Automatic speech assessment - Health Tech Lunch - Dr. Mathew Magimai Doss

Health Tech Lunch - 13.02.2018, 12h00 - Sierre, Techno-Pôle (Room Atlas)

Presentation by Dr. Mathew Magimai Doss (IDIAP)

Title : Automatic speech assessment: combining knowledge and data

Abstract : Speech assessment is crucial part of development of speech technologies such as speech transmission systems, text-to-speech systems, language learning systems, speech therapy systems to name a few. Assessment of aspects such as speech intelligibility, speech quality is typically carried out through subjective tests, which can be time consuming and expensive. Furthermore, it may not be always be reproducible. In this talk, I will present two different automatic speech assessment frameworks that we are pursuing: (a) linguistic prior knowledge-driven and (b) end-to-end data-driven that uses minimal prior knowledge. Through experimental studies on intelligibility assessment, assessment of accentedness of non-native speech and detection of presentation attacks, I will demonstrate the potential of these frameworks in combining knowledge and data for effective speech assessment.

Bio : Dr. Mathew Magimai Doss received the Bachelor  of Engineering  (B.E.)  in  Instrumentation and  Control Engineering  from the  University  of Madras, India in 1996; the Master of Science (M.S.) by  Research  in  Computer  Science  and Engineering from  the  Indian Institute  of  Technology,  Madras, India in 1999; the PreDoctoral diploma and the Ph.D. from the Ecole Polytechnique Fédérale de Lausanne (EPFL), Switzerland in 2000 and 2005,  respectively.  He was  a postdoctoral  fellow  at the International Computer Science Institute (ICSI), Berkeley, USA  from  April  2006  till  March  2007.  Since April  2007, he  has been  working  as  a  Researcher  at  the  Idiap Research  Institute,  Martigny, Switzerland.  He  is  also  a lecturer at  EPFL,  where  he  teaches  courses  on speech and audio processing. He is a Senior Area Editor of the IEEE Signal Processing Letters. His main  research  interest  lies  in signal  processing, statistical pattern  recognition, artificial  neural  networks  and  computational linguistics with applications to speech and audio processing and multimodal signal processing.

​Registration : https://doodle.com/poll/ddvy66a3in62yhdy