Repository files navigation

new-fave is a tool for automating and optimizing vowel formant extraction. It is philosophically similar (and named after)the FAVE-suite. However,new-fave has been completely written from scratch, and has some key differences from the FAVE-suite.

1. new-fave does not include a forced-aligner.It can process alignments produced by fave-align,but we would recommend using the Monteal Forced Aligner instead
2. new-fave does not require speaker demographics.You can optionally passfave-extract a speakerdemographics file to be merged into your formant data,but this doesnot influence how the data is processedin any way. Besides including file name and speakernumber data, you can passany demographic informationyou would like.
3. new-fave does not assume North American English vowels.Your alignments can contain any set of vowels, inany transcription system, as long as you can providea regular expression to identify them.
4. new-fave is customizable.With config files, you can customize vowel recoding,labelset parsing, and point measurement heuristics.
5. new-fave is focused on formant tracks.You can still produce single point measurementsfor vowels, butnew-fave is built upontheFastTrack method. By default, it will writeoutput files including point measurements, fullformant tracks, and Discrete Cosine Transformcoefficients.
6. new-fave is maintainable. As time goes on, and thecode base needs updating, the organization andinfrastructure ofnew-fave should allow it to bereadilly updateable.

You can read more atthenew-fave documentation.

You can installnew-fave withpip.

# bashpip install new-fave

To use the default settings (which assume CMUdictionary transcriptions), you can use one of thesepatterns.

# bashfave-extract audio-textgrid speaker1.wav speaker1.TextGrid

# bashfave-extract corpus speakers/

# bashfave-extract subcorpora data/*