Songjun Cao

Censer: Curriculum Semi-supervised Learning for Speech Recognition Based on Self-supervised Pre-training

T. Shinozaki, Yike Zhang, Bo Zhang, 2022, ArXiv.

Censer: Curriculum Semi-supervised Learning for Speech Recognition Based on Self-supervised Pre-training

T. Shinozaki, Yike Zhang, Songjun Cao, 2022, INTERSPEECH.

Improving Streaming Transformer Based ASR Under a Framework of Self-supervised Learning pdf

Sining Sun, Yike Zhang, Xiaoshuo Xu, 2021, Interspeech.

Improving CTC-Based Speech Recognition Via Knowledge Transferring from Pre-Trained Language Models

Keqi Deng, Yike Zhang, Pengyuan Zhang, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Multi-head Monotonic Chunkwise Attention For Online Speech Recognition pdf

Weibin Zhang, Long Ma, Sining Sun, 2020, ArXiv.

Improving Accent Identification and Accented Speech Recognition Under a Framework of Self-supervised Learning pdf

Keqi Deng, Long Ma, Songjun Cao, 2021, Interspeech.

Improving Speech Recognition Accuracy of Local POI Using Geographical Models

Yike Zhang, Songjun Cao, Long Ma, 2021, 2021 IEEE Spoken Language Technology Workshop (SLT).

Improving Hybrid CTC/Attention End-to-End Speech Recognition with Pretrained Acoustic and Language Models pdf

Keqi Deng, Long Ma, Songjun Cao, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

DistillW2V2: A Small and Streaming Wav2vec 2.0 Based ASR Model

Songjun Cao, Long Ma, Yueteng Kang, 2023, ArXiv.

Explore wav2vec 2.0 for Mispronunciation Detection

Xiaoshuo Xu, Binghuai Lin, Long Ma, 2021, Interspeech.