1

I'm using Sphinx4 to perform speech recognition with a grammar, but I want, for another purpose, saving to an audio file that the user said without a grammar.

Basically the user says something and when it's silent an audio file is created and I want to know if I can reuse Sphinx4 system to perform this action. If yes, how can I do this?

user3549728
  • 11
  • 2

1 Answers1

1

Unfortunately, this feature is not supported at this moment. You need to implement your own DataProcessor that will cache audio data and make it available through the API. If you just want to dump utterances, insert WavWriter component into fronted pipeline in a configuration file:

  <item>speechMarker </item>
  <item>nonSpeechDataFilter </item>
  <item>wavWriter </item>
  <item>preemphasizer </item>
  <item>windower </item>
  .......

If you just using xml config files, you can modify your current file. Otherwise you can modify default config file in edu/cmu/sphinx/api/default.config.xml

Nikolay Shmyrev
  • 24,897
  • 5
  • 43
  • 87