Log In Sign Up

Fusing information streams in end-to-end audio-visual speech recognition

by   Wentao Yu, et al.

End-to-end acoustic speech recognition has quickly gained widespread popularity and shows promising results in many studies. Specifically the joint transformer/CTC model provides very good performance in many tasks. However, under noisy and distorted conditions, the performance still degrades notably. While audio-visual speech recognition can significantly improve the recognition rate of end-to-end models in such poor conditions, it is not obvious how to best utilize any available information on acoustic and visual signal quality and reliability in these models. We thus consider the question of how to optimally inform the transformer/CTC model of any time-variant reliability of the acoustic and visual information streams. We propose a new fusion strategy, incorporating reliability information in a decision fusion net that considers the temporal effects of the attention mechanism. This approach yields significant improvements compared to a state-of-the-art baseline model on the Lip Reading Sentences 2 and 3 (LRS2 and LRS3) corpus. On average, the new system achieves a relative word error rate reduction of 43 audio-only setup and 31


page 1

page 2

page 3

page 4


Attentive Fusion Enhanced Audio-Visual Encoding for Transformer Based Robust Speech Recognition

Audio-visual information fusion enables a performance improvement in spe...

Large-vocabulary Audio-visual Speech Recognition in Noisy Environments

Audio-visual speech recognition (AVSR) can effectively and significantly...

End-to-end Audio-visual Speech Recognition with Conformers

In this work, we present a hybrid CTC/Attention model based on a ResNet-...

End-to-end acoustic modelling for phone recognition of young readers

Automatic recognition systems for child speech are lagging behind those ...

Audio-Visual Decision Fusion for WFST-based and seq2seq Models

Under noisy conditions, speech recognition systems suffer from high Word...

Predict-and-Update Network: Audio-Visual Speech Recognition Inspired by Human Speech Perception

Audio and visual signals complement each other in human speech perceptio...

Multimodal Integration for Large-Vocabulary Audio-Visual Speech Recognition

For many small- and medium-vocabulary tasks, audio-visual speech recogni...