Samvaad-Talk by Prof. RamSubramanian (November 26, 2018)

Title: “Some paradigms in automatic speech recognition"
Abstract: This talk will focus on automatic speech recognition (ASR), highlighting some of the recent / ongoing work we are pursuing. Specifically the talk will dwell on 7 major directions of research constituting current Masters and Doctoral students’ work: i) multi-lingual ASR using predicted articulatory features, ii) semi-supervised (or self-training) and active-learning scenarios for acoustic model refinement, iii) attention based models for ASR, iv) 0-speech (zero-speech) paradigms, v) acoustic sub-word unit based ASR, vi) co-articulation modelling for ASR and vii) associative memory formulations based on Hopfield and Boltzmann networks. Most of these paradigms are defined/re-defined within current machine-learning / deep-learning frameworks, combining the complementary strengths of conventional speech-specific knowledge and intensive data-driven machine-learning trends, a kind of amalgamation repeatedly emphasized as the optimal approach for developing machine-recognition of speech, capable of integrating and nearing human-speech recognition performances, but which has usually lead to divisive research positionings in every cycle of new and emerging paradigms.

Speaker Biography: Ramasubramanian obtained his B.S. degree from the University of Madras in 1981, B.E. degree from Indian Institute of Science, Bangalore in 1984 and the Ph.D. degree from Tata Institute of Fundamental Research (TIFR), Bombay in 1992. He has been engaged in research in speech processing and related areas for nearly 3 decades. Prior to the present position, he was Professor at PES Institute of Technology, South Campus, Bangalore, 2013-2017. He has worked in various institutions and universities, such as TIFR, Bombay (1984-99) as Research Scholar, Fellow and Reader; University of Valencia, Spain as Visiting Scientist (1991-92); Advanced Telecommunications Research (ATR) Laboratories, Kyoto, Japan as Invited Researcher (1996-97); Indian Institute of Science (IISc), Bangalore as Research Associate (2000-04) and Siemens Corporate Research & Technology (2005-13) as Senior Member Technical Staff and as Head of the speech research group “Professional Speech Processing – India” (2006-09). He has over 65 research publications in these areas in peer reviewed international journals and conferences. He is also author of a Springer monograph on “Ultra low bit-rate speech coding”, Springer NY, 2015.