Phonemes conversion

[JRMeyer]

>>> naveen
[December 11, 2017, 9:15am]

How can I use deepspeech to convert wav file to phonemes. I wanted to
compare two person's speech audio file and output whether they are
saying the same words or where they differ. So I thought to convert
speech to phoneme and then compare between that.

[This is an archived TTS discussion thread from discourse.mozilla.org/t/phonemes-conversion]

[JRMeyer]

>>> JanX2
[December 12, 2017, 3:48pm]

As far as I can tell, this is not currently possible with Deep Speech. I
would recommend having a look at Kaldi.
Gentle uses it to do this under the
hood.

[Archived Post]

[JRMeyer]

>>> kdavis
[December 13, 2017, 2:34am]

Why not just compare the text outputs?

[Archived Post]

[JRMeyer]

>>> naveen
[December 13, 2017, 5:22pm]

Ill take a look at it. Thanks

[Archived Post]

[JRMeyer]

>>> iveskins
[December 15, 2017, 4:10pm]

Gentle will just give you the timings of the sentences. AFIK it just
shows phonemes from a dictionary. slash

project to extract vowel sounds from sentences. slash
I think most TTS projects do a lot of predictions bassed on sound
signal. they don't really output exactly what people say. slash
But if you want to just check for whole word differences, you compare
the text output of TTS. slash
If you want to compare things at a phoneme level... its a bit difficult,
because phonemes are not really a real thing... slash
check out slash

CMUSphinx Open Source Speech
Recognition

### Phoneme Recognition (caveat emptor)

CMUSphinx is an open source speech recognition system for mobile and
server applications. Supported languages: C, C++, C slash #, Python, Ruby,
Java, Javascript. Supported platforms: Unix, Windows, IOS, Android,
hardware.

slash
and then slash

CMUSphinx Open Source Speech
Recognition

### Pocketsphinx for Pronunication Evaluation

CMUSphinx is an open source speech recognition system for mobile and
server applications. Supported languages: C, C++, C slash #, Python, Ruby,
Java, Javascript. Supported platforms: Unix, Windows, IOS, Android,
hardware.

slash
and the paper at the top slash
and this google summer of code project slash

{.site-icon width='32'

This year slash 's GSoC is ending now, so this will be my last blog for the
journey I went through with my teammates and mentors. Working with
cm slash ...

slash
... slash
you could get yourself a free google-cloud speech-to-text api key, and
use autosub slash

{.site-icon width='32'

### agermanidis/autosub

Command-line utility for auto-generating subtitles for any video file -
agermanidis/autosub

slash
to make timed text file of what they said, then compare those files...
or run those files through gentle to get the word by word timings from
Google's STT transcript.

[Archived Post]

[JRMeyer]

>>> JanX2
[December 15, 2017, 6:37pm]

Have a look at the Gentle website's
source code as an example,
. The JSON that is
generated contains the start time for each word and the duration of each
phoneme.

[Archived Post]

[JRMeyer]

>>> iveskins
[December 15, 2017, 9:13pm]

Oh sorry, yes, Gentle gives the timing of words, and phonemes. I meant
that it doesn't tell you what phonemes were actually said. It also
outputs how certain it was. slash
is asking about taking two
audio files converting them to phonemes and then comparing the output.
Gentle needs a transcript and an audio file.

[Archived Post]

[JRMeyer]

>>> JanX2
[December 15, 2017, 9:19pm]

Yes. And it uses Kaldi behind the scenes to do exactly what the OP
wants: convert the audio to phonemes. That it also does this for the
text and diffs the two doesn't help the OP, but the rest is pretty much
a template for a solution.

[Archived Post]