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

Add to Chrome

Add to Firefox

Picture for Helen Meng

Helen Meng

FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

Mar 26, 2022
Jun Chen, Zilin Wang, Deyi Tuo, Zhiyong Wu, Shiyin Kang, Helen Meng

Figure 1 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

Figure 2 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

Figure 3 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

Figure 4 for FullSubNet+: Channel Attention FullSubNet with Complex Spectrograms for Speech Enhancement

* Accepted by ICASSP 2022

Access Paper or Ask Questions

Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

Mar 24, 2022
Xintao Zhao, Feng Liu, Changhe Song, Zhiyong Wu, Shiyin Kang, Deyi Tuo, Helen Meng

Figure 1 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

Figure 2 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

Figure 3 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

Figure 4 for Disentangleing Content and Fine-grained Prosody Information via Hybrid ASR Bottleneck Features for Voice Conversion

* Accepted by ICASSP 2022

Access Paper or Ask Questions

A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

Mar 22, 2022
Haohan Guo, Hui Lu, Xixin Wu, Helen Meng

Figure 1 for A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

Figure 2 for A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

Figure 3 for A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

Figure 4 for A Multi-Scale Time-Frequency Spectrogram Discriminator for GAN-based Non-Autoregressive TTS

* Submitted to INTERSPEECH 2022

Access Paper or Ask Questions

Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

Mar 19, 2022
Shujie Hu, Shansong Liu, Xurong Xie, Mengzhe Geng, Tianzi Wang, Shoukang Hu, Mingyu Cui, Xunying Liu, Helen Meng

Figure 1 for Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

Figure 2 for Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

Figure 3 for Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

Figure 4 for Exploiting Cross Domain Acoustic-to-articulatory Inverted Features For Disordered Speech Recognition

* accepted by ICASSP 2022

Access Paper or Ask Questions

Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

Mar 17, 2022
Mengzhe Geng, Xurong Xie, Zi Ye, Tianzi Wang, Guinan Li, Shujie Hu, Xunying Liu, Helen Meng

Figure 1 for Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

Figure 2 for Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

Figure 3 for Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

Figure 4 for Speaker Adaptation Using Spectro-Temporal Deep Features for Dysarthric and Elderly Speech Recognition

* In submission to IEEE/ACM Transactions on Audio Speech and Language Processing

Access Paper or Ask Questions

Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

Feb 18, 2022
Disong Wang, Songxiang Liu, Xixin Wu, Hui Lu, Lifa Sun, Xunying Liu, Helen Meng

Figure 1 for Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

Figure 2 for Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

Figure 3 for Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

Figure 4 for Speaker Identity Preservation in Dysarthric Speech Reconstruction by Adversarial Speaker Adaptation

* Accepted to ICASSP 2022. Demo page is available at https://wendison.github.io/ASA-DSR-demo/

Access Paper or Ask Questions

VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

Feb 18, 2022
Disong Wang, Shan Yang, Dan Su, Xunying Liu, Dong Yu, Helen Meng

Figure 1 for VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

Figure 2 for VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

Figure 3 for VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

Figure 4 for VCVTS: Multi-speaker Video-to-Speech synthesis via cross-modal knowledge transfer from voice conversion

* Accepted to ICASSP 2022. Demo page is available at https://wendison.github.io/VCVTS-demo/

Access Paper or Ask Questions