top of page
About the Workshop

Speech Processing is a scientific discipline as well as a technology frontier with immense applications. The treatment of speech signal processing requires an initial grounding in digital signal processing. On one side of the spectrum is the speech and language sciences, such as linguistics, phonetics and psychoacoustics, and on the other side are the signal processing theory and pattern recognition and artificial intelligence. This leads to enhanced human-human & human-machine communication systems, such as speech and audio coding, automatic speech and speaker recognition, speech synthesis, speech enhancement etc. Pursuit of such wide ranging research and development demands a broad base of fundamental knowledge, as well as the mastering of clever algorithms and techniques.

 

The program is open to the UG and PG students, PhD research scholars, faculty members of E.E.E., E.C.E, C.S.E., I.T., M.C.A. departments who choose speech recognition for their research work.

The Objective of the Workshop is to:

​

  • Exchange ideas, methodologies and techniques of how to work towards the implementation of Continuous speech recognition systems;

  • Review existing Automatic speech recognition(ASR) systems;

  • Be informed of the benefits and limitations of the existing ASR systems;

  • Identify and recommend appropriate actions required for further research in this field.

The Scope of Workshop:

​

Today, voice and natural language processing are at the forefront of any human machine interaction environment.

the goal of speech technology is to make speaking to devices around you (home, in car), devices you wear (watch), devices with you (phone, tablet) ubiquitous and seamless. it covers the various areas of research like:

  • Speech and audio coding;

  • Automatic speech and speaker recognition;

  • Speech synthesis;

  • Language modeling;

  • Speech enhancement etc.

​

The Outcomes of the Workshop will be:

​

  • Increased understanding of Automatic Speech Recognition working ;

  • Able to work on open source speech recognition tools like HTK 3.4.1 and sphinx;

  • The confidence to keep going on research of speech recognition

  • Able to find out the future research direction in this field

Hands-on Session Details (ASR Tools)

Program

Schedule

1.HTK 3.4.1:
The Hidden Markov Model Toolkit (HTK 3.4.1) is a speech recognition toolkit developed by Cambridge University(CUED). The tools provide sophisticated facilities for speech analysis, HMM training, testing and result analysis.
visit:- http://htk.eng.cam.ac.uk/


2.CMU Sphinx:

CMU Sphinx describe a group of speech recognition systems developed at CMU. These include a series of speech recognizers (Sphinx 2-4) and an acoustic model trainer (SphinxTrain).
Visit:- https://cmusphinx.github.io/

​


Day First:
1.Introduction of Linguistics/  phonology                                                  09:30-11:30 AM
2. Introduction to ASR using HTK 1                                                            11:30-2:00 PM
3.Hands on session on HTK- Phonebased acoustic modeling                 03:00-5:00 PM
 

Day Second:
1.Introduction to Sphinx                                                                                09:00-11:00 AM
2. Hands on session on Sphinx                                                                     11:30-01:30  PM
3. Introduction to DNN in Speech Recognition                                         02:30-05:00 PM

​

Resource Persons

Mr. Ankit Kumar

Qualification:-

M.Tech (C.S.E.) ,N.I.T. Kurukshetra

Ph.D* (CSE) ,N.I.T. Kurukshetra

​

Experience:- 7 Years

​

Research Interest:- Speech Recognition, Natural Language Processing, Artificial Intelligence

 

Biographical Narrative:-

Mr. Ankit Kumar is currently working as an assistant professor in A.B.E.S. Engineering College, Ghaziabad. He completed his M.Tech from National Institute of Technology, Kurukshetra. Currentlyhe is pursuing his Ph.D from National Institute of Technology, Kurukshetra in Hindi Speech Recognition. his area of great interest is Large vocabulary robust Hindi Speech Recognition. He has authored and co-authored of various publication in major referred scientific conferences and journals.

​

Mr. Mohit Dua

Qualification:-

M.Tech (C.S.E.) ,N.I.T. Kurukshetra

Ph.D* (CSE) ,N.I.T. Kurukshetra

​

Experience:- 12 Years

​

Research Interest:- Speech Processing, Pattern Recognition, Image Processing, Natural Language Processing, Soft Computing, Cryptography

 

Biographical Narrative:-

Mr. Mohit Dua is working as an assistant professor in National Institute of technology, Kurukshetra. 

he has more than 12 years of teaching experience. He has authored and co-authored of various publication in major referred scientific conferences and journals.

bottom of page