Automatic Speech and Speaker Recognition Advanced Topics

Automatic Speech and Speaker Recognition Advanced Topics / edited by Chin-Hui Lee, Frank K. Soong, Kuldip K. Paliwal.

Research in the field of automatic speech and speaker recognition has made a number of significant advances in the last two decades, influenced by advances in signal processing, algorithms, architectures, and hardware. These advances include: the adoption of a statistical pattern recognition paradig...

Full description

Saved in:
Bibliographic Details
Corporate Author: SpringerLink (Online service)
Other Authors: Lee, Chin-Hui (Editor), Soong, Frank K. (Editor), Paliwal, Kuldip K. (Editor)
Format: eBook
Language:English
Published: New York, NY : Springer US : Imprint: Springer, 1996.
Edition:1st ed. 1996.
Series:The Springer International Series in Engineering and Computer Science, 355
Springer eBook Collection.
Subjects:
Signal processing.
Image processing.
Speech processing systems.
Electrical engineering.
Electronic resources (E-books)
Online Access:Click to view e-book
Holy Cross Note:Loaded electronically.
Electronic access restricted to members of the Holy Cross Community.
Table of Contents:
  • 1 An Overview of Automatic Speech Recognition
  • 2 An Overview of Speaker Recognition Technology
  • 3 Maximum Mutual Information Estimation of Hidden Markov Models
  • 4 Bayesian Adaptive Learning and Map Estimation of HMM
  • 5 Statistical and Discriminative Methods for Speech Recognition
  • 6 Context Dependent Vector Quantization for Speech Recognition
  • 7 Hidden Markov Network for Precise Acoustic Modeling
  • 8 From HMMS to Segment Models: Stochastic Modeling for CSR
  • 9 Voice Identification Using Nonparametric Density Matching
  • 10 The Use of Recurrent Networks in Continuous Speech Recognition
  • 11 Hybrid Connnectionist Models for Continuous Speech Recognition
  • 12 Automatic Generation of Detailed Pronunciation Lexicons
  • 13 Word Spotting — Extracting Partial Information from Continuous Utterances
  • 14 Spectral Dynamics for Speech Recognition under Adverse Conditions
  • 15 Signal Processing for Robust Speech Recognition
  • 16 Dynamic Programming Search: from Digit Strings to Large Vocabulary Word Graphs
  • 17 Fast Matching Techniques
  • 18 Multiple-Pass Search Strategies
  • 19 Issues in Practical Large Vocabulary Isolated Word Recognition: The IBM Tangora System
  • 20 From Sphinx-II to Whisper: Making Speech Recognition Usable.

Similar Items