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

Add to Chrome

Add to Firefox

Picture for Viet Anh Trinh

Viet Anh Trinh

CUNY Graduate Center

Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation

Jul 16, 2022
Viet Anh Trinh, Pegah Ghahremani, Brian King, Jasha Droppo, Andreas Stolcke, Roland Maas

Figure 1 for Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation

Figure 2 for Reducing Geographic Disparities in Automatic Speech Recognition via Elastic Weight Consolidation

* Accepted for publication at Interspeech 2022

Access Paper or Ask Questions

ImportantAug: a data augmentation agent for speech

Dec 14, 2021
Viet Anh Trinh, Hassan Salami Kavaki, Michael I Mandel

Figure 1 for ImportantAug: a data augmentation agent for speech

Figure 2 for ImportantAug: a data augmentation agent for speech

Figure 3 for ImportantAug: a data augmentation agent for speech

Figure 4 for ImportantAug: a data augmentation agent for speech

* Submitted to ICASSP 2022

Access Paper or Ask Questions

Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses

Nov 16, 2021
Viet Anh Trinh, Sebastian Braun

Figure 1 for Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses

Figure 2 for Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses

Figure 3 for Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses

Figure 4 for Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses

* Submitted to ICASSP 2022

Access Paper or Ask Questions

Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

Dec 02, 2020
Felix Grezes, Zhaoheng Ni, Viet Anh Trinh, Michael Mandel

Figure 1 for Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

Figure 2 for Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

Figure 3 for Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

Figure 4 for Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement

* arXiv admin note: text overlap with arXiv:2012.01576, arXiv:2012.02191

Access Paper or Ask Questions

Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Dec 02, 2020
Zhaoheng Ni, Felix Grezes, Viet Anh Trinh, Michael I. Mandel

Figure 1 for Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Figure 2 for Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Figure 3 for Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

Figure 4 for Improved MVDR Beamforming Using LSTM Speech Models to Clean Spatial Clustering Masks

* arXiv admin note: substantial text overlap with arXiv:2012.01576

Access Paper or Ask Questions

Large scale evaluation of importance maps in automatic speech recognition

May 21, 2020
Viet Anh Trinh, Michael I Mandel

Figure 1 for Large scale evaluation of importance maps in automatic speech recognition

Figure 2 for Large scale evaluation of importance maps in automatic speech recognition

Figure 3 for Large scale evaluation of importance maps in automatic speech recognition

Figure 4 for Large scale evaluation of importance maps in automatic speech recognition

* submitted to INTERSPEECH 2020

Access Paper or Ask Questions