DeepAI
Log In Sign Up

Phoneme Based Neural Transducer for Large Vocabulary Speech Recognition

10/30/2020
by   Wei Zhou, et al.
0

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.

READ FULL TEXT

page 1

page 2

page 3

page 4

10/31/2016

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...
07/02/2018

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

In this work we present simple grapheme-based system for low-resource sp...
01/06/2022

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...
10/26/2018

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

Deep Feedforward Sequential Memory Network (DFSMN) has shown superior pe...
03/30/2017

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

A simplified speech recognition system that uses the maximum mutual info...
05/19/2020

Fast, Simpler and More Accurate Hybrid ASR Systems Using Wordpieces

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