Alert button
Picture for Chunlei Zhang

Chunlei Zhang

Alert button

uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models

Oct 02, 2023
Muqiao Yang, Chunlei Zhang, Yong Xu, Zhongweiyang Xu, Heming Wang, Bhiksha Raj, Dong Yu

Figure 1 for uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Figure 2 for uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Figure 3 for uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Figure 4 for uSee: Unified Speech Enhancement and Editing with Conditional Diffusion Models
Viaarxiv icon

Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions

Sep 16, 2023
Heming Wang, Meng Yu, Hao Zhang, Chunlei Zhang, Zhongweiyang Xu, Muqiao Yang, Yixuan Zhang, Dong Yu

Figure 1 for Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Figure 2 for Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Figure 3 for Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Figure 4 for Unifying Robustness and Fidelity: A Comprehensive Study of Pretrained Generative Methods for Speech Enhancement in Adverse Conditions
Viaarxiv icon

Make-A-Voice: Unified Voice Synthesis With Discrete Representation

May 30, 2023
Rongjie Huang, Chunlei Zhang, Yongqi Wang, Dongchao Yang, Luping Liu, Zhenhui Ye, Ziyue Jiang, Chao Weng, Zhou Zhao, Dong Yu

Figure 1 for Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Figure 2 for Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Figure 3 for Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Figure 4 for Make-A-Voice: Unified Voice Synthesis With Discrete Representation
Viaarxiv icon

C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification

Aug 15, 2022
Chunlei Zhang, Dong Yu

Figure 1 for C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
Figure 2 for C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
Figure 3 for C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
Figure 4 for C3-DINO: Joint Contrastive and Non-contrastive Self-Supervised Learning for Speaker Verification
Viaarxiv icon

UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder

Jun 07, 2022
Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli, Dong Yu

Figure 1 for UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder
Figure 2 for UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder
Figure 3 for UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder
Figure 4 for UTTS: Unsupervised TTS with Conditional Disentangled Sequential Variational Auto-encoder
Viaarxiv icon

LAE: Language-Aware Encoder for Monolingual and Multilingual ASR

Jun 05, 2022
Jinchuan Tian, Jianwei Yu, Chunlei Zhang, Chao Weng, Yuexian Zou, Dong Yu

Figure 1 for LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Figure 2 for LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Figure 3 for LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Figure 4 for LAE: Language-Aware Encoder for Monolingual and Multilingual ASR
Viaarxiv icon

NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement

May 20, 2022
Meng Yu, Yong Xu, Chunlei Zhang, Shi-Xiong Zhang, Dong Yu

Figure 1 for NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Figure 2 for NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Figure 3 for NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Figure 4 for NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement
Viaarxiv icon

Towards Improved Zero-shot Voice Conversion with Conditional DSVAE

May 11, 2022
Jiachen Lian, Chunlei Zhang, Gopala Krishna Anumanchipalli, Dong Yu

Figure 1 for Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Figure 2 for Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Figure 3 for Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Figure 4 for Towards Improved Zero-shot Voice Conversion with Conditional DSVAE
Viaarxiv icon

EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers

Mar 31, 2022
Yushi Ueda, Soumi Maiti, Shinji Watanabe, Chunlei Zhang, Meng Yu, Shi-Xiong Zhang, Yong Xu

Figure 1 for EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers
Figure 2 for EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers
Figure 3 for EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers
Figure 4 for EEND-SS: Joint End-to-End Neural Speaker Diarization and Speech Separation for Flexible Number of Speakers
Viaarxiv icon

Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion

Mar 30, 2022
Jiachen Lian, Chunlei Zhang, Dong Yu

Figure 1 for Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
Figure 2 for Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
Figure 3 for Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
Figure 4 for Robust Disentangled Variational Speech Representation Learning for Zero-shot Voice Conversion
Viaarxiv icon