This is a writeup of the steps I took to perform acoustic model adaptation for an acoustic model to be used in Sphinx 4. I followed the well-written CMU howto. I performed all steps on a mostly-new Ubuntu 11.04 install and adapted the Communicator acoustic model for use in Sphinx 4. Keep an eye out for paths that may be different on your system and any error messages that pop up when running these commands.
I also generated a new, full set of adaptation prompt data from the CMU ARCTIC prompts.
…I’m running 99 jobs and not a glitch in one. Thanks to HPCC for letting me run many different speech recognition configurations on many different audio files in parallel :)
That is all.
Speech recognition that does not take advantage of domain specific language models produces silly results. The recognition menagerie below was generated with Sphinx 4. I used the HUB4 acoustic model and an SRILM language model generated from the human annotator transcripts.
This space reserved for speech and language processing tips, nerdy notions, and the occasional serious attempt to contribute a bit of carefully curated knowledge to the great indexer in the cloud.
