Timing information for runRecognitionOnWavFile

[michaelgallacher]

I need timing information for speech recognized in a WAV file. I have successfully retrieved hypotheses from OpenEars. I added RapidEarsDemo but am not getting any RapidEars events when calling runRecognitionOnWavFile. I am specifically hoping for:

rapidEarsDidDetectFinishedSpeech(asWordArray words: [Any]!, scoreArray scores: [Any]!, startTime startTimes: [Any]!, endTime endTimes: [Any]!)

to be called but (based on the method name) it appears it will only be called when finished speech is detected while using real-time listening.

Is timing supported for WAV files or is it only available for real-time? I will provide logging if this scenario is supported.

[Halle Winkler]

Welcome,

Sorry, runRecognitionOnWaveFile is an OpenEars-only method, not a RapidEars method, so it shouldn’t invoke a RapidEars callback. Have you tried it out with pathToTestFile? I am doubtful that there is a way to do exactly what you’re trying for here, but pathToTestFile will invoke RapidEars hypothesis callbacks.

[Author]

Posts