AIConfPaper
← Search

Frank Zhang

6 accepted papers

2022

Improved Language Identification Through Cross-Lingual Self-Supervised Learning

Andros Tjandra, Diptanu Gon Choudhury, Frank Zhang, Kritika Singh, Alexis Conneau, Alexei Baevski +3
ICASSP 2022accepted

Language identification greatly impacts the success of downstream tasks such as automatic speech recognition. Recently, self-supervised speech representations learned by wav2vec 2.0 have been shown to be very effective for a range of speech tasks. We extend previous self-supervised work on language…

Cited by 0Source ↗Scholar ↗
2021

Emformer: Efficient Memory Transformer Based Acoustic Model for Low Latency Streaming Speech Recognition

Yangyang Shi, Yongqiang Wang, Chunyang Wu, Ching-Feng Yeh, Julian Chan, Frank Zhang +2
ICASSP 2021accepted

This paper proposes an efficient memory transformer Emformer for low latency streaming speech recognition. In Emformer, the long-range history context is distilled into an augmented memory bank to reduce self-attention’s computation complexity. A cache mechanism saves the computation for the key and…

Cited by 0Source ↗Scholar ↗
2021

Transformer in Action: A Comparative Study of Transformer-Based Acoustic Models for Large Scale Speech Recognition Applications

Yongqiang Wang, Yangyang Shi, Frank Zhang, Chunyang Wu, Julian Chan, Ching-Feng Yeh +1
ICASSP 2021accepted

Transformer-based acoustic models have shown promising results very recently. In this paper, we summarize the application of transformer and its streamable variant, Emformer based acoustic model [1] for large scale speech recognition applications. We compare the transformer based acoustic models wit…

Cited by 0Source ↗Scholar ↗
2020

DEJA-VU: Double Feature Presentation and Iterated Loss in Deep Transformer Networks

Andros Tjandra, Chunxi Liu, Frank Zhang, Xiaohui Zhang, Yongqiang Wang, Gabriel Synnaeve +2
ICASSP 2020accepted

Deep acoustic models typically receive features in the first layer of the network, and process increasingly abstract representations in the subsequent layers. Here, we propose to feed the input features at multiple depths in the acoustic model. As our motivation is to allow acoustic models to re-exa…

Cited by 0Source ↗Scholar ↗
2020

Training ASR Models By Generation of Contextual Information

Kritika Singh, Dmytro Okhonko, Jun Liu, Yongqiang Wang, Frank Zhang, Ross B. Girshick +5
ICASSP 2020accepted

Supervised ASR models have reached unprecedented levels of accuracy, thanks in part to ever-increasing amounts of labelled training data. However, in many applications and locales, only moderate amounts of data are available, which has led to a surge in semi- and weakly-supervised learning research.…

Cited by 0Source ↗Scholar ↗
2020

Transformer-Based Acoustic Modeling for Hybrid Speech Recognition

Yongqiang Wang, Abdelrahman Mohamed, Duc Le, Chunxi Liu, Alex Xiao, Jay Mahadeokar +7
ICASSP 2020accepted

We propose and evaluate transformer-based acoustic models (AMs) for hybrid speech recognition. Several modeling choices are discussed in this work, including various positional embedding methods and an iterated loss to enable training deep transformers. We also present a preliminary study of using l…

Cited by 0Source ↗Scholar ↗