This book presents recent advances in nonlinear
speech processing beyond nonlinear techniques. It shows that it exploits
heuristic and psychological models of human interaction in order to succeed in
the implementations of socially believable VUIs and applications for human
health and psychological support. The book takes into account the
multifunctional role of speech and what is "outside of the box" (see Bjoern
Schuller's foreword). To this aim, the book is organized in 6 sections, each
collecting a small number of short chapters reporting advances "inside" and
"outside" themes related to nonlinear speech research. The themes emphasize
theoretical and practical issues for modelling socially believable speech
interfaces, ranging from efforts to capture the nature of sound changes in
linguistic contexts and the timing nature of speech; labors to identify and
detect speech features that help in the diagnosis of psychological and neuronal
disease, attempts to improve the effectiveness and performance of Voice User
Interfaces, new front-end algorithms for the coding/decoding of effective and
computationally efficient acoustic and linguistic speech representations, as
well as investigations capturing the social nature of speech in signaling
personality traits, emotions and improving human machine interactions.