Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

no code implementations • 17 Sep 2022 • Ye Bai, Jie Li, Wenjing Han, Hao Ni, Kaituo Xu, Zhuo Zhang, Cheng Yi, Xiaorui Wang

Experimental results show that the proposed model achieves competitive performance with 1/3 of the parameters of the encoder, compared with the full-parameter model.

Knowledge Distillation speech-recognition +1

Efficiently Fusing Pretrained Acoustic and Linguistic Encoders for Low-resource Speech Recognition

no code implementations • 17 Jan 2021 • Cheng Yi, Shiyu Zhou, Bo Xu

In this work, we fuse a pre-trained acoustic encoder (wav2vec2. 0) and a pre-trained linguistic encoder (BERT) into an end-to-end ASR model.

Automatic Speech Recognition Automatic Speech Recognition (ASR) +2

Applying Wav2vec2.0 to Speech Recognition in Various Low-resource Languages

no code implementations • 22 Dec 2020 • Cheng Yi, Jianzhong Wang, Ning Cheng, Shiyu Zhou, Bo Xu

To verify its universality over languages, we apply pre-trained models to solve low-resource speech recognition tasks in various spoken languages.

speech-recognition Speech Recognition

A Comparison of Label-Synchronous and Frame-Synchronous End-to-End Models for Speech Recognition

no code implementations • 20 May 2020 • Linhao Dong, Cheng Yi, Jianzong Wang, Shiyu Zhou, Shuang Xu, Xueli Jia, Bo Xu

End-to-end models are gaining wider attention in the field of automatic speech recognition (ASR).

Automatic Speech Recognition Automatic Speech Recognition (ASR) +1