中央研究院 資訊科學研究所

Human speech communication involves a series of complicated processes that require inter-disciplinary knowledge to understand and comprehend thoroughly. From signal processing points of view, we are interested in the unique properties of acoustic speech signals and how these properties contribute to effective communication from the speaker to the listener. Along the speech communication pathway, there are many imperfections that are related to disabilities of the speakers or listeners. Regardless of the causes of the disabilities, the acoustic speech signals transmitted from the speaker to the listener remain the most relevant physical observables, which can be analyzed, intervened or manipulated by signal processing techniques. In this talk, we will first review our previous work on Chinese-focused spoken language technologies and subsequently describe therecent efforts on applying speech processing techniques to address various problems related to speech and hearing disorders. Theseinclude signal enhancement for improving tone perception of hearing impaired listeners, pitch control for electro-larynx systems, objective assessment and analysis of disordered voice and aphasia speech.