TensorFlow acoustic models are integrated with Kaldi WFST decoder and achieve equivalent word error rates to native Kaldi models on RM, WSJ, and LibriSpeech.
The system is divided into fea ture extraction, GMM training, DNN training, and WFST decoding processes
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
eess.AS 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Integration of TensorFlow based Acoustic Model with Kaldi WFST Decoder
TensorFlow acoustic models are integrated with Kaldi WFST decoder and achieve equivalent word error rates to native Kaldi models on RM, WSJ, and LibriSpeech.