Songjun Cao

Explore wav2vec 2.0 for Mispronunciation Detection

Xiaoshuo Xu, Yueteng Kang, Songjun Cao et al. · 2021 · 45 citations

Wav2vec 2.0, Robust Speech Recognition, Speech Processing +2

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

Keqi Deng, Songjun Cao, Long Ma · 2021 · 30 citations

Engineering, Machine Learning, Speech Recognition +21

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

Keqi Deng, Songjun Cao, Yike Zhang et al. · ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) · 2022 · 29 citations

Llm Fine-tuning, Engineering, Machine Learning +23

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

Keqi Deng, Songjun Cao, Yike Zhang et al. · 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) · 2021 · 16 citations

Engineering, Machine Learning, Self-supervised Pretraining Methods +21

Multi-head Monotonic Chunkwise Attention For Online Speech Recognition

Baiji Liu, Songjun Cao, Sining Sun et al. · arXiv (Cornell University) · 2020 · 13 citations · Full text

Engineering, Machine Learning, Neurolinguistics +20