Return to Research

Research themes

Explicit modeling of speech production and perception

Speech signals result from the movements of articulators. A good knowledge of their position with respect to sounds is essential to improve, on the one hand, articulatory speech synthesis, and on the other hand, the relevance of the diagnosis and of the associated feedback in computer assisted language learning. Production and perception processes are interrelated, so a better …

Statistical modeling of speech

Statistical approaches are common for speech processing, and their performance enables their use in actual applications. However, they still have limited capabilities in certain scenarios, e.g., when dealing with degraded (e.g., noisy, reverberated, or overlapped) speech. Source localization and separation The focus is set on source localization and separation methods using multiple microphones and/or models of speech and …

Uncertainty estimation and exploitation in speech processing

Speech signals are highly variable and often degraded by noise or overlapping speech. The output of speech enhancement or source separation methods typically differs from the true “clean” speech signal, and estimation errors must be taken into account in further processing. We also aim to estimate the reliability of phonetic segment boundaries and prosodic parameters for which no such …