江文斌

杭州电子科技大学通信工程学院，特聘副教授，硕士生导师。

上海交通大学电子工程系博士、计算机科学与工程系博士后。研究方向为智能语音信息处理，主要包括：语音增强、语音唤醒、语音识别、声源分离、语音理解大模型、低码率语音编解码等。主要成果：在声学和语音信号领域的国际顶级期刊和会议IEEE TASLP、ICASSP、InterSpeech等上发表和录用论文十余篇，授权国家发明专利十余项；主持科技部创新专项项目课题，参与多项国家级项目；IEEE会员、CCF语音对话与听觉专业委员会执行委员， ICASSP、InterSpeech、Scientific Reports、ACML、NCMMSC等期刊和会议审稿人。

主持项目/课题：

1. 科技部-科技创新项目课题，多任务语音理解大模型，主持，在研

2. 横向项目，语音感知前沿技术研究，主持，在研

3. 横向项目，智能家居语音指令控制系统研发，主持，在研

4. 横向项目，智能语音交互的语音数据采集系统开发，主持，结题

5. 横向项目，智能语音交互的模型优化与测试系统开发，主持，结题

已发表论文(一作/通信):

[1] W. Jiang, F. Wen and K. Yu, "MOS-GAN: Mean Opinion Score GAN for Unsupervised Speech Enhancement," IEEE Signal Processing Letters, Accepted, 2025.

[2] J. Li, W. Jiang*, Y. Tian, and Z. Li. "NC-KWS: Few-Shot Class-Incremental Keyword Spotting Based on Neural Collapse. 2025 National Conference on Man-Machine Speech Communication (NCMMSC 2025). Accepted. 2025.

[3] Y. Zhang, W. Jiang*, K. Wu, and W. Zhang. "MelGenSE: Generative Speech Enhancement on Mel-Spectrogram via Conditional Flow Matching". 2025 National Conference on Man-Machine Speech Communication (NCMMSC 2025). Accepted. 2025.

[4] 张雯, 江文斌*, 吴开颖, 张杨, 蔡轩昊. 融合相位估计的声码器语音增强算法. 2025 National Conference on Man-Machine Speech Communication (NCMMSC 2025). Accepted. 2025.

[5] W. Jiang, K. Yu, and F. Wen, “Unsupervised Speech Enhancement Using Optimal Transport and Speech Presence Probability,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol.32, pp.4445 - 4455, 2024.

[6] W. Jiang and K. Yu, 'Speech Enhancement With Integration of Neural Homomorphic Synthesis and Spectral Masking,' IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 1758–1770, 2023.

[7] Y. Zhang, W. Jiang*, Q. Zhuo, and K. Yu, "Iterative Noisy-Target Approach: Speech Enhancement Without Clean Speech,' in Proc. National Conference on Man-Machine Speech Communication, 2023, pp. 256-264

[8] Q. Pan, W. Jiang*, Q. Zhuo, and K. Yu,  "A Framework Combining Separate and Joint Training for Neural Vocoder-Based Monaural Speech Enhancement," in Proc. National Conference on Man-Machine Speech Communication, 2023, pp. 189-202

[9] W. Jiang, F. Wen, Y. Zhang, and K. Yu, “UnSE: Unsupervised Speech Enhancement using Optimal Transport,” in Proc. Interspeech, 2023, pp. 4029–4033.

[10] W. Jiang, Z. Liu, K. Yu, and F. Wen, “Speech enhancement with neural homomorphic synthesis,” in Proc. ICASSP, 2022, pp. 376–380.

[11] W. Jiang, T. Liu, and K. Yu, “Efficient speech enhancement with neural homomorphic synthesis,” in Proc. Interspeech, 2022, pp. 986–990.

[12] W. Jiang, F. Wen, and P. Liu, “Robust Beamforming for Speech Recognition Using DNN-Based Time-Frequency Masks Estimation,” IEEE Access, vol. 6, pp. 52385–52392, 2018.

[13] W. Jiang, P. Liu, and F. Wen, “Speech Magnitude Spectrum Reconstruction from MFCCs Using Deep Neural Network,” Chinese Journal of Electronics, vol. 27, no. 2, pp. 393–398, Mar. 2018.

[14] W. Jiang, P. Liu, and F. Wen, “An improved vector quantization method using deep neural network,” AEU - International Journal of Electronics and Communications, vol. 72, pp. 178–183, Feb. 2017.

[15] W. Jiang, R. Ying, and P. Liu, “Noise identification for model-based speech enhancement,” in Proc. ICSP, 2014, pp. 478–483.

[16] W. Jiang, Y. Rendong, and L. Peilin, “Speech reconstruction for MFCC-based low bit-rate speech coding,” in Proc. ICMEW, 2014, pp. 1–6.

[17] W. Jiang, Y. Rendong, and L. Peilin, “A novel speech reconstruction algorithm for DSR back-end,” in International conference on audio, language and image processing, 2014, pp. 367–371.

学生工作：

大学生创新创业训练计划项目（第一指导老师）

1. 一种基于条件流匹配和声码器的语音增强算法，张杨，国家级，2025

2. 面向边缘设备的语音增强与识别一体化小模型，周禹含，省级，2025

3. 一种融合声码器与相位估计的语音增强算法，蔡轩昊，国家级，2024

4. 基于在线无监督学习的可扩展指令识别系统 ，李锦，国家级，2024

5. 基于神经同态合成的语音增强算法研究，魏婕，校级，2024

6. 一种基于倒谱-余弦域的双阶段实时语音增强算法，张杨，院级，2024

7. 面向边缘设备的语音增强与识别一体化小模型 ，周禹含，院级，2024

8. 基于神经坍塌的少样本类增量学习语音指令识别研究，詹蝉瑜，院级，2024