Duc Le

Improving RNN Transducer Based ASR with Auxiliary Tasks

2021

End-to-end automatic speech recognition (ASR) models with a single neural network have recently demonstrated state-of-the-art results compared to conventional hybrid speech recognizers. Specifically, recurrent neural network transducer (RNN-T) has shown competitive ASR performance on various …

From Senones to Chenones: Tied Context-Dependent Graphemes for Hybrid Speech Recognition

2019 · 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU)

There is an implicit assumption that traditional hybrid approaches for automatic speech recognition (ASR) cannot directly model graphemes and need to rely on phonetic lexicons to get competitive performance, especially on English which has poor …