activity
20152021
most citedA Fixed-Size Encoding Method for Variable-Length Sequences with its Application to Neural Network Language Models

13 citations · 22 across the 2 of their papers we have counts for

collaborators
Showing eess.ASShow all

2 papers · 1 filter

eess.AS2021

HMM-Free Encoder Pre-Training for Streaming RNN Transducer

Lu Huang, Jingyu Sun, Yufeng Tang +4

This work describes an encoder pre-training procedure using frame-wise label to improve the training of streaming recurrent neural network transducer (RNN-T) model. Streaming RNN-T…

eess.AS2020★ 9 cited

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

Liangfa Wei, Jie Zhang, Junfeng Hou +1

Audio-visual information fusion enables a performance improvement in speech recognition performed in complex acoustic scenarios, e.g., noisy environments. It is required to explore…