Log In Sign Up

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

by   Wei Zhou, et al.

To join the advantages of classical and end-to-end approaches for speech recognition, we present a simple, novel and competitive approach for phoneme-based neural transducer modeling. Different alignment label topologies are compared and word-end-based phoneme label augmentation is proposed to improve performance. Utilizing the local dependency of phonemes, we adopt a simplified neural network structure and a straightforward integration with the external word-level language model to preserve the consistency of seq-to-seq modeling. We also present a simple, stable and efficient training procedure using frame-wise cross-entropy loss. A phonetic context size of one is shown to be sufficient for the best performance. A simplified scheduled sampling approach is applied for further improvement. We also briefly compare different decoding approaches. The overall performance of our best model is comparable to state-of-the-art results for the TED-LIUM Release 2 and Switchboard corpora.


page 1

page 2

page 3

page 4


Neural Speech Recognizer: Acoustic-to-Word LSTM Model for Large Vocabulary Speech Recognition

We present results that show it is possible to build a competitive, grea...

Exploring End-to-End Techniques for Low-Resource Speech Recognition

In this work we present simple grapheme-based system for low-resource sp...

Improving Mandarin End-to-End Speech Recognition with Word N-gram Language Model

Despite the rapid progress of end-to-end (E2E) automatic speech recognit...

A novel pyramidal-FSMN architecture with lattice-free MMI for speech recognition

Deep Feedforward Sequential Memory Network (DFSMN) has shown superior pe...

Simplified End-to-End MMI Training and Voting for ASR

A simplified speech recognition system that uses the maximum mutual info...

Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

In this work, we first show that on the widely used LibriSpeech benchmar...