Qiujia Li

Confidence Estimation for Attention-Based Sequence-to-Sequence Models for Speech Recognition pdf

Liangliang Cao, Philip C. Woodland, Yu Zhang, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Combining Frame-Synchronous and Label-Synchronous Systems for Speech Recognition

Philip C. Woodland, Qiujia Li, Chao Zhang, 2021, SSRN Electronic Journal.

Knowledge Distillation for Neural Transducers from Large Self-Supervised Pre-trained Models

Philip C. Woodland, Qiujia Li, Xiaoyu Yang, 2021 .

Multi-Task Learning for End-to-End ASR Word and Utterance Confidence with Deletion Prediction pdf

Ian McGraw, Liangliang Cao, Qiujia Li, 2021, Interspeech.

Residual Energy-Based Models for End-to-End Speech Recognition pdf

Liangliang Cao, Philip C. Woodland, Qiujia Li, 2021, Interspeech 2021.

Learning Word-Level Confidence for Subword End-To-End ASR

Tara N. Sainath, Ian McGraw, Liangliang Cao, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Confidence Estimation on Out-of-Domain Data for End-to-End Speech Recognition pdf

Philip C. Woodland, Qiujia Li, David Qiu, 2021, ArXiv.