081002-信号与信息处理

语音信号处理，人工智能，水声目标识别

2014-09--2019-06   中国科学院声学研究所   工学博士
2010-09--2014-06   西安电子科技大学   工学学士

   

2023-11~现在, 中国科学院声学研究所, 副研究员
2021-10~2023-11,中国科学院声学研究所, 助理研究员
2019-07~2021-10,中国科学院声学研究所, 博士后

   

（1） 智能语音能力平台关键技术及其在智能客服行业应用, 二等奖, 省级, 2019

（ 1 ） 一种语音检测模型训练和语音检测方法, 发明专利, 2023, 第 1 作者, 专利号: CN116597818A

（ 2 ） 一种融合分布对齐和对抗学习的无监督跨域声纹识别方法, 发明专利, 2021, 第 3 作者, 专利号: CN112820301A

（ 3 ） 一种融合分布对齐和对抗学习的无监督跨域声纹识别方法, 2023, 第 3 作者, 专利号: CN112820301B

（ 4 ） 全连接多尺度的残差网络及其进行声纹识别的方法, 专利授权, 2021, 第 1 作者, 专利号: CN111833886B

（ 5 ） 一种基于空洞卷积神经网络的端到端语种识别分类方法, 发明专利, 2021, 第 3 作者, 专利号: CN113539238A

（ 6 ） 一种说话人分段聚类方法及装置, 专利授权, 2019, 第 6 作者, 专利号: CN109859742A

（ 7 ） 一种针对声纹识别的语音降噪方法及装置, 专利授权, 2019, 第 2 作者, 专利号: CN110070874A

   

[1] Wang, Yunhao, Nie, Weihang, Liu, Ziyuan, Xu, Ji, Wang, Wenchao. Enhancing feature-aided data association tracking in passive sonar arrays: An advanced Siamese network approach. JOURNAL OF THE ACOUSTICAL SOCIETY OF AMERICA[J]. 2025, 第 5 作者  通讯作者  157(2): 681-698, http://dx.doi.org/10.1121/10.0035577.
[2] Fang, Haotian, Xie, Yuan, Ren, Jiawei, Wang, Wenchao, Xu, Ji. A momentum-based adversarial training approach for generalization in underwater acoustic target recognition: An individual-vessel perspective. The Journal of the Acoustical Society of America[J]. 2025, 第 4 作者157(5): 3508-3523, https://pubs.aip.org/asa/jasa/article/157/5/3508/3346218/A-momentum-based-adversarial-training-approach-for.
[3] zhenduo zhao, zhuo li, xueshuai zhang, wenchao wang, pengyuan zhang. Prototype Division for Self-Supervised Speaker Verification. IEEE SIGNAL PROCESSING LETTERS[J]. 2024, 第 4 作者  通讯作者  
[4] yuxiang zhang, zhuo li, jingze lu, wenchao wang, Zhang, Pengyuan. Synthetic Speech Detection Based on Temporal Consistency and Distribution of Speaker Features. IEEE SIGNAL PROCESSING LETTERS[J]. 2024, 第 4 作者  通讯作者  null(null): 
[5] yuxiang zhang, zhuo li, jingze lu, hua hua, wenchao wang, pengyuan zhang. The Impact of Silence on Speech Anti-Spoofing. IEEE/ACM Transactions on Audio, Speech and Language Processing (TASLP)[J]. 2023, 第 5 作者  通讯作者  
[6] zhenduo zhao, zhuo li, wenchao wang, pengyuan zhang. PCF: ECAPA-TDNN with progressive channel fusion for speaker verification. ICASSP2023. 2023, 第 3 作者
[7] Ji Xu, Yuan Xie, Wenchao Wang. Underwater. OCEAN ENGINEERING[J]. 2023, 第 3 作者
[8] Li, Zhuo, Xiao, Runqiu, Chen, Hangting, Zhao, Zhenduo, Wang, Wenchao, Zhang, Pengyuan. How to make embeddings suitable for PLDA. COMPUTER SPEECH AND LANGUAGE[J]. 2023, 第 5 作者  通讯作者  81: http://dx.doi.org/10.1016/j.csl.2023.101523.
[9] Ji Xu, Yuan Xie, Wenchao Wang. Underwater Acoustic Target Recognition based on Smoothness-inducing Regularization and Spectrogram-based Data Augmentation. Ocean Engineering[J]. 2023, 第 3 作者
[10] yuxiang zhang, wenchao wang, pengyuan zhang. The effect of silence and dual-band fusion in anti-spoofing system. Interspeech. 2021, 第 2 作者
[11] Runqiu Xiao, xiaoxiao miao, wenchao wang, Pengyuan Zhang. Adaptive Margin Circle Loss for Speaker Verification. Interspeech. 2021, 第 3 作者  通讯作者  http://arxiv.org/abs/2106.08004.
[12] Miao, Xiaoxiao, McLoughlin, Ian, Wang, Wenchao, Zhang, Pengyuan. D-MONA: A dilated mixed-order non-local attention network for speaker and language recognition. NEURAL NETWORKS[J]. 2021, 第 3 作者139: 201-211, http://dx.doi.org/10.1016/j.neunet.2021.03.014.
[13] Li, Chen, Liu, Ziyuan, Ren, Jiawei, Wang, Wenchao, Xu, Ji. A Feature Optimization Approach Based on Inter-Class and Intra-Class Distance for Ship Type Classification. SENSORS[J]. 2020, 第 4 作者20(18): https://doaj.org/article/7529bf77fd2b44fc8b3e4a27f0b6003f.
[14] Wang, Wenchao, Zhang, Yike, Xu, Ji, Yan, Yonghong, IEEE. MULTIPLE TEMPORAL SCALES BASED SPEAKER EMBEDDINGS LEARNING FOR TEXT-DEPENDENT SPEAKER RECOGNITION. 2019 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING (ICASSP). 2019, 第 1 作者  通讯作者  6311-6315, http://dx.doi.org/10.1109/icassp.2019.8682799.
[15] WANG Wenchao, XU Ji, YAN Yonghong. Identity Vector Extraction Using Shared Mixture of PLDA for Short-Time Speaker Recognition. 电子学报(英文)[J]. 2019, 第 1 作者  通讯作者  357-363, http://lib.cqvip.com/Qikan/Article/Detail?id=69689088504849574850485048.
[16] Wang Wenchao, Xu Ji, Yan Yonghong. Identity Vector Extraction Using Shared Mixture of PLDA for Short-Time Speaker Recognition. CHINESE JOURNAL OF ELECTRONICS[J]. 2019, 第 1 作者  通讯作者  28(2): 357-363, https://www.doi.org/10.1049/cje.2018.06.005.

   

（ 1 ） 面向特定说话人的伪造语音检测技术, 负责人, 国家任务, 2023-01--2025-12