How to use Speech recognition for previously recorded raw audio

[toinedeboer@outlook.com]

Hello,

For Android I have been using PocketSphinx for doing speech recognition for previously recorded audio parts, a single word represented in a byte array (PCM16).

Can this be done by OpenEars as well?
(without needed to use the microphone implementation)

Maybe the Android (PocketSphinx) code make my requirements more clear
// decoder is PcoektSphinx decoder, loaded with language models etc.
decoder.StartUtt();
decoder.ProcessRaw(audioBytesShorts, audioBytesShortsLength, false, true);
decoder.EndUtt();

var finalHypothesis = decoder.Hyp();
var nbestIterator = decoder.Nbest()?.Iterator(); … etc

Is something possible with OpenEars for iOS?
That would be great, instead of needed to make PocketSphinx workable on iOS myself.
Kind Regards,
Toine

[Halle Winkler]

Welcome,

This is not really an intended/supported feature of OpenEars, so I don’t really recommend it and can’t offer support assistance, but it is possible using the APIs which are intended for testing found in OEPocketsphinxController. If you take a look in the docs or header for the APIs beginning with runRecognitionOnWavFileAtPath and pathToTestFile, you can learn more about how this would work. This isn’t going to give identical results to your android code. Good luck!

[toinedeboer@outlook.com]

Thanks for your reply, ill take look.

[Author]

Posts