An HMM-based subband processing approach to speaker identification

DOI10.1007/3-540-45344-X_24MaRDI QIDQ2776956zbMATH OpenFDO

Authors J. E. Higgins, Robert I. Damper

Publication date 7 March 2002

Published in Lecture Notes in Computer Science (Search for Journal in Brave)

Full work available at URL http://link.springer.de/link/service/series/0558/bibs/2091/20910169, https://eprints.soton.ac.uk/255928/1/paper.pdf

Mathematics Subject Classification ID

Pattern recognition, speech recognition (68T10) Computing methodologies and applications (68U99)

Recommendations

• Improved data modeling for text-dependent speaker recognition using sub-band processing
• Application of multiple classifier techniques to subband speaker identification with an HMM/ANN system
• Subband architecture for automatic speaker recognition.
• Union: A new approach for combining sub-band observations for noisy speech recognition
• Speaker recognition

Cited in

(9)

• A study of HMM-based bandwidth extension of speech signals
• Subband architecture for automatic speaker recognition.
• Improved data modeling for text-dependent speaker recognition using sub-band processing
• Speaker identification in the shouted environment using suprasegmental hidden Markov models
• Improving speaker identification performance under the shouted talking condition using the second-order hidden Markov models
• Application of multiple classifier techniques to subband speaker identification with an HMM/ANN system
• Bandwidth-adjusted LPC analysis for robust speech recognition
• Union: A new approach for combining sub-band observations for noisy speech recognition
• Application of acoustic discriminative training in an ergodic HMM for speaker identification

This page was built for publication: An HMM-based subband processing approach to speaker identification

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2776956)