Tackling the Cocktail Party Problem for Hearing Devices: Solutions, Challenges and Opportunities

Abstract. The cocktail party problem has remained to be one of the most challenging problems for hearing devices even after decades of extensive research. In this talk, we will introduce and discuss our research on the multi-microphone speech enhancement with an emphasis on robust and practical real-time algorithms for hearing devices. We will first present our research on multiple-microphone speech enhancement using a microphone array alone. Secondly, we will present our latest research on the multimodal speech enhancement using both brain signals (i.e. EEG) and microphone signals in a single joint-optimization framework. In both cases, we will use objective and subjective evaluation to demonstrate the algorithms’ effectiveness. Finally, we will discuss the challenges and opportunities in deploying these algorithms in the real-world.

Biography. 

Tao Zhang received his B.S. degree in physics from Nanjing University, Nanjing, China in 1986, M.S. degree in electrical engineering from Peking University, Beijing, China in 1989, and Ph.D. degree in speech and hearing science from the Ohio-State University, Columbus, OH, USA in 1995. He joined the Advanced Research Department at Starkey Laboratories, Inc. as in 2001 and since 2014, he has been Director of the Signal Processing Research department at Starkey Hearing Technologies. He is a senior member of IEEE and the Signal Processing Society and the Engineering in Medicine and Biology Society. He is an IEEE SPS Distinguished Industry Speaker, the Chair of IEEE Twin-cities Signal Processing and Communication Chapter and a Member of IEEE ComSoc North America Region Board. He serves on the IEEE AASP Technical Committee and the IEEE Industrial Relationships Committee.