Speech and language processing for mental health research and care

Speech signal processing is being increasingly explored in health domains given both its centrality as a behavioral cue and the promise of robust, automated analysis of data at scale. We discuss general issues in health-related speech research. We further highlight two health applications we have undertaken: addiction counseling and autism spectrum disorder. Methods range from deep supervised learning to knowledge-based signal processing of highly subjective constructs of psychological states and traits. A unique aspect of the research has been to model both health care provider and patient behaviors jointly in clinical encounters, wherein any individual behavior cannot be considered in isolation given the inherent mutual influence.