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 Peter Bell

It's not what you said, it's how you said it: discriminative perception of speech as a multichannel communication system


May 01, 2021
Sarenne Wallbridge, Peter Bell, Catherine Lai


  Access Paper or Ask Questions

Segmenting Subtitles for Correcting ASR Segmentation Errors


Apr 16, 2021
David Wan, Chris Kedzie, Faisal Ladhak, Elsbeth Turcan, Petra Galuščáková, Elena Zotkina, Zhengping Jiang, Peter Bell, Kathleen McKeown


  Access Paper or Ask Questions

Train your classifier first: Cascade Neural Networks Training from upper layers to lower layers


Feb 09, 2021
Shucong Zhang, Cong-Thanh Do, Rama Doddipatla, Erfan Loweimi, Peter Bell, Steve Renals

* Accepted by ICASSP 2021 

  Access Paper or Ask Questions

Enhancing Human Pose Estimation in Ancient Vase Paintings via Perceptually-grounded Style Transfer Learning


Dec 10, 2020
Prathmesh Madhu, Angel Villar-Corrales, Ronak Kosti, Torsten Bendschus, Corinna Reinhardt, Peter Bell, Andreas Maier, Vincent Christlein

* Link to the repository containing the code to reproduce the experiments. For further details, please read the README. Link: https://anonymous.4open.science/r/3b1bd8ac-bd3a-4df6-8671-56d4f9bdbd8d/ 

  Access Paper or Ask Questions

On the Usefulness of Self-Attention for Automatic Speech Recognition with Transformers


Nov 08, 2020
Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals

* arXiv admin note: substantial text overlap with arXiv:2005.13895 

  Access Paper or Ask Questions

Stochastic Attention Head Removal: A Simple and Effective Method for Improving Automatic Speech Recognition with Transformers


Nov 08, 2020
Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals


  Access Paper or Ask Questions

Leveraging speaker attribute information using multi task learning for speaker verification and diarization


Oct 27, 2020
Chau Luu, Peter Bell, Steve Renals

* Submitted to ICASSP 2021 

  Access Paper or Ask Questions

Subtitles to Segmentation: Improving Low-Resource Speech-to-Text Translation Pipelines


Oct 19, 2020
David Wan, Zhengping Jiang, Chris Kedzie, Elsbeth Turcan, Peter Bell, Kathleen McKeown

* [email protected] 2020 68-73 

  Access Paper or Ask Questions

Understanding Compositional Structures in Art Historical Images using Pose and Gaze Priors


Sep 08, 2020
Prathmesh Madhu, Tilman Marquart, Ronak Kosti, Peter Bell, Andreas Maier, Vincent Christlein

* To be Published in ECCV 2020 Workshops (VISART V) 

  Access Paper or Ask Questions

Adaptation Algorithms for Speech Recognition: An Overview


Aug 14, 2020
Peter Bell, Joachim Fainberg, Ondrej Klejch, Jinyu Li, Steve Renals, Pawel Swietojanski

* Submitted to IEEE Open Journal of Signal Processing. 30 pages, 27 figures 

  Access Paper or Ask Questions

When Can Self-Attention Be Replaced by Feed Forward Layers?


May 28, 2020
Shucong Zhang, Erfan Loweimi, Peter Bell, Steve Renals


  Access Paper or Ask Questions

Recognizing Characters in Art History Using Deep Learning


Apr 01, 2020
Prathmesh Madhu, Ronak Kosti, Lara Mührenberg, Peter Bell, Andreas Maier, Vincent Christlein

* In Proceedings of the 1st Workshop on Structuring and Understanding of Multimedia heritAge Contents, pp. 15-22 (2019, October) 

  Access Paper or Ask Questions

DropClass and DropAdapt: Dropping classes for deep speaker representation learning


Feb 02, 2020
Chau Luu, Peter Bell, Steve Renals

* Submitted to Speaker Odyssey 2020 

  Access Paper or Ask Questions

Multi-scale Octave Convolutions for Robust Speech Recognition


Oct 31, 2019
Joanna Rownicka, Peter Bell, Steve Renals

* submitted to ICASSP2020 

  Access Paper or Ask Questions

Channel adversarial training for speaker verification and diarization


Oct 25, 2019
Chau Luu, Peter Bell, Steve Renals

* Submitted to IEEE ICASSP 2020 

  Access Paper or Ask Questions

Speaker Adaptive Training using Model Agnostic Meta-Learning


Oct 23, 2019
Ondřej Klejch, Joachim Fainberg, Peter Bell, Steve Renals

* Accepted to IEEE ASRU 2019 

  Access Paper or Ask Questions

Acoustic Model Adaptation from Raw Waveforms with SincNet


Sep 30, 2019
Joachim Fainberg, Ondřej Klejch, Erfan Loweimi, Peter Bell, Steve Renals

* Accepted to IEEE ASRU 2019 

  Access Paper or Ask Questions

Embeddings for DNN speaker adaptive training


Sep 30, 2019
Joanna Rownicka, Peter Bell, Steve Renals

* Accepted at ASRU 2019 

  Access Paper or Ask Questions

Lattice-Based Unsupervised Test-Time Adaptation of Neural Network Acoustic Models


Jun 27, 2019
Ondrej Klejch, Joachim Fainberg, Peter Bell, Steve Renals


  Access Paper or Ask Questions

Lattice-based lightly-supervised acoustic model training


May 30, 2019
Joachim Fainberg, Ondřej Klejch, Steve Renals, Peter Bell

* Submitted to INTERSPEECH 2019 

  Access Paper or Ask Questions

Analyzing deep CNN-based utterance embeddings for acoustic model adaptation


Nov 12, 2018
Joanna Rownicka, Peter Bell, Steve Renals

* accepted to SLT 2018 

  Access Paper or Ask Questions

Few-shot learning with attention-based sequence-to-sequence models


Nov 08, 2018
Bertrand Higy, Peter Bell

* Submitted to ICASSP 2019 

  Access Paper or Ask Questions

Learning to adapt: a meta-learning approach for speaker adaptation


Aug 30, 2018
Ondřej Klejch, Joachim Fainberg, Peter Bell

* Interspeech 2018 

  Access Paper or Ask Questions

WERd: Using Social Text Spelling Variants for Evaluating Dialectal Speech Recognition


Sep 21, 2017
Ahmed Ali, Preslav Nakov, Peter Bell, Steve Renals

* ASRU-2017 

  Access Paper or Ask Questions

The MGB-2 Challenge: Arabic Multi-Dialect Broadcast Media Recognition


May 14, 2017
Ahmed Ali, Peter Bell, James Glass, Yacine Messaoui, Hamdy Mubarak, Steve Renals, Yifan Zhang


  Access Paper or Ask Questions

Automatic Dialect Detection in Arabic Broadcast Speech


Aug 11, 2016
Ahmed Ali, Najim Dehak, Patrick Cardinal, Sameer Khurana, Sree Harsha Yella, James Glass, Peter Bell, Steve Renals


  Access Paper or Ask Questions