黄志华｜新疆大学｜学者主页

2026

TSRH-Net: A serial time-frequency backbone with SNR-gated refinement for extremely low-SNR speech enhancement

Bixin Wu, Zhihua Huang, Yujie Xiong, Wenjie Su, Yonghong Yan

Applied Acoustics

DOI

2026

Improving Audio Anti-Spoofing with FLA and Local-global Feature Fusion

Jialei Sang, Zhihua Huang

International Conference on Electronic Engineering and Informatics (EEI)

DOI

2026

DyTSwiG-Mamba: Layer Normalization-Free CNN-Mamba Speech Enhancement Network With Dual-Branch Phase Prediction

Yujie Xiong, Zhihua Huang, Bixin Wu

IEEE Transactions on Audio Speech and Language Processing

DOI

2026

CL-EDiff: Cross-Lingual Emotional TTS System Based on Diffusion Model

Haiyang Zhou, Zhihua Huang, Bowen Li

Communications in computer and information science

DOI

2025

A comprehensive validation study on the influencing factors of cough-based COVID-19 detection through multi-center data with abundant metadata

Jiakun Shen, Xueshuai Zhang, Yanfen Tang, Pengyuan Zhang, Yong-Hong Yan, Peng-Fei Ye, Shaoxing Zhang, Zhihua Huang

Journal of Biomedical Informatics

DOI

2025

ZCS-CDiff: A Zero-Shot Code-Switching TTS System with Conformer-Based Diffusion Model

Ke Chen, Zhihua Huang, Liang Ju He, Yonghong Yan

IEEE International Conference on Acoustics Speech and Signal Processing

DOI

2024

Fast Sampling Based on Policy Gradient for Diffusion-Based Speech Enhancement

Yubo Jiang, Zhihua Huang

DOI

2024

CosDiff: Code-Switching TTS Model Based on A Multi-Task DDIM

Ke Chen, Zhihua Huang, Kexin Lu, Yonghong Yan

IEEE International Conference on Multimedia and Expo (ICME)

DOI

2024

M-CMGAN: Attempting to Use Mamba on Speech Enhancement

Yu-Jie Xiong, Zhihua Huang

Communications in computer and information science

DOI

2024

Cross-Model Knowledge Distillation and Metadata Fusion for Respiratory Sound Classification

Zhengyang Sun, Zhihua Huang, Xueyuan Xu, Binyu Li

Communications in computer and information science

DOI

2024

The Contributions of Formants to the Intelligibility in Uyghur Sine-Wave Sentences

Xiaoming Liang, Zhihua Huang

DOI

2024

The Contribution of Sub-Band Temporal Fine Structure to the Intelligibility of Uyghur Sentences

Jingyi Song, Zhihua Huang, Ruilin Wu, Xiaoming Liang

IEEE International Conference on Pattern Recognition and Machine Learning (PRML)

DOI

2024

Optimizing Uyghur Speech Synthesis by Combining Pretrained Cross-Lingual Model

Kexin Lu, Zhihua Huang, Mingming Yin, Ke Chen

ACM Transactions on Asian and Low-Resource Language Information Processing

DOI

2024

Improving Speech Perceptual Quality and Intelligibility Through Sub-band Temporal Envelope Characteristics

Ruilin Wu, Zhihua Huang, Jingyi Song, Xiaoming Liang

Communications in computer and information science

DOI

2023

Piecewise Position Encoding in Convolutional Neural Network for Cough-Based Covid-19 Detection

Jiakun Shen, Xueshuai Zhang, Peng-Yuan Zhang, Yong-Hong Yan, Shenmin Zhang, Zhihua Huang, Yanfen Tang, Yu Wang, Fu-Jie Zhang, Aijun Sun

IEEE International Conference on Acoustics, Speech, and Signal Processing

DOI

2023

YOLO-Drone: An Optimized YOLOv8 Network for Tiny UAV Object Detection

Xianxu Zhai, Zhihua Huang, Tao Li, Hanzhe Liu, Siyuan Wang

Electronics

DOI

2023

Keyword Spotting Based on Efficient Neural Architecture Search

Wenchen Liu, Zhihua Huang, Dafei Wang

IEEE International Conference on Pattern Recognition and Machine Learning (PRML)

DOI

2023

MetricGAN+ Speech Enhancement Model Combining Multi-scale and Multi-resolution Feature Network and Joint Perception Loss

Chuangjian Guo, Zhihua Huang, Hui Li, Jingyi Song

IEEE International Conference on Pattern Recognition and Machine Learning (PRML)

DOI

2022

基于时域的基频感知语音分离方法

王凯，李鸣鹤，黄志华，黄浩

《新疆大学学报(自然科学版中英文)》

2022

基于深度压缩感知的语音增强模型

康峥，黄志华，赖惠成

《声学技术》

2022

Two-Branch Network with Selective Kernel Convolution for Time-Domain Speech Enhancement

Hui Li, Zhihua Huang, Chuangjian Guo

International Symposium on Chinese Spoken Language Processing

DOI

2022

Robust Cough Feature Extraction and Classification Method for COVID-19 Cough Detection Based on Vocalization Characteristics

Xueshuai Zhang, Jiakun Shen, J. Zhou, Peng-Yuan Zhang, Yong-Hong Yan, Zhihua Huang, Yanfen Tang, Yu Wang, Fu-Jie Zhang, Shenmin Zhang, Aijun Sun

Interspeech

DOI

2022

Low-Resource Speech Keyword Search Based on Residual Neural Network

Da-Fei Wang, Zhihua Huang, Hui Li, Wencheng Liu

Chinese Conference on Biometric Recognition

DOI

2022

Speech Enhancement Using U-Net with Compressed Sensing

Zhenguo Kang, Zhihua Huang, Chenshen Lu

Applied Sciences

DOI

2021

注意力机制对生成对抗网络语音增强迁移学习模型的影响

曹中辉，黄志华，葛文萍，黄浩

《声学技术》

DOI

2021

End-to-end Speech Enhancement Using Self-Attention Generative Adversarial Networks

Zhonghui Cao, Zhihua Huang

2021 6th International Symposium on Computer and Information Processing Technology (ISCIPT)

DOI

2021

Temporal Convolution Network Based Joint Optimization of Acoustic-to-Articulatory Inversion

Guolun Sun, Zhihua Huang, Li Wang, Peng-Yuan Zhang

Applied Sciences

DOI

2021

LinearSpeech: Parallel Text-to-Speech with Linear Complexity

Haozhe Zhang, Zhihua Huang, Zengqiang Shang, Peng-Yuan Zhang, Yong-Hong Yan

Interspeech

DOI

2021

End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain

Kai Wang, Hao Huang, Ying Hu, Zhihua Huang, Sheng Li

Interspeech

DOI

2021

Cough-based COVID-19 Detection with Multi-band Long-Short Term Memory and Convolutional Neural Networks

Jiakun Shen, Xueshuai Zhang, Wenchao Wang, Zhihua Huang, Peng-Yuan Zhang, Yong-Hong Yan

International Symposium on Artificial Intelligence in Medical Sciences

DOI

2021

Incorporating Cross-Speaker Style Transfer for Multi-Language Text-to-Speech

Zengqiang Shang, Zhihua Huang, Haozhe Zhang, Peng-Yuan Zhang, Yong-Hong Yan

Interspeech

DOI

2021

A Pronunciation Prior Assisted Vowel Reduction Detection Framework with Multi-Stream Attention Method

Zong-Ming Liu, Zhihua Huang, Li Wang, Peng-Yuan Zhang

Applied Sciences

DOI

2021

Connectionist temporal classification loss for vector quantized variational autoencoder in zero-shot voice conversion

Xiaoyang Kang, Hao Huang, Ying Hu, Zhihua Huang

Digit. Signal Process.

DOI

黄志华

精选作品

期刊论文

TSRH-Net: A serial time-frequency backbone with SNR-gated refinement for extremely low-SNR speech enhancement

Improving Audio Anti-Spoofing with FLA and Local-global Feature Fusion

DyTSwiG-Mamba: Layer Normalization-Free CNN-Mamba Speech Enhancement Network With Dual-Branch Phase Prediction

CL-EDiff: Cross-Lingual Emotional TTS System Based on Diffusion Model

A comprehensive validation study on the influencing factors of cough-based COVID-19 detection through multi-center data with abundant metadata

ZCS-CDiff: A Zero-Shot Code-Switching TTS System with Conformer-Based Diffusion Model

Fast Sampling Based on Policy Gradient for Diffusion-Based Speech Enhancement

CosDiff: Code-Switching TTS Model Based on A Multi-Task DDIM

M-CMGAN: Attempting to Use Mamba on Speech Enhancement

Cross-Model Knowledge Distillation and Metadata Fusion for Respiratory Sound Classification

The Contributions of Formants to the Intelligibility in Uyghur Sine-Wave Sentences

The Contribution of Sub-Band Temporal Fine Structure to the Intelligibility of Uyghur Sentences

Optimizing Uyghur Speech Synthesis by Combining Pretrained Cross-Lingual Model

Improving Speech Perceptual Quality and Intelligibility Through Sub-band Temporal Envelope Characteristics

Piecewise Position Encoding in Convolutional Neural Network for Cough-Based Covid-19 Detection

YOLO-Drone: An Optimized YOLOv8 Network for Tiny UAV Object Detection

Keyword Spotting Based on Efficient Neural Architecture Search

MetricGAN+ Speech Enhancement Model Combining Multi-scale and Multi-resolution Feature Network and Joint Perception Loss

基于时域的基频感知语音分离方法

基于深度压缩感知的语音增强模型

Two-Branch Network with Selective Kernel Convolution for Time-Domain Speech Enhancement

Robust Cough Feature Extraction and Classification Method for COVID-19 Cough Detection Based on Vocalization Characteristics

Low-Resource Speech Keyword Search Based on Residual Neural Network

Speech Enhancement Using U-Net with Compressed Sensing

注意力机制对生成对抗网络语音增强迁移学习模型的影响

End-to-end Speech Enhancement Using Self-Attention Generative Adversarial Networks

Temporal Convolution Network Based Joint Optimization of Acoustic-to-Articulatory Inversion

LinearSpeech: Parallel Text-to-Speech with Linear Complexity

End-to-End Speech Separation Using Orthogonal Representation in Complex and Real Time-Frequency Domain

Cough-based COVID-19 Detection with Multi-band Long-Short Term Memory and Convolutional Neural Networks

Incorporating Cross-Speaker Style Transfer for Multi-Language Text-to-Speech

A Pronunciation Prior Assisted Vowel Reduction Detection Framework with Multi-Stream Attention Method

Connectionist temporal classification loss for vector quantized variational autoencoder in zero-shot voice conversion

会议论文

共振峰对维吾尔语语音可懂度的影响

基于噪声稀疏特性的语音增强算法分析

研究方向