Chaojun Liu

Large margin HMMs for speech recognition

Hui Jiang, Xinwei Li, Chaojun Liu, 2005, Proceedings. (ICASSP '05). IEEE International Conference on Acoustics, Speech, and Signal Processing, 2005..

Normalization of ASR Confidence Classifier Scores via Confidence Mapping

Y. Gong, Chaojun Liu, Kshitiz Kumar, 2021 .

Investigations on speaker adaptation of LSTM RNN models for speech recognition

Yongqiang Wang, Yifan Gong, Kshitiz Kumar, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Estimating confidence scores on ASR results using recurrent neural networks

Kaisheng Yao, Yifan Gong, Kaustubh Kalgaonkar, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Predicting speech recognition confidence using deep learning with word identity and score features

Yifan Gong, Po-Sen Huang, Li Deng, 2013, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

Confidence-features and confidence-scores for ASR applications in arbitration and DNN speaker adaptation

Yifan Gong, Yong Zhao, Benoît Dumoulin, 2015, INTERSPEECH.

Normalization of ASR confidence classifier scores via confidence mapping

Yifan Gong, Kshitiz Kumar, Chaojun Liu, 2014, INTERSPEECH.

Recurrent support vector machines for speech recognition

Yifan Gong, Jinyu Li, Shi-Xiong Zhang, 2016, 2016 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Deep neural support vector machines for speech recognition

Kaisheng Yao, Yifan Gong, Shi-Xiong Zhang, 2015, 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Large margin hidden Markov models for speech recognition

Hui Jiang, Xinwei Li, Chaojun Liu, 2006, IEEE Transactions on Audio, Speech, and Language Processing.

Challenges in and Solutions to Deep Learning Network Acoustic Modeling in Speech Recognition Products at Microsoft

Yifan Gong, Jinyu Li, Yan Huang, 2017, New Era for Robust Speech Recognition, Exploiting Deep Learning.