Menu

Sphinxtrain: Transcription preparation

Help
Paul
2021-03-09
2021-03-10
  • Paul

    Paul - 2021-03-09

    Hello,

    I'm doing some work with Sphinxtrain and was wondering, does the tool search alternate phonetic spellings during the training process?

    For example, let's assume the transcript is something like " I REPLIED TO THE EMAIL (name_of_file)".

    If the dictionary has two alternative phonetic spellings for replied, something like ....
    REPLIED R IH P L AY D
    REPLIED(1) R IY P L AY D

    Does the training process automatically search both spellings to find the best fit?

    Or, must the transcript file be coded to the correct pronunciation, (let's assume the subject ennuciated the second pronunciations) eg

    " I REPLIED(1) TO THE(2) EMAIL (name_of_file)".

    Thanks for any help,
    Paul

     
    • Nickolay V. Shmyrev

      I'm doing some work with Sphinxtrain

      It is very outdated technology these days.

      Does the training process automatically search both spellings to find the best fit?

      No.

      Or, must the transcript file be coded to the correct pronunciation, (let's assume the subject ennuciated the second pronunciations) eg

      You can point proper transcription variant in the transcription file. You can also run forced alignment stage, it will try to select a proper pronunciation, but the accuracy is not guaranteed.

       
  • Paul

    Paul - 2021-03-10

    Thank you

     

Log in to post a comment.

Want the latest updates on software, tech news, and AI?
Get latest updates about software, tech news, and AI from SourceForge directly in your inbox once a month.