I have tried working on Kaldi and CMU's Sphinx, these work well for US accent however the accuracy for Indian English is not good. To train the model with Indian English there is a need of phonetic dictionary. So here I am with the below questions:
- Is there any open source/commercial tool for speech to text for Indian English?
- Is there any training data-set available for Indian speech recognition along with its phonetics ?
- Can we do this with existing tools (Kaldi/Sphinx) or is it advisable to build it from scratch ?
I doubt if you can find enough data for training your indian english ASR from scratch. What we do usually is to adapt an American English ASR model to a very small Accented English dataset. using MAP or MLLR, etc (regarding to the size of adaptation dataset). I know that MAP and MLLR already exist in HTK toolkit and I'm pretty sure it is embedded in KALDI as well. Or you can simply retrain your American English model with a small Indian English dataset.
No currently there are no tool TTS tools available for Indian languages/. Still research is going on the labs. You can implement a TTS for any indian language
- Badges
- Science topic