• 2. Background
• Speech recognition systems in mobile devices allow users to communicate and provide commands to the mobile device with minimal usage of input controls such as, for example, keypads, buttons, and dials. Some speech recognition tasks can be a complex process for mobile devices, requiring an extensive analysis of speech signals and search of word and language statistical models. This is because mobile devices typically have limited computational, memory, and battery resources. As such, more complex speech recognition tasks are oftentimes offloaded to speech recognition systems located externally to the mobile device such as, for example, speech recognition systems in network servers.
• Since more complex speech recognition tasks are performed on network servers and not on the mobile device, the results of the voice command may be limited to data stored in the network server. For these speech recognition tasks, the mobile device user does not have the benefit of viewing query results that may correspond to the voice command based on data stored in the mobile device. In addition, the delay time in transferring the voice command to the network server, performing the speech recognition operation at the network server, and transferring the query result from the network server to the mobile device can be significant. Significant delay time in the execution of applications on mobile devices, such as speech recognition tasks, can lead to a poor user experience.
• Methods and systems are needed for performing speech recognition tasks on a client device, such as a mobile device, to overcome the above-noted limitations of speech recognition systems in mobile applications.
SUMMARY
• Embodiments include a method for performing a voice command on a client device. The method includes translating, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command and generating a first query result using the first machine-readable voice command to query a client database. In addition, the audio stream can be transmitted to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer. Further, the method includes receiving a second query result from the remote server device, where the second query result is generated by the remote server device using the second machine-readable voice command to query a remote server database, and displaying the first query result and the second query result on the client device. The transmission of the audio stream to the remote server device and the transmission of the second query result from the remote server device to the client device can occur simultaneously, substantially at the same time as, or a time period that overlaps with the generation of the first query result by the client device.
• Embodiments additionally include a computer program product that includes a computer-usable medium with computer program logic recorded thereon for enabling a processor to perform a voice command on a client device. The computer program logic includes the following: first computer readable program code that enables a processor to translate, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command; second computer readable program code that enables a processor to generate a first query result using the first machine-readable voice command to query a client database; third computer readable program code that enables a processor to transmit the audio stream to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer; fourth computer readable program code that enables a processor to process a second query result from the remote server device, wherein the second query result is generated by the remote server device using the second machine-readable voice command; and, fifth computer readable program code that enables a processor to a control a display of the first query result and the second query result on the client device.
• Embodiments further include a system for performing a voice command on a client device. The system includes a first speech recognizer device, a client query manager, and a display device. The first speech recognizer device is configured to translate an audio stream of a voice command to a first machine-readable voice command. The client query manager is configured to perform the following functions: generate a first query result using the first machine-readable voice command to query a client database; transmit the audio stream to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer; and, receive a second query result from the remote server device, where the second query result is generated by the remote server device using the second machine-readable voice command to query a remote server database. Further, the display device is configured to display the first query result and the second query result on the client device.
• Further features and advantages of embodiments described herein, as well as the structure and operation of various embodiments, are described in detail below with reference to the accompanying drawings. It is noted that the embodiments described below are not limited to the specific embodiments described herein. Such embodiments are presented herein for illustrative purposes only. Additional embodiments will be apparent to persons skilled in the relevant art based on the teachings contained herein.
BRIEF DESCRIPTION OF THE DRAWINGS
• The accompanying drawings, which are incorporated herein and form a part of the specification, illustrate embodiments and, together with the description, further serve to explain the principles of the embodiments and to enable a person skilled in the relevant art to make and use the embodiments.
• FIG. 1 is an illustration of an exemplary communication system in which embodiments can be implemented.
• FIG. 2 is an illustration of an embodiment of a client device.
• FIG. 3 is an illustration of an embodiment of a server device.
• FIG. 4 is an illustration of an embodiment of a method for performing a voice command on a client device.
• FIGS. 5(a)-5(c) are illustrations of an exemplary user interface on a mobile phone in accordance with embodiments.
• FIG. 6 is an illustration of an embodiment of a method for performing a voice command on a client device.
• FIGS. 7(a) and8(b) are illustrations of another exemplary user interface on a mobile phone in accordance with embodiments.
• FIG. 8 is an illustration of an embodiment of another method for performing a voice command on a client device.
• FIG. 9 is an illustration of an embodiment of another method for performing a voice command on a client device.
• FIGS. 10(a)-10(e) are illustrations of an of yet another exemplary user interface on a mobile phone in accordance with embodiments.
• FIG. 11 is an illustration of an example computer system in which embodiments can be implemented.
DETAILED DESCRIPTION
• The following detailed description refers to the accompanying drawings that illustrate exemplary embodiments. Other embodiments are possible, and modifications can be made to the embodiments within the spirit and scope of this description. Therefore, the detailed description is not meant to limit the embodiments described below.
• It would be apparent to one of skill in the relevant art that the embodiments described below can be implemented in many different embodiments of software, hardware, firmware, and/or the entities illustrated in the figures. Any actual software code with the specialized control of hardware to implement embodiments is not limiting of this description. Thus, the operational behavior of embodiments will be described with the understanding that modifications and variations of the embodiments are possible, given the level of detail presented herein.
• FIG. 1 is an illustration of anexemplary communication system100 in which embodiments can be implemented.Communication system100 includes aclient device110 that is communicatively coupled to aserver device130 via anetwork120.Client device110 can be, for example and without limitation, a mobile phone, a personal digital assistant (PDA), a laptop, or other similar types of mobile devices.Server device130 can be, for example and without limitation, a telecommunications server, a web server, or other similar types of database servers. In an embodiment,server device130 can have multiple processors and multiple shared or separate memory components such as, for example and without limitation, one or more computing devices incorporated in a clustered computing environment or server farm. The computing process performed by the clustered computing environment, or server farm, may be carried out across multiple processors located at the same or different locations. In an embodiment,server device130 can be implemented on a single computing device. Examples of computing devices include, but are not limited to, a central processing unit, an application-specific integrated circuit, or other type of computing device having at least one processor and memory. Further,network120 can be, for example and without limitation, a wired (e.g., ethernet) or a wireless (e.g., Wi-Fi and 3G) network that communicatively couplesclient device110 toserver device130.
• FIG. 2 is an illustration of an embodiment ofclient device110.Client device110 includes aspeech recognizer210, aclient query manager220, amicrophone230, aclient database240, and adisplay device250. In an embodiment,microphone230 is coupled tospeech recognizer210, which is coupled toclient query manager220.Client manager220 is also coupled toclient database240 anddisplay250, according to an embodiment.
• In an embodiment,speech recognizer210 andclient query manager220 can be implemented in software, firmware, hardware, or a combination thereof. Embodiments ofspeech recognizer210 andclient query manager220, or portions thereof, can also be implemented as computer-readable code executed on one or more computing devices capable of carrying out the functionality described herein. Examples of computing devices include, but are not limited to, a central processing unit, an application-specific integrated circuit, or other type of computing device having at least one processor and memory.
• In an embodiment,microphone230 is configured to receive an audio stream corresponding to a voice command and to provide the voice command tospeech recognizer210. The voice command can be generated from an audio source such as, for example and without limitation, a mobile phone user, according to an embodiment. In turn,speech recognizer210 is configured to translate the audio stream to a machine-readable voice command, according to an embodiment. Methods and techniques to translate the audio stream to the machine-readable voice command are known to a person of ordinary skill in the relevant art. Examples of these methods and techniques can be found in commercial speech recognition software such as Dragon Naturally Speaking Software and MacSpeech Software, both by Nuance Communications, Inc.
• Based on the machine-readable voice command, in an embodiment,client query manager220queries client database240 to generate a query result. In an embodiment,client database240 contains information that is locally stored inclient device110 such as, for example and without limitation, telephone numbers, address information, and results from previous voice commands (described in further detail below). Based on the description herein, a person of ordinary skill in the relevant art will recognize that other data stored inclient database240 can provide query results to embodiments described herein.
• In an embodiment,client query manager220 also coordinates a transmission of the audio stream corresponding to the voice command toserver device130 vianetwork120 ofFIG. 1. The audio stream can be transmitted toserver device130 in multiple types of audio file formats such as, for example and without limitation, a WAVE audio format. Afterserver device130 processes the audio stream, which will be described in further detail below,client query manager220 coordinates a reception of a query result fromserver device130 vianetwork120. The transmission of data to and reception of data fromserver device130 can be performed using a transceiver (not shown inFIG. 2), which is known by a person of ordinary skill in the relevant art.
• Client query manager220 ofFIG. 2 coordinates the transmission of the audio stream toserver device130 simultaneously, substantially the same time, or in a parallel manner as it queriesclient database240, according to an embodiment. As a result, in an embodiment, the query result fromserver device130 can be received byclient query manager220 and displayed ondisplay device250 at substantially the same time as, in parallel with, or soon after the query result fromclient device110. In the alternative, depending on the computation time forclient query manager220 to queryclient database240 or the complexity of the voice command, the query result fromserver device130 can be received byclient query manager220 and displayed ondisplay device250 prior to the display of a query result fromclient database240, according to an embodiment.
• In reference toFIG. 2, in an embodiment,display device250 is configured to display the query results fromclient database240 and fromserver device130. These query results are stored inclient database240 and may be retrieved at a later time based on a future voice command that is substantially the same as or substantially similar to the voice command used to generate the query results, according to an embodiment.
• FIG. 3 is an illustration of an embodiment ofserver device130.Server device130 includes aspeech recognizer310, aserver query manager320, and aserver database330. In an embodiment,speech recognizer310 is coupled toserver query manager320, which is coupled toserver database330.
• In an embodiment,speech recognizer310 andserver query manager320 can be implemented in software, firmware, hardware, or a combination thereof. Embodiments ofspeech recognizer310 andserver query manager320, or portions thereof, can also be implemented as computer-readable code executed on one or more computing device capable of carrying out the functionality described herein. Examples of computing devices include, but are not limited to, a central processing unit, an application-specific integrated circuit, or other type of computing device having at least one processor and memory.
• As described above, with respect toFIG. 2,server device130 receives an audio stream corresponding to a voice command fromclient device110. In an embodiment,server query manager320 coordinates the reception of the audio stream fromclient device110 via a transceiver (not shown inFIG. 3) and transfer of the audio stream tospeech recognizer310. In turn,speech recognizer310 is configured to translate the audio stream to a machine-readable voice command, according to an embodiment of the present.
• In an embodiment,speech recognizer310 is configured to translate both simple speech recognition tasks, as well as more complex speech recognition tasks than those tasks translated byspeech recognizer210 inclient device110. This is becausespeech recognizer310 has more computational and memory resources thanspeech recognizer210 to translate more complex voice commands to corresponding machine-readable voice commands, according to an embodiment. Methods and techniques to process complex speech recognition tasks are known to a person of ordinary skill in the relevant art.
• Based on the machine-readable voice command translated byspeech recognizer310, in an embodiment,server query manager320queries server database330 to generate a query result. In an embodiment,server database330 contains a wide array of information such as, for example and without limitation, text data, image data, and video. Based on the description herein, a person of ordinary skill in the relevant art will recognize that other data stored inserver database330 can provide query results to embodiments described herein.
• After a query result is retrieved fromserver database330,server query manager320 coordinates a transmission of the query result toclient device110 vianetwork120 ofFIG. 1. The transmission of data to and the reception of data fromclient device110 can be performed using a transceiver (not shown inFIG. 3), which is known by a person of ordinary skill in the relevant art.
• FIG. 4 is an illustration of an embodiment of amethod400 for performing a voice command on a client device.Method400 can occur using, for example,client device110 incommunication system100 ofFIG. 1. Unlike speech recognition systems that offload more complex voice commands to a server device for processing and returns a corresponding query result to the client device, a speech recognition system performing in accordance withmethod400 processes both simple and complex voice commands on the client device as well as the server device. The query results generated by both the client device and the server device provide information from a client database and a server database, respectively. As a result, the user of the client device receives the benefit of viewing query results that may correspond to the voice command based on data stored on the client device as well as data stored on the server device.
• For ease of explanation,communication system100 will be used to facilitate in the description ofmethod400. However, based on description herein, a person of ordinary skill in the relevant art will recognize thatmethod400 can be executed on other communication systems. These other communication systems are within the scope and spirit of the embodiments described herein.
• Further, for ease of explanation,method400 will be described in the context of a mobile phone (e.g.,client device110 ofFIG. 1) with a mobile phone user as the audio source of the voice command. The mobile phone is communicatively coupled to a network server (e.g.,server device130 ofFIG. 1) via a communications network (e.g.,network120 ofFIG. 1). Based on the description herein, a person of ordinary skill in the relevant art will recognize thatmethod400 can be executed on other types of client devices such as, for example and without limitation, a PDA and a laptop and with other audio sources such as, for example and without limitation, a radio and a computer. These other types of client devices and audio sources are within the scope and spirit of the embodiments described herein.
• Instep410, an audio stream of a voice command is translated into a machine-readable voice command with a speech recognizer located on the mobile phone. As described above, with respect toFIG. 2,speech recognizer210 translates the audio stream received bymicrophone230.
• Instep420, a query is made to a database of the mobile phone to generate a query result based on the machine-readable voice command generated fromstep410. In reference toFIG. 2, based on the machine-readable voice command translated byspeech recognizer210,client query manager220queries client database240 to generate the query result.
• FIGS. 5(a)-(c) are illustrations of an exemplary user interface (UI)510 on a mobile phone in accordance with embodiments described herein. These illustrations are used to help facilitate in the explanation ofsteps410 and420 ofFIG. 4.
• With respect toFIG. 5(a),mobile phone UI510 prompts the mobile phone user for a voice command. In this example, the mobile phone user provides “Barry Cage” as the voice command. In turn, in accordance withstep410, the mobile phone translates the audio stream of the voice command into a machine-readable voice command using its embedded speech recognizer (e.g.,speech recognizer210 ofFIG. 2). A query manager on the mobile phone (e.g.,client query manager220 ofFIG. 2) queries the mobile phone's database for “Barry Cage.”
• With respect toFIG. 5(b), the mobile phone's query manager queries a contact list database for the name “Barry Cage” and finds aquery result520. Based on the description herein, a person of ordinary skill in the relevant art will recognize that other databases on the mobile phone can be queried to generate the query result such as, for example and without limitation, call log information, music libraries, and calendar listings.
• With respect toFIG. 5(c), the mobile phone user can selectquery result520 to viewcontact information530 corresponding to the voice command.
• In reference toFIG. 4, instep430, the audio stream of the voice command is transmitted to a network server, where the voice command is translated to a machine-readable voice command with a speech recognizer located on the network server. As described above, with respect toFIG. 2,client query manager220 coordinates a transmission of the audio stream toserver device130.
• Instep440, a query result is received from the network server, where the query result is generated from a query made to a server database based on the machine-readable voice command fromstep430. With respect toFIG. 3,speech recognizer310 translates the voice command to the machine-readable voice command. Based on the machine-readable voice command,server query manager320queries server database330 to generate the query result. This query result is then transmitted fromserver device130 toclient device110 vianetwork120.
• In an embodiment, as illustrated inmethod600 ofFIG. 6, the transmission of the audio stream to the network server (step430) and the reception of the query result from the network server (step440) can be performed simultaneously with, substantially at the same time as, or to overlap with the translation of the audio stream of the voice command by the mobile phone (step410) and query of the database on the mobile phone (step420). As a result, in an embodiment, the query result from the network server can be received by and displayed on the mobile phone at substantially the same time as, in parallel with, or soon after a display of the query result from the database of the mobile phone. In the alternative, depending on the computation time to query the mobile phone's database or the complexity of the voice command, the query result from the network server can be received by and displayed on the mobile phone prior to the display of the query result from the mobile phone's database, according to an embodiment.
• Instep450 ofFIG. 4, the query result fromstep420 and the query result fromstep440 are displayed on the mobile phone. In an embodiment, the query results fromsteps420 and440 are stored in the database of the mobile phone and may be displayed based on a future voice command by the mobile phone user.
• FIGS. 7(a) and7(b) are illustrations of anexemplary UI710 on a mobile phone in accordance with embodiments described herein. These illustrations are used to help facilitate in the explanation of steps430-450 ofFIG. 4.
• Similar toFIG. 5, the illustrations ofFIGS. 7(a) and7(b) assume that the mobile phone user provides “Barry Cage” as the voice command. With respect toFIG. 7(a), in accordance withsteps410 and420 ofFIG. 4,field720 displays a query result from a query made to the mobile phone's database (e.g.,client database240 ofFIG. 2). In addition, in accordance with steps430-450,field730 displays a query result from a query made to the network server (e.g.,server database330 ofFIG. 3).
• In the example ofFIG. 7(a),field730 is a list of three entries in which the network server returns as possible matches for the voice command: “barry cage”; “mary paige”; and, “mary peach.” If the mobile phone user does not decide to select an entry from field720 (i.e., “Barry Cage”), then the mobile phone user can select an entry fromfield730. In addition, a partial portion of the list in field630 can be received by and displayed on the mobile phone at a first time instance and the remainder of the list infield730 can be received by and displayed on the mobile phone at a second time instance (e.g., later in time than the first time instance). In this way, the mobile phone user can view a portion of the query results as the remainder of the query results is being processed by the network server and received by the mobile phone.
• With respect toFIG. 7(b), if the mobile phone user selects “barry cage” fromfield730 ofFIG. 7(a), then results740 from a web search is displayed on the mobile phone. The mobile phone user can then scroll throughsearch results740 to locate a hyperlink of interest. In accordance withstep450 ofFIG. 4, search results740 and the query result fromstep420 ofFIG. 4 (e.g.,field720 ofFIG. 7(a)) are stored in the mobile phone for a future voice command by the mobile phone user, according to an embodiment. For instance, if the mobile phone user provides “Barry Cage” as a voice command at a later point in time, “Barry Cage” infield720 and “barry cage” infield730 ofFIG. 7(a) would be retrieved from the mobile phone's memory and displayed to the mobile phone user. In storing the web search result for “Barry Cage,” the mobile phone user receives the benefit of viewing a previously-selected web search result. In turn, the mobile phone user's experience is enhanced since the mobile phone is able to quickly recall a selected entry from a previous voice command. An exemplary method and system to store and retrieve data infields720 and730 ofFIG. 7(a) can be found in U.S. patent application Ser. No. 12/783,470 (Atty. Docket No. 2525.2360000), which is entitled “Personalization and Latency Reduction for Voice-Activated Commands” and incorporated herein by reference in its entirety.
• FIG. 8 is an illustration of anothermethod800 for performing a voice command on a client device.Method800 can occur using, for example,client device110 incommunication system100 ofFIG. 1. Similar tomethod400 ofFIG. 4, for ease of explanation,communication system100 will be used to facilitate in the description ofmethod800. Further, for ease of explanation,method800 will be described in context of a mobile phone (e.g.,client device110 ofFIG. 1) with a mobile phone user as the audio source of the voice command.
• In step810, an audio stream of a voice command is received by the mobile phone. As described above, with respect toFIG. 2,microphone230 is configured to receive the audio stream of the voice command.
• Instep820, a speech recognizer located on the mobile phone determines whether the audio stream (from step810) can be translated into a machine-readable voice command with an appropriate confidence score. In an embodiment, due to computational and memory resources of the mobile phone, the speech recognizer located on the mobile phone (e.g.,speech recognizer210 ofFIG. 2) may not be able to translate more complex voice command into corresponding machine-readable voice commands with relatively high confidence scores. In particular, if a speech recognition confidence score for the voice command is below a predetermined threshold, then a query is not made to a database of the mobile phone based on the voice command, according to an embodiment. Instead, in an embodiment, the mobile phone stores the machine-readable voice command with the relatively low confidence score for future recall by the mobile phone. This future recall feature will be described in further detail below. Methods and techniques to determine speech recognition confidence scores are known to a person of ordinary skill in the relevant art.
• Instep830, if the speech recognizer located on the mobile phone is able to provide a machine-readable voice command translation for the audio stream of the voice command, then the voice command is translated into the machine-readable voice command with the speech recognizer located on the mobile phone. Step830 performs a similar function asstep410 ofFIG. 4.
• Instep840, a query is made on a database of the mobile phone to generate a query result based on the machine-readable voice command generated fromstep830. Step840 performs a similar function asstep420 ofFIG. 4.
• Instep850, regardless of whether the speech recognizer located on the mobile phone is able to provide the machine-readable voice command translation for the audio stream of the voice command with the appropriate confidence score, the audio stream of the voice command is transmitted to a network server, where the voice command is translated to a machine-readable voice command with a speech recognizer located on the network server. Step850 performs a similar function asstep430 ofFIG. 4.
• Instep860, a query result is received from the network server, where the query result is generated from a query made to a server database based on the machine-readable voice command fromstep850. Step860 performs a similar function asstep440 ofFIG. 4.
• FIG. 9 is an illustration of anothermethod900 for performing a voice command on a client device. Similar tosteps430 and440 ofFIG. 6,steps860 and870 ofFIG. 8 can be performed simultaneously with, substantially at the same time as, to overlap with the translation of the audio stream of the voice command by the mobile phone (step830) and query of the database on the mobile phone (step840), according to an embodiment. As a result, in an embodiment, the query result from the network server can be received by and displayed on the mobile phone at substantially the same time as, in parallel with, or soon after a display of the query result from the database of the mobile phone. In the alternative, depending on the computation time to query the mobile phone's database or the complexity of the voice command, the query result from the network server can be received by and displayed on the mobile phone prior to the display of a query result from the mobile phone's database, according to an embodiment.
• In reference to step880 ofFIG. 8, if the speech recognizer located on the mobile phone is able to provide a machine-readable voice command translation for the audio stream of the voice command (see step870), the query result fromstep820 and the query result from840 are displayed on the mobile phone (see step880). In an embodiment, the query results fromsteps820 and840 are stored in the database of the mobile phone for a future voice command by the mobile phone user.
• In the alternative, if the speech recognizer located on the mobile device is not able to provide a machine-readable voice command translation for the audio stream of the voice command (see step870), then only the query result fromstep840 is displayed on the mobile phone (see step890). In an embodiment, the query result fromstep840 is stored in the database of the mobile phone for a future voice command by the mobile phone user.
• In an embodiment, a future voice command can be translated into a machine-readable voice command, in which this machine-readable voice command can be compared to the machine-readable voice command with the relatively low confidence score (fromstep820 ofFIG. 2). If the two machine-readable voice commands substantially match one another or are substantially similar to one another, then the mobile phone displays the query result fromstep820 and/or the query result fromstep840, according to an embodiment. An exemplary method and system to store and retrieve data infields720 and730 ofFIG. 7(a) can be found in U.S. patent application Ser. No. 12/783,470 (Atty. Docket No. 2525.2360000), which is entitled “Personalization and Latency Reduction for Voice-Activated Commands” and incorporated herein by reference in its entirety.
• In addition, according to an embodiment, the audio stream corresponding to the future voice command is transmitted to the network server, where the voice command is translated to a machine-readable voice command with the speech recognizer located on the network server. Based on the machine-readable voice command corresponding to the future voice command, in an embodiment, a query is made to a database on the network server to generate a query result. This query result is received by, displayed on, and stored in the mobile phone, according to an embodiment.
• A benefit, among others, in displaying the stored query result corresponding to the prior voice command and another query result corresponding to the future voice command is that the mobile phone user receives the benefit of viewing an updated query result (if any) from the network server, according to an embodiment. In addition, in an embodiment, the speech recognizer on the mobile phone may mischaracterize the future voice command as corresponding to a previously-stored voice command. In this case, the speech recognizer located on the network server may be able to resolve the mischaracterization by providing a more accurate translation of the future voice command than the translation provided by speech recognizer located on the mobile phone, according to an embodiment.
• FIGS. 10(a)-(e) are illustrations of anexemplary UI1010 on a mobile phone in accordance with embodiments described herein. These illustrations are used to help facilitate in the explanation ofmethod800.
• With respect toFIG. 10(a),mobile phone UI1010 prompts the mobile phone user for a voice command. In this example, the mobile phone user provides “pizza my heart” as the voice command. In turn, in accordance withsteps810 and820, the mobile phone receives the voice command and determines whether the audio stream of the voice command can be translated into a machine-readable voice command with an appropriate confidence score.
• In the example illustrated inFIG. 10, the voice command “pizza my heart” does not return a speech recognition confidence score above the predetermined threshold value. In other words, the voice command “pizza my heart” does not return a high-confidence match from the speech recognizer located on the mobile phone. The audio stream of the voice command is transmitted to a network server for further speech recognition processing, in accordance withstep850.
• FIG. 10(b) is an illustration of an exemplary list ofquery results1020 from the voice command made to the network server. Exemplary list ofquery results1020 is transmitted from the network server to the mobile phone, in accordance withstep850. In an embodiment, as the mobile phone user views exemplary list ofquery results1020, information relating to each of the query results (e.g., web pages, images, text data) is stored in cache memory of the mobile phone. This allows the mobile user to select a query result of interest from exemplary list ofquery results1020 and instantly view information relating to the query result, thus improving the mobile phone user's experience. For instance, with respect toFIG. 10(c), the mobile phone user selects the top entry “pizza my heart” from exemplary list ofquery results1020 and a list ofweb search results1030 is displayed on the mobile phone. From the web search results, the mobile phone user can select a hyperlink of interest (e.g., www.pizzamyheart.com) and view the contents of the web page on the mobile phone, as illustrated in aweb page1040 ofFIG. 10(d).
• Further, in an embodiment ofstep850, a partial portion of the exemplary list of query results can be received by and displayed on the mobile phone at a first time instance and the remainder of the exemplary list of query results can be received by and displayed on the mobile phone at a second time instance (e.g., later in time than the first time instance). In this way, the mobile phone user can view a portion of the query results as the remainder of the query results is being processed by the network server and received by the mobile phone.
• In an embodiment, the query result selected by the mobile phone user (e.g., www.pizzamyheart.com) is stored in the database of the mobile phone for a future voice command by the mobile phone user. For instance, the hyperlink “www.pizzamyheart.com” appears as a query result from a query made to the database of the mobile phone when, at a later time, the mobile phone user provides “pizza my heart” as a voice command to the mobile phone. This is illustrated infield1050 ofFIG. 10(e). The mobile phone user can select the query result infield1050 and view the web page at “www.pizzamyheart.com,” as illustrated inFIG. 10(d). In storing the query result and associated web page, the mobile phone user receives the benefit of viewing a previously-selected web search result. In turn, the mobile phone user's experience is enhanced since the mobile phone is able to quickly recall a selected entry from a previous voice command. An exemplary method and system to store and retrieve data infield1050 ofFIG. 10(e) can be found in U.S. patent application Ser. No. 12/783,470 (Atty. Docket No. 2525.2360000), which is entitled “Personalization and Latency Reduction for Voice-Activated Commands” and incorporated herein by reference in its entirety.
• Various aspects of the embodiments described herein may be implemented in software, firmware, hardware, or a combination thereof.FIG. 11 is an illustration of anexample computer system1100 in which embodiments, or portions thereof, can be implemented as computer-readable code. For example, the methods illustrated byflowchart400 ofFIG. 4,flowchart600 ofFIG. 6,flowchart800 ofFIG. 8, orflowchart900 ofFIG. 9 can be implemented incomputer system1100. Various embodiments are described in terms of thisexample computer system1100. After reading this description, it will become apparent to a person skilled in the relevant art how to implement embodiments described herein using other computer systems and/or computer architectures.
• Computer system1100 is an example computing device and includes one or more processors, such asprocessor1104.Processor1104 may be a special purpose or a general-purpose processor.Processor1104 is connected to a communication infrastructure1106 (e.g., a bus or network).
• Computer system1100 also includes amain memory1108, preferably random access memory (RAM), and may also include asecondary memory1110.Secondary memory1110 can include, for example, ahard disk drive1112, aremovable storage drive1114, and/or a memory stick.Removable storage drive1114 can comprise a floppy disk drive, a magnetic tape drive, an optical disk drive, a flash memory, or the like. Theremovable storage drive1114 reads from and/or writes to aremovable storage unit1118 in a well-known manner.Removable storage unit1118 can include a floppy disk, magnetic tape, optical disk, etc. which is read by and written to byremovable storage drive1114. As will be appreciated by persons skilled in the relevant art,removable storage unit1118 includes a computer-usable storage medium having stored therein computer software and/or data.
• In alternative implementations,secondary memory1110 can include other similar devices for allowing computer programs or other instructions to be loaded intocomputer system1100. Such devices can include, for example, a removable storage unit1122 and aninterface1120. Examples of such devices can include a program cartridge and cartridge interface (such as those found in video game devices), a removable memory chip (e.g., EPROM or PROM) and associated socket, and other removable storage units1122 andinterfaces1120 which allow software and data to be transferred from the removable storage unit1122 tocomputer system1100.
• Computer system1100 can also include acommunications interface1124.Communications interface1124 allows software and data to be transferred betweencomputer system1100 and external devices. Communications interface1124 can include a modem, a network interface (such as an Ethernet card), a communications port, a PCMCIA slot and card, or the like. Software and data transferred viacommunications interface1124 are in the form of signals, which may be electronic, electromagnetic, optical, or other signals capable of being received bycommunications interface1124. These signals are provided tocommunications interface1124 via acommunications path1126.Communications path1126 carries signals and may be implemented using wire or cable, fiber optics, a phone line, a cellular phone link, a RF link or other communications channels.
• In this document, the terms “computer program medium” and “computer-usable medium” are used to generally refer to media such asremovable storage unit1118, removable storage unit1122, and a hard disk installed inhard disk drive1112. Computer program medium and computer-usable medium can also refer to memories, such asmain memory1108 andsecondary memory1110, which can be memory semiconductors (e.g., DRAMs, etc.). These computer program products provide software tocomputer system1100.
• Computer programs (also called computer control logic) are stored inmain memory1108 and/orsecondary memory1110. Computer programs may also be received viacommunications interface1124. Such computer programs, when executed, enablecomputer system1100 to implement embodiments discussed herein. In particular, the computer programs, when executed, enable processor904 to implement processes described above, such as the steps in the methods illustrated byflowchart400 ofFIG. 4,flowchart600 ofFIG. 6,flowchart800 ofFIG. 8, andflowchart900 ofFIG. 9, discussed above. Accordingly, such computer programs represent controllers of thecomputer system1100. Where embodiments described herein are implemented using software, the software can be stored in a computer program product and loaded intocomputer system1100 usingremovable storage drive1114,interface1120,hard drive1112 orcommunications interface1124.
• Based on the description herein, a person of ordinary skill in the relevant will recognize that the computer programs, when executed, can enable one or more processors to implement processes described above, such as the steps in the methods illustrated byflowchart400 ofFIG. 4,flowchart600 ofFIG. 6,flowchart800 ofFIG. 8, andflowchart900 ofFIG. 9. In an embodiment, the one or more processors can be part of a computing device incorporated in a clustered computing environment or server farm. Further, in an embodiment, the computing process performed by the clustered computing environment such as, for example, the steps in the methods illustrated byflowcharts400,600,800, and900 may be carried out across multiple processors located at the same or different locations.
• Embodiments are also directed to computer program products including software stored on any computer-usable medium. Such software, when executed in one or more data processing device, causes a data processing device(s) to operate as described herein. Embodiments employ any computer-usable or -readable medium, known now or in the future. Examples of computer-usable mediums include, but are not limited to, primary storage devices (e.g., any type of random access memory), secondary storage devices (e.g., hard drives, floppy disks, CD ROMS, ZIP disks, tapes, magnetic storage devices, optical storage devices, MEMS, nanotechnological storage devices, etc.), and communication mediums (e.g., wired and wireless communications networks, local area networks, wide area networks, intranets, etc.).
• While various embodiments have been described above, it should be understood that they have been presented by way of example only, and not limitation. It will be understood by those skilled in the relevant art that various changes in form and details can be made therein without departing from the spirit and scope of the embodiments described herein. It should be understood that this description is not limited to these examples. This description is applicable to any elements operating as described herein. Accordingly, the breadth and scope of this description should not be limited by any of the above-described exemplary embodiments, but should be defined only in accordance with the following claims and their equivalents.

Claims (20)

1. A method for performing a voice command on a client device, comprising:

translating, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command;

generating a first query result using the first machine-readable voice command to query a client database;

transmitting the audio stream to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer;

receiving a second query result from the remote server device, wherein the second query result is generated by the remote server device using the second machine-readable voice command to query a remote server database; and

displaying the first query result and the second query result on the client device.

2. The method ofclaim 1, further comprising:

storing at least a portion of the first and second query results on the client device.

3. The method ofclaim 2, further comprising retrieving the stored first and second query results when translation of a subsequent voice command is determined to be substantially similar to the translated voice command that generated the first and second query results.

4. The method ofclaim 3, further comprising:

transmitting to the remote server device a second audio stream associated with the subsequent voice command;

translating the second audio stream to a third machine-readable voice command using the second speech recognizer;

receiving a third query result from the remote server device, wherein the third query result is generated from a subsequent query made to the server database based on the third machine-readable voice command; and

displaying the first, second, and third query results on the client device.

5. The method ofclaim 2, further comprising identifying which portion of the first and second query results to store, the identification comprising:

receiving a user selection of an item of interest from a list of items returned as part of the second query result.

6. The method ofclaim 1, wherein generating the first query result comprises transmitting the audio stream to the second speech recognizer such that the query made to the remote server database based on the second machine-readable voice command occurs during a time period that overlaps when the query is made to the client database based on the first machine-readable voice command.

7. The method ofclaim 1, wherein transmitting the audio stream comprises transmitting a compressed audio stream of the voice command from the client device to the server device.

8. The method ofclaim 1, wherein displaying the first and second query results comprises displaying the first result and a first subset of the second query result at a first time instance and the first result, the first subset of the second query result, and a second subset of the second query result at a second time instance.

9. A computer program product comprising a computer-usable medium having computer program logic recorded thereon for enabling a processor to perform a voice command on a client device, the computer program logic comprising:

first computer readable program code that enables a processor to translate, using a first speech recognizer located on the client device, an audio stream of a voice command to a first machine-readable voice command;

second computer readable program code that enables a processor to generate a first query result using the first machine-readable voice command to query a client database;

third computer readable program code that enables a processor to transmit the audio stream to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer;

fourth computer readable program code that enables a processor to receive a second query result from the remote server device, wherein the second query result is generated by the remote server device using the second machine-readable voice command to query a remote server database; and

fifth computer readable program code that enables a processor to display the first query result and the second query result on the client device.

10. The computer program product ofclaim 9, further comprising:

sixth computer readable program code that enables a processor to store at least a portion of the first and second query results on the client device.

11. The computer program product ofclaim 10, further comprising:

seventh computer readable program code that enables a processor to retrieve the stored first and second query results when translation of a subsequent voice command is determined to be substantially similar to the translated voice command that generated the first and second query results.

12. The computer program product ofclaim 11, further comprising:

eighth computer readable program code that enables a processor to transmit to the remote server device a second audio stream associated with the subsequent voice command;

ninth computer readable program code that enables a processor to translate the second audio stream to a third machine-readable voice command using the second speech recognizer;

tenth computer readable program code that enables a processor to receive a third query result from the remote server device, wherein the third query result is generated from a subsequent query made to the server database based on the third machine-readable voice command; and

eleventh computer readable program code that enables a processor to display the first, second, and third query results on the client device.

13. The computer program product ofclaim 10, wherein the sixth computer readable program code comprises:

seventh computer readable program code that enables a processor to identify which portion of the first and second query results to store, the identification comprising receiving a user selection of an item of interest from a list of items returned as a part of the second query result.

14. The computer program product ofclaim 9, wherein the second computer readable program code comprises:

sixth computer readable program code that enables a processor to transmit the audio stream to the second speech recognizer such that the query made to the remote server database based on the second machine-readable voice command occurs during a time period that overlaps when the query is made to the client database based on the first machine-readable voice command.

15. A system for performing a voice command on a client device, comprising:

a first speech recognizer device configured to translate an audio stream of a voice command to a first machine-readable voice command;

a client query manager configured to:

generate a first query result using the first machine-readable voice command to query a client database;

transmit the audio stream to a remote server device that translates the audio stream to a second machine-readable voice command using a second speech recognizer device; and

receive a second query result from the remote server device, wherein the second query result is generated by the remote server device using the second machine-readable voice command to query a remote server database; and

a display device configured to display the first query result and the second query result on the client device.

16. The system ofclaim 15, further comprising:

a microphone configured to receive the audio stream of the voice command and to provide the audio stream to the first speech recognizer device; and

a storage device configured to store at least a portion of the first and second query results on the client device.

17. The system ofclaim 16, wherein the client query manager is configured to retrieve the stored first and second query results from the storage device when translation of a subsequent voice command is determined to be substantially similar to the translated voice command that generated the first and second query results.

18. The system ofclaim 17, wherein the client query manager is configured to:

transmit to the remote server device a second audio stream associated with the subsequent voice command;

translate the second audio stream to a third machine-readable voice command using the second speech recognizer device; and

receive a third query result from the remote server device, wherein the third query result is generated from a subsequent query made to the server database based on the third machine-readable voice command.

19. The system ofclaim 15, wherein the client query manager is configured to transmit the audio stream to the second speech recognizer device such that the query made to the remote server database based on the second machine-readable voice command occurs during a time period that overlaps when the query is made to the client database based on the first machine-readable voice command.

20. The system ofclaim 15, wherein the display device is configured to display the first result and a first subset of the second query result at a first time instance and the first result, the first subset of the second query result, and a second subset of the second query result at a second time instance.

Images