报告题目：GAN-based Speech Enhancement
报告时间：2023年7月3日（周一）15:45
报告地点：信息科技大楼A101-102会议室
主持人：张国庆副教授
Dr. Ruili Wang, Fellow of Engineering of New Zealand, is currently the Professor of Artificial Intelligence and Chair of Research in the School of Natural and Computational Sciences, Massey University, Auckland, New Zealand, where he is the Director of the Centre of Language and Speech Processing. His current research interests include video processing, speech processing, and natural language processing. He serves as a member and an Associate Editor of the editorial boards for international journals, including the journals of IEEE Transactions on Emerging Topics in Computational Intelligence, Neurocomputing, Knowledge and Information Systems, and Applied Soft Computing.
报告（内容）摘要：
Speech enhancement, aiming at improving the intelligibility and overall perceptual quality of a contaminated speech signal, is an effective way to improve speech communications, which has been widely used in mobile communication, hearing aids devices, voice assistants, etc. Recently, we proposed several generative adversarial network (GAN) -based speech enhancement methods. The seminar will present two of them. The first one is an adversarial latent representation learning for latent space exploration. Based on adversarial feature learning, this method employs an extra encoder to learn inverse mapping from the generated data distribution to the latent space. In other words, the encoder establishes an inner connection between the generator and the latent space. Secondly, we propose an adversarial multi-task learning with inverse mappings methods for effective speech representation. This method focuses on enhancing the generator’s capability of speech information capture and representation learning. To implement this method, two extra networks are developed to learn the inverse mappings from the generated distribution to the input data domains.
欢迎广大师生踊跃参加！
计算机学院、网络空间安全学院
2023年7月3日
