Umar17

Acoustic model is not trained well for silence seemingly. Its not server problem rather training issue.

@jin1004 Did the proposed solution of @calderma work?

I have shifted HMM based acoustic model to Neural Net based which has back tracing feature as well and improves garbage decoding to a reasonable utterance. So I didn't need...

Yes. Decoding is fine with kaldi's decoding script. If I don't comment out ivector-extraction-config in configuration it raises: _ERROR ([5.2]:Compute():nnet-compute-online.cc:55) Feature dimension is 113, but network expects 13_