Login
Course Information
Identification

CS 753: Automatic Speech Recognintion
 
Description

Introduction to the statistical approach for automatic speech recognition (ASR)

• Weighted Finite State Transducers and their Application to ASR

• Acoustic Signal Processing for ASR

• Acoustic models: Hidden Markov Models, Gaussian Mixture Models, Baum-Welch Maximum Likelihood

Estimation

• Discriminative Training of Acoustic Models: Maximum Mutual Information, Minimum Word/Phone Error Criteria

• Acoustic models continued: Neural network models (Deep feed-forward neural networks, convolutional neural

networks and recurrent neural networks)

• Pronunciation models: Pronunciation dictionaries, grapheme-to-phoneme models, feature-based models

• N-gram language models: estimation, smoothing

• ASR decoding problem: search algorithms, Viterbi estimation, finite-state transducer optimizations

Programming assignments for a few of the above listed topics, along with a final research project, will be part of the

curriculum.
 
References

Speech and Language Processing, Daniel Jurafsky and James H. Martin, 2nd edition, Prentice-Hall, 2008.

(Textbook)

• A Tutorial on Hidden Markov Models and Selected Applications in Speech Recognition, Lawrence R. Rabiner,

Proceedings of the IEEE, 77(2):257—286, 1989.

• Weighted Finite-state Transducers in Speech Recognition, Mehryar Mohri, Fernando Pereira and Michael Riley,

Computer Speech and Language, 16.1:69—88, 2002.

• The Application of Hidden Markov Models in Speech Recognition, Mark Gales and Steve Young, Foundations and

Trends in Signal Processing, 1(3):195—304, 2008.

• Deep Neural Networks for Acoustic Modeling in Speech Recognition, Geoffrey Hinton, Li Deng, Dong Yu,

George E. Dahl, Abdel-rahman Mohamed, Navdeep Jaitly, Andrew Senior, Vincent Vanhoucke, Patrick Nguyen,

Tara N. Sainath, and Brian Kingsbury, IEEE Signal Processing Magazine, 6:82—97, 2012.

• Automatic Speech Recognition – A Deep Learning Approach, Dong Yu and Li Deng, Springer, 2014.
 
Home Page

https://www.cse.iitb.ac.in/~pjyothi/cs753/
 
Prerequisites

CS725 or Desired background for taking the course
 
Other Details

Duration : Full Semester Total Credit : 6
Type : Theory
 
Autumn Semester 2019-20

Status : Offered Instructor : Prof. Preethi Jyothi
 
Spring Semester 2019-20

Status : Not Offered Instructor : ---




Last Modified Date: 15-Jul-2013

Webmail

Username:
Password:
Faculty CSE IT
Forgot Password
    [+] Sitemap     Feedback