如何使用 cmusphinx/mozilla deepspeech/google stt 等检测填充声音，如 um、uh 等？

Question

I am working on a project in Speech Recognition and the task is to detect filler sounds like um, uh, eh, etc. on audio clips of children/students speaking in English. Their speaking English is not that great.

How can this be done using cmuSphinx/Mozilla deep speech/google cloud speech/Kaldi? Or do I need to start from scratch?

I also tried to go through other posts and papers on how to build an ASR but since its not a long term project, I do not have the time to spend on building it from scratch and see the results. Also, I am okay with less accuracy which I can claim to improve later on.

Answer 1

Have you tried just adding the filler words in your lexicon? eg the CMU pronunciation dictionary have these words as entries their published lexicon ( LINK TO COMPLETE DICTIONARY )

For example, in the CMU pronunciation dictionary, they have the following entries that correspond to filler sounds

AH   AA1
HM   HH AH0 M
HMM  HH AH0 M
UH   AH1
UHH  AH1
UM   AH1 M