Recognize SaveThatWave file in OpenEars

[peagasilva]

Hey,

first of all, amazing plugins!

I’d like to know: is it possible to OpenEars recognize the wav file generated by SaveThatWave?

Thanks in advance!

[Halle Winkler]

Welcome,

Can you describe the interface goal in doing that? The reason I ask is that the WAV is to some extent the output of the recognition process, so it was probably already recognized.

[peagasilva]

Thanks for the answer, Halle.

Actually, I think I didn’t make myself clear, sorry for that.

If I record a WAV file, with a random sound, is OpenEars capable of recognizing this sound from the file?

Thanks in advance!

[Halle Winkler]

OK, in order to perform recognition on an existing WAV file, you can submit a WAV file that is 16-bit/16k/mono to this method of OEPocketsphinxController:

- (void) runRecognitionOnWavFileAtPath:(NSString *)wavPath usingLanguageModelAtPath:(NSString *)languageModelPath dictionaryAtPath:(NSString *)dictionaryPath acousticModelAtPath:(NSString *)acousticModelPath languageModelIsJSGF:(BOOL)languageModelIsJSGF;

and SaveThatWave creates files in that format. But, the method above won't create a different recognition than the main OpenEars recognition method creates. Does that answer help?

[peagasilva]

If I record a police car siren and send it through that method, would OpenEars be able to recognize that police car siren?

[Halle Winkler]

No, OpenEars can’t identify non-speech sounds.

[peagasilva]

Ok, Halle.

Thanks for the time! :D

[Author]

Posts