Swapping the Lookup List

Home Forums OpenEars Swapping the Lookup List

Viewing 4 posts - 1 through 4 (of 4 total)

  • Author
    Posts
  • #1031961
    msolares
    Participant

    I’d like to accept various pronunciations of certain words, to make detection more lenient. I’d like to experiment with a wider range of acceptable pronunciations than the standard LanguageModelGeneratorLookupList.text

    For example, for the word CAT, I could try:

    cat K AE T
    cat(2) K EY T
    cat(3) K AH T

    My questions are:

    1. Is this done by just swapping out the language model lookup list?
    2. Can I do this real-time within an app session? ie. update the list without rebuilding the app
    3. Is there any reason this wouldn’t work? Accepting ‘bike’ as pronunciation for bicycle:
    bicycle B AY S IH K AH L
    bicycle(2) B AY K

    Thanks
    Mateo

    #1031964
    Halle Winkler
    Politepix

    Hi Mateo,

    Although I don’t give support for this, you can add pronunciations to the English lookup list (but not any other languages) by editing the file in the bundle, if you are very careful to use working phonemes, match the formatting of other entries, and keep everything alphabetical. You can’t make changes to that functionality at runtime. There is no special reason that adding fake pronunciations wouldn’t work, but it makes more sense in terms of maintainability to do that via substitution at the time of detection (i.e. detect “bike” and process it as if it were “bicycle”).

    #1031965
    msolares
    Participant

    Halle,

    Thanks for your answers. If not at runtime, then is it possible at app start, to grab the acoustic model bundle from an external source?

    Bike/bicycle makes sense as you say.

    Will you be adding keyword spotting and/or allphones listening modes to OpenEars? They’re mentioned at the end of this document:

    https://cmusphinx.github.io/wiki/tutorialpocketsphinx/

    Mateo

    #1031966
    Halle Winkler
    Politepix

    Hi Mateo,

    Sorry, there are no exposed APIs for the developer to work with the lookup list specifically, but all of the APIs which work with an acoustic model take an arbitrary path to it, so you can point this elsewhere. I unfortunately can’t offer support for using different acoustic models or altering them because that becomes a very broad topic, sorry I can’t help more!

Viewing 4 posts - 1 through 4 (of 4 total)
  • The topic ‘Swapping the Lookup List’ is closed to new replies.