What Should We Learn? Cognitive Speech Coding

Speech coding is a field in which compression paradigms have not changed in the last 30 years. Speech signals are most commonly encoded with compression methods that have roots in linear predictive theory dating back to the early 1940s. The article Cognitive Speech Coding Examining the impact of cognitive speech processing on speech compression by Milos Cernak, et al, published in IEEE Signal Processing Magazine in May, 2018, bridges this influential theory with recent cognitive studies applicable in speech communication engineering. It reviews the mechanisms of speech perception that have led to perceptual speech coding. The focus is on human speech communication and machine learning and the application of cognitive speech processing in speech compression that presents a paradigm shift from perceptual (auditory) speech processing toward cognitive (auditory plus cortical) speech processing.

The authors' aim is to provide an overview of the impact of cognitive speech processing on speech compression and to discuss challenges faced in this interdisciplinary speech processing field. In this context, the traditional speech coding techniques as well as emerging approaches facilitated by deep-learning computational methods are covered. Key references are identified on fundamental teachings of psycholinguistics and speech neuroscience, and a valuable background for beginners and practitioners is given regarding the promising directions of incorporating principles of cognitive speech processing in speech compression.