Zhiyong Wu

发表

Disambiguation of Chinese Polyphones in an End-to-End Framework with Semantic Features Extracted by Pre-Trained BERT

Dan Su, Zhiyong Wu, Dong Yu, 2019, INTERSPEECH.

Tackling Spoofing-Aware Speaker Verification with Multi-Model Fusion

Haibin Wu, Hung-yi Lee, H. Meng, 2022, Odyssey.

Adversarial Sample Detection for Speaker Verification by Neural Vocoders

Shanshan Zhang, Haibin Wu, Hung-yi Lee, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Emotion Controllable Speech Synthesis Using Emotion-Unlabeled Dataset with the Assistance of Cross-Domain Speech Emotion Recognition pdf

Helen Meng, Zhiyong Wu, Xiong Cai, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Enhancing Word-Level Semantic Representation via Dependency Structure for Expressive Text-to-Speech Synthesis

H. Meng, Dan Su, Zhiyong Wu, 2021, INTERSPEECH.

FusionFormer: Fusing Operations in Transformer for Efficient Streaming Speech Recognition

Binbin Zhang, Peng Zhang, Di Wu, 2022, ArXiv.

Speech Representation Disentanglement with Adversarial Mutual Information Learning for One-shot Voice Conversion

H. Meng, Jianzong Wang, Zhiyong Wu, 2022, INTERSPEECH.

VocEmb4SVS: Improving Singing Voice Separation with Vocal Embeddings

Shichao Hu, Zhiyong Wu, Yi Li, 2022, 2022 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC).

Generating emphatic speech with hidden Markov model for expressive speech synthesis

Lianhong Cai, Jia Jia, Zhiyong Wu, 2014, Multimedia Tools and Applications.

One-Shot Voice Conversion with Global Speaker Embeddings

Zhiyong Wu, Helen Meng, Runnan Li, 2019, INTERSPEECH.

Towards Cross-speaker Reading Style Transfer on Audiobook Dataset

H. Meng, Zhiyong Wu, Xiang Li, 2022, INTERSPEECH.

A Review of Deep Learning Based Speech Synthesis

Zhiyong Wu, Sheng He, Yishuang Ning, 2019, Applied Sciences.

Code-Switched Speech Synthesis Using Bilingual Phonetic Posteriorgram with Only Monolingual Corpora

Songxiang Liu, Yuewen Cao, Dan Su, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Speech-XLNet: Unsupervised Acoustic Model Pretraining For Self-Attention Networks

Dong Yu, H. Meng, Dan Su, 2019, INTERSPEECH.

Neural Architecture Search for Speech Emotion Recognition

H. Meng, Xunying Liu, Xixin Wu, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Adversarially learning disentangled speech representations for robust multi-factor voice conversion pdf

Zhiyong Wu, Helen Meng, Jingbei Li, 2021, Interspeech.

Enhancing the Vocal Range of Single-Speaker Singing Voice Synthesis with Melody-Unsupervised Pre-Training

H. Meng, Xu Li, Zhiyong Wu, 2023, IEEE International Conference on Acoustics, Speech, and Signal Processing.

TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length Penalty

Binbin Zhang, Di Wu, Zhiyong Wu, 2022, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

ZeroPrompt: Streaming Acoustic Encoders are Zero-Shot Masked LMs

Binbin Zhang, Di Wu, Zhiyong Wu, 2023, ArXiv.

MFA-Conformer: Multi-scale Feature Aggregation Conformer for Automatic Speaker Verification

Haibin Wu, Hung-yi Lee, H. Meng, 2022, INTERSPEECH.

Neufa: Neural Network Based End-to-End Forced Alignment with Bidirectional Attention Mechanism

H. Meng, Qiao Tian, Zhiyong Wu, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Disentangled Speech Representation Learning for One-Shot Cross-Lingual Voice Conversion Using ß-VAE

Helen M. Meng, Xunying Liu, Xixin Wu, 2022, Spoken Language Technology Workshop.

Av-Sepformer: Cross-Attention Sepformer for Audio-Visual Target Speaker Extraction

Helen M. Meng, Heinrich Dinkel, Zhiyong Wu, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Reconstructing Dual Learning for Neural Voice Conversion Using Relatively Few Samples

H. Meng, Jianzong Wang, Jing Xiao, 2021, Automatic Speech Recognition & Understanding.

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

H. Meng, Z. Wang, Zhiyong Wu, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Adversarial Speaker Disentanglement Using Unannotated External Data for Self-supervised Representation Based Voice Conversion

H. Meng, Zhiyong Wu, Shuai Wang, 2023, 2305.09167.

Acoustic to articulatory mapping with deep neural network

Kai Zhao, Xixin Wu, Zhiyong Wu, 2014, Multimedia Tools and Applications.

GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained Genre Token Network

H. Meng, Zhiyong Wu, Weiqing Li, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Adversarial Defense for Automatic Speaker Verification by Cascaded Self-Supervised Learning Models

Haibin Wu, Hung-yi Lee, Zhiyong Wu, 2021, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-To-End Accent Conversion Without Using Native Utterances

Songxiang Liu, Yuewen Cao, Dan Su, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Information

Heinrich Dinkel, Zhiyong Wu, Zhiyong Yan, 2023, Interspeech.

Unsupervised Multi-scale Expressive Speaking Style Modeling with Hierarchical Context Information for Audiobook Speech Synthesis

Dong Xu, H. Meng, Zhiyong Wu, 2022, COLING.

FERNet: Fine-grained Extraction and Reasoning Network for Emotion Recognition in Dialogues

Mingxing Xu, Zhiyong Wu, Yingmei Guo, 2020, AACL.

LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech

Jing Chen, Binbin Zhang, Zhiyong Wu, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Disentangling Content and Fine-Grained Prosody Information Via Hybrid ASR Bottleneck Features for Voice Conversion

H. Meng, Zhiyong Wu, Changhe Song, 2022, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Improving Language Model-Based Zero-Shot Text-to-Speech Synthesis with Multi-Scale Acoustic Prompts

Tao Jiang, Xixin Wu, Zhiyong Wu, 2023, ArXiv.

Content-Dependent Fine-Grained Speaker Embedding for Zero-Shot Speaker Adaptation in Text-to-Speech Synthesis

H. Meng, Dan Su, Zhiyong Wu, 2022, INTERSPEECH.

TFCnet: Time-Frequency Domain Corrector for Speech Separation

H. Meng, Zhiyong Wu, Jun Chen, 2023, ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Enhancing Monotonicity for Robust Autoregressive Transformer TTS

Sheng Zhao, Zhiyong Wu, Runnan Li, 2020, INTERSPEECH.

Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement pdf

Yuxuan Wang, Zhiyong Wu, Mu Wang, 2020, ArXiv.

Enhancing Speaking Styles in Conversational Text-to-Speech Synthesis with Graph-Based Multi-Modal Context Modeling

H. Meng, Chao Weng, Dan Su, 2021, ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Syntactic Representation Learning For Neural Network Based TTS with Syntactic Parse Tree Traversal pdf

Helen Meng, Zhiyong Wu, Changhe Song, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Focus on the Sound around You: Monaural Target Speaker Extraction via Distance and Speaker Information

Heinrich Dinkel, Zhiyong Wu, Zhiyong Yan, 2023, INTERSPEECH 2023.

Conversational Co-Speech Gesture Generation via Modeling Dialog Intention, Emotion, and Context with Diffusion Models

Zhiyong Wu, Zhensong Zhang, Sicheng Yang, 2023, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Re-Weighted Interval Loss for Handling Data Imbalance Problem of End-to-End Keyword Spotting

Kun Zhang, Binheng Song, Zhiyong Wu, 2020, INTERSPEECH.

HILvoice:Human-in-the-Loop Style Selection for Elder-Facing Speech Synthesis

H. Meng, Xixin Wu, Zhiyong Wu, 2022, 2022 13th International Symposium on Chinese Spoken Language Processing (ISCSLP).

CALM: Contrastive Cross-modal Speaking Style Modeling for Expressive Text-to-Speech Synthesis

H. Meng, Zhiyong Wu, Xiang Li, 2023, ArXiv.

MSStyleTTS: Multi-Scale Style Modeling With Hierarchical Context Information for Expressive Speech Synthesis

H. Meng, Xixin Wu, Zhiyong Wu, 2023, IEEE/ACM Transactions on Audio, Speech, and Language Processing.

Neural Concatenative Singing Voice Conversion: Rethinking Concatenation-Based Approach for One-Shot Singing Voice Conversion

Zhiyong Wu, Yin Shan, Helen Meng, 2023, ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information

H. Meng, Zhiyong Wu, Deyi Tuo, 2022, INTERSPEECH.

Inferring Speaking Styles from Multi-modal Conversational Context by Multi-scale Relational Graph Convolutional Networks

H. Meng, Xixin Wu, Qiao Tian, 2022, ACM Multimedia.