We consider the problem of blind multi-channel speech dereverberation without the knowledge of room acoustics. The dereverberated speech component is estimated by subtracting the undesired component, estimated using multi-channel linear prediction (MCLP), from the reference microphone signal. In this paper we present a framework for MCLP-based speech dereverberation by exploiting sparsity in th...

We present a novel method for recovering articulator movements from speech acoustics based on a constrained form [9] of a hidden Markov model. The model attempts to explain sequences of high dimensional data using smooth and slow trajectories in a latent variable space. The key insight is that this continuity constraint when applied to speech helps to solve the \ill-posed" problem of acoustic t...

We have developed a data-driven conceptual framework that links two areas of science: the source-filter model of acoustics and cortical sensory processing streams. The source-filter model describes the mechanics behind speech production: the identity of the speaker is carried largely in the vocal cord source and the message is shaped by the ever-changing filters of the vocal tract. Sensory proc...

Individuals with bipolar disorder typically exhibit changes in the acoustics of their speech. Mobile health systems seek to model these changes to automatically detect and correctly identify current states in an individual and to ultimately predict impending mood episodes. We have developed a program, PRIORI (Predicting Individual Outcomes for Rapid Intervention), that analyzes acoustics of spe...

After differentiating attitudes from emotions, the present work investigates prosodic manifestations and perceptual attributes of Mandarin utterances conveying various attitudes. A speech corpus was designed to incorporate five classes of attitudes: friendly/hostile, polite/rude, serious/joking, praising/blaming, and confident/uncertain. Perceptual experiment reveals two different patterns betw...

Categorical effects are found across speech sound categories, with the degree of these effects ranging from extremely strong categorical perception in consonants to nearly continuous perception in vowels. We show that both strong and weak categorical effects can be captured by a unified model. We treat speech perception as a statistical inference problem, assuming that listeners use their knowl...

A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification Victor Poblete a,b, Felipe Espic a,1, Simon King c, Richard M. Stern d, Fernando Huenupán e, Josué Fredes a, Nestor Becerra Yoma a,∗ a Speech Processing and Transmission Laboratory, Electrical Engineering Department, University of Chile, Santiago, Chile b Institute of Aco...