Summer School On Speech Signal Processing,Da-Iict, Gandhinagar
8th - 12th July 2017
Mrs. Sanghamitra V. Arora, Head of Department of Applied Sciences & Humanities, Dronacharya College of Engineering, Gurgaon attended the “S4P-Summer School on Speech Signal Processing” organized at Speech Research Lab, Dhirubhai Ambani Institute of Information and Communication Technology (DA-IICT), Gandhinagar from 8th - 12th July 2017. The total participation was of 106 members from presitigious academic institutes and research labs of the country and abroad.
The summer school provided an opportunities to researchers and professionals to enhance their fundamentals and get exposed to cutting-edge research areas in the field of speech signal processing on a global platform. The school constitutes of a theme topic and tutorials surrounding it.
Speaker recognition (voice biometrics) has gained a lot of interests in a large number of e-commerce and forensics related applications such as automatic access through voice profile, filtering of telephone calls. Discussion related to the development of speaker recognition systems which are robust to noise, channel variability, intrinsic variability (due to speakers, health issues, stress, etc.) was the major goal of S4P 2017. In addition, the recent research work related to the development of countermeasures against spoofing and tampering attacks were also covered in this summer school. Language Identification (LID) with the major focus on dialect and accent identification was also explored.
All the sessions were conducted by expert persons from reputed Universities and research labs.
Keynote speaker for the summer school were Haizhou Li Professor, National University of Singapore (NUS), Singapore., John H. L. Hansen Professor of Electrical Engineering, Erik Jonsson School of Engineering and Computer Science, UT-Dallas, USA. Douglas A. Reynolds Human Language Technology Group, Lincoln Laboratory, Massachusetts Institute of Technology (MIT), USA. Kong Aik Lee Scientist, Human Language Technology Department, Institute for Infocomm Research (I2R), A*STAR, Singapore. B. Yegnanarayana Professor Emeritus, BITS-Pilani, Hyderabad Hema A Murthy Professor, Indian Institute of Technology (IIT), Madras. S. R. M. Prasanna Professor, Indian Institute of Technology (IIT), Guwahati.
Apart from the above list there were experts from C-DAC, IIIT - Hyderabad and Bangalore Campus and Microsoft Research, Bangalore.
Day 1: 8th July 2017
First day session began with the lecture of B. Yegnanarayana. He explained Extracting Dynamic Characteristics of Speech Production. Next lecture was by Douglas A. Reynolds and he gave introduction to Speaker Recognition. He explained Speaker recognition is the identification of a person from characteristics of voices. He told there is a difference between speaker recognition (recognizing who is speaking) and speech recognition (recognizing what is being said).Continuing the lecture S. R. M. Prasanna explained Speaker Verification using Limited Data Conditions.
Day 2: 9th July 2017
Second day session began with the lecture of Prof. Haizhou Li. He discussed Speech to Singing Synthesis. Next Kong Aik Lee conducted the lecture on Factor Analysis for Speaker and Language Recognition. Prof. Hema A Murthy discussed Feature Switching for Speaker Verification and Spoof Detection. V. Ram Subraminium explained Speaker Profiling and Micro-articulometry.
Day 3: 10th July 2017
Third day session began with the lecture of John H. L. Hansen. He explained Speaker and Environment Variability: Impact on Speech/Speaker Systems. Next Haizhou Li conduted the lecture on Voice Conversion and Spoofing Countermeasure for Speaker Verification. Later Development of Text-to-Speech (TTS) Synthesis for Spoofing was discussed by Sunayana Sitaram. Continuing the lecture Leena Mary explained Prosodic Features for Speaker and Language Recognition.
Day 4: 11th July 2017
John H. L. Hansen began the fourth day lecture with the discussion on Diarization for Naturalistic Data: Examples from the Classroom, Earth and to the Moon. Kong Aik Lee conducted the next lecture on SIDEKIT – Python Toolkit for Speaker and Language Recognition. Last session of the day was conducetd by Tanvina V. Patel. He explained Countermeasures for Spoofed Speech Detection System.
Day 5: 12th July 2017
Third day session began with the lecture of John H. L. Hansen. He explained Challenges in Speaker Recognition/Verification: Lombard Effect, Vocal Effort, and Distant Speech.Next Douglas A. Reynolds discussed DNNs in Speaker and Language Recognition. S. Gangashetty explained Countermeasures for Replay Speech Detection. Last lecture was conducted by Hemant A. Patil (Organiser) , he discussed Person Recognition using Humming.
The participants of the summer school were highly benefited by invited talks from eminent speech processing researchers from academia, industry and research laboratories from India and abroad. Attending such informative and interactive programs with the researchers serves as an eye opener as to where the world is heading.