王帅
职务/职称
深圳市大数据研究院语音语义实验室研究科学家
研究方向
智能语音处理，说话人识别，语音增强，语音合成与转换
电子邮箱
wangshuai@sribd.cn
教育背景
上海交通大学 博士
西北工业大学 学士
主要成果/荣誉
VoxCeleb Speaker Recognition Challenge 2019: 全部两个赛道冠军
DIHARD Speaker Diarization Challenge 2019: 全部四个赛道冠军
IEEE Ganesh N. Ramaswamy Memorial Award (2018)
个人介绍
王帅博士，目前是深圳市大数据研究院语音语义实验室研究科学家，在此之前，他曾任腾讯光子工作室高级研究员，主要从事服务于腾讯游戏的语音合成、语音转换、音频检索等方面的研究与落地工作。2020年博士毕业于上海交通大学计算机科学与工程系，博士期间从事说话人识别相关研究，发表多篇语音领域顶级会议及期刊，参与搭建的说话人识别、日志系统在国际权威比赛中两次夺冠，系统还支持了类似oppo手机语音助手的工业应用。更多信息可参见其个人主页 wsstriving.github.io
代表性论文
• Shuai Wang, Yexin Yang, Zhanghao Wu, Yanmin Qian and Kai Yu. Data Augmentation using Deep Generative Models for Embedding based Speaker Verification. IEEE/ACM Transactions on Audio Speech and Language Processing 2020
• Shuai Wang, Zili Huang, Yanmin Qian and Kai Yu. Discriminative Neural Embedding Learning for Short-Duration Text-Independent Speaker Verification. IEEE/ACM Transactions on Audio Speech and Language Processing 2019
• Heinrich Dinkel, Shuai Wang, Xuenan Xu, Mengyue Wu, Kai Yu. Voice activity detection in the wild: A data-driven approach using teacher-student training. IEEE/ACM Transactions on Audio Speech and Language Processing 2021
• Yanmin Qian, Zhengyang Chen, Shuai Wang. Audio-Visual Deep Neural Network for Robust Person Verification. IEEE/ACM Transactions on Audio Speech and Language Processing 2021
• Hongji Wang, Chengdong Liang, Shuai Wang*, Zhengyang Chen, Binbin Zhang, Xu Xiang, Yanlei Deng, Yanmin Qian. Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit. ICASSP 2023 (*通讯作者)
• Aiwen Deng, Shuai Wang*, Wenxiong Kang, Feiqi Deng. On the Importance of Different Frequency Bins for Speaker Verification. ICASSP 2022 (*通讯作者)
• Shuai Wang, Yexin Yang, Yanmin Qian, Kai Yu. Revisiting the Statistics Pooling Layer in Deep Speaker Embedding Learning. ISCSLP 2021
• Shuai Wang*, Yexin Yang*, Xun Gong, Yanmin Qian and Kai Yu. Text adaptation for speaker verification with speaker-text factorized embeddings. (*共同一作) ICASSP 2020
• Shuai Wang, Johan Rohdin, Oldřich Plchot, Lukáš Burget, Kai Yu and Jan Černocký. Investigation of SpecAugment for deep speaker embedding learning. ICASSP 2020
• Shuai Wang, Johan Rohdin, Lukáš Burget, Oldřich Plchot, Yanmin Qian, Kai Yu and Jan Černocký. On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction. Interspeech 2019.
• Hossein Zeinali, Shuai Wang, Anna Silnova, Pavel Matějka, Oldřich Plchot. BUT System Description to VoxCeleb Speaker Recognition Challenge 2019
• Shuai Wang, Yexin Yang, Tianzhe Wang, Yanmin Qian and Kai Yu. Knowledge Distillation for Small Foot-print Deep Speaker Embedding. ICASSP 2019.
• Shuai Wang*, Zili Huang* and Kai Yu. Angular Softmax for Short-Duration Text-independent Speaker Verification. (* 共同一作) Interspeech 2018
• Shuai Wang, Yanmin Qian and Kai Yu. Focal KL-Divergence based Dilated Convolutional Neural Networks for Cochannel Speaker Identification. ICASSP 2018 (IEEE Ganesh N. Ramaswamy Memorial Award)
• Shuai Wang, Yanmin Qian and Kai Yu. What Does the Speaker Embedding Encode? Interspeech 2017
