Wavelet-based speaker change detection in single channel speech data

Michael Wiesenegger, F. Pernkopf · Interspeech · 2009

Summary

A metric-based algorithm based on Discrete Wavelet Transform (DWT) features and principal component analysis (PCA) or linear discriminant analysis (LDA) are further used to reduce the dimensionality of the feature space and remove redundant information.

Published: 2009-01-01
Cited by: 0
References: 14
DOI: https://doi.org/10.21437/interspeech.2009-255
Semantic Scholar: https://api.semanticscholar.org/CorpusID:9707409

References

Information Theory: 1948-1998 - Guest EditorialSergio Verdú — 1998
Pattern Recognition and Machine LearningChris Bishop — 2006
Robust speaker diarization for meetingsXavier Anguera — 2006
Selection of acoustic features for speaker identificationM. R. Sambur — 1975
Speaker segmentation and clusteringMargarita Kotti, Vassiliki Moschou, Constantine Kotropoulos — 2008
DISTBIC: A speaker-based segmentation for audio data indexingPerrine Delacourt, C. Wellekens — 2000
Effective metric-based speaker segmentation in the frequency domainChristoph Boehm, Franz Pernkopf — 2009
Unsupervised speaker change detection using probabilistic pattern matchingA. Malegaonkar, A. Ariyaeeinia, P. Sivakumaran — 2006
A wavelet tour of signal processingStéphane Mallat — 1998
Strategies for automatic segmentation of audio dataThomas Kemp, Mikkel N. Schmidt, Martin Westphal — 2000
Speech and language technologies for audio indexing and retrievalJ. Makhoul, Francis Kubala, Timothy R. Leek — 2000
An overview of automatic speaker diarization systemsS.E. Tranter, D.A. Reynolds — 2006

Cited by

No citing papers recorded for this paper.

Related papers

No related papers recorded.