English Conversational Speech Recognition
1 papers with code • 0 benchmarks • 1 datasets
Benchmarks
These leaderboards are used to track progress in English Conversational Speech Recognition
Latest papers with no code
On the limit of English conversational speech recognition
Compensation of the decoder model with the probability ratio approach allows more efficient integration of an external language model, and we report 5. 9% and 11. 5% WER on the SWB and CHM parts of Hub5'00 with very simple LSTM models.
Building competitive direct acoustics-to-word models for English conversational speech recognition
This is because A2W models recognize words from speech without any decoder, pronunciation lexicon, or externally-trained language model, making training and decoding with such models simple.
Direct Acoustics-to-Word Models for English Conversational Speech Recognition
Our CTC word model achieves a word error rate of 13. 0%/18. 8% on the Hub5-2000 Switchboard/CallHome test sets without any LM or decoder compared with 9. 6%/16. 0% for phone-based CTC with a 4-gram LM.
TheanoLM - An Extensible Toolkit for Neural Network Language Modeling
We present a new tool for training neural network language models (NNLMs), scoring sentences, and generating text.