Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Philip C. Woodland

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


Mar 25, 2021
Qiujia Li, Yu Zhang, Bo Li, Liangliang Cao, Philip C. Woodland

* Submitted to Interspeech 2021 

  Access Paper or Ask Questions

A Distributed Optimisation Framework Combining Natural Gradient with Hessian-Free for Discriminative Sequence Training


Mar 12, 2021
Adnan Haider, Chao Zhang, Florian L. Kreyssig, Philip C. Woodland


  Access Paper or Ask Questions

Emotion recognition by fusing time synchronous and time asynchronous representations


Oct 27, 2020
Wen Wu, Chao Zhang, Philip C. Woodland


  Access Paper or Ask Questions

Confidence Estimation for Attention-based Sequence-to-sequence Models for Speech Recognition


Oct 23, 2020
Qiujia Li, David Qiu, Yu Zhang, Bo Li, Yanzhang He, Philip C. Woodland, Liangliang Cao, Trevor Strohman

* Submitted to ICASSP 2021 

  Access Paper or Ask Questions

Improved Large-margin Softmax Loss for Speaker Diarisation


Nov 10, 2019
Yassir Fathullah, Chao Zhang, Philip C. Woodland

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Discriminative Neural Clustering for Speaker Diarisation


Oct 22, 2019
Qiujia Li, Florian L. Kreyssig, Chao Zhang, Philip C. Woodland

* Submitted to ICASSP 2020 

  Access Paper or Ask Questions

Integrating Source-channel and Attention-based Sequence-to-sequence Models for Speech Recognition


Oct 01, 2019
Qiujia Li, Chao Zhang, Philip C. Woodland

* To appear in Proc. ASRU2019, December 14-18, 2019, Sentosa, Singapore 

  Access Paper or Ask Questions

Sequence Training of DNN Acoustic Models With Natural Gradient


Apr 06, 2018
Adnan Haider, Philip C. Woodland

* In Proceedings of IEEE ASRU 2017 

  Access Paper or Ask Questions