Time-aligned SVD analysis for speaker identification

Patrick Clemins; Heather Ewalt; Michael Johnson

Time-aligned SVD analysis for speaker identification

Patrick Clemins, Heather Ewalt, Michael Johnson

Electrical and Computer Engineering

Producción científica: Conference article › revisión exhaustiva

3 Citas (Scopus)

Resumen

This paper presents a time-aligned singular value decomposition (SVD) analysis for speaker identification. SVD analysis has been used for fast spectral matching based on a global representation of an entire utterance. We incorporate temporal normalization directly into the decomposition by using a dynamic time warping (DTW) path to time-align the rows of the feature matrix prior to SVD analysis. Speaker identification results using the TI-46 database indicates that the time-aligned SVD significantly improves accuracy for most threshold choices.

Idioma original	English
Páginas (desde-hasta)	IV/4160
Publicación	ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volumen	4
Estado	Published - 2002
Evento	2002 IEEE International Conference on Acoustic, Speech, and Signal Processing - Orlando, FL, United States Duración: may 13 2002 → may 17 2002

ASJC Scopus subject areas

Software
Signal Processing
Electrical and Electronic Engineering

Otros archivos y enlaces

Citar esto

@article{ba8c8238466b4ebfaf1d7859626e4d80,

title = "Time-aligned SVD analysis for speaker identification",

abstract = "This paper presents a time-aligned singular value decomposition (SVD) analysis for speaker identification. SVD analysis has been used for fast spectral matching based on a global representation of an entire utterance. We incorporate temporal normalization directly into the decomposition by using a dynamic time warping (DTW) path to time-align the rows of the feature matrix prior to SVD analysis. Speaker identification results using the TI-46 database indicates that the time-aligned SVD significantly improves accuracy for most threshold choices.",

author = "Patrick Clemins and Heather Ewalt and Michael Johnson",

year = "2002",

language = "English",

volume = "4",

pages = "IV/4160",

note = "2002 IEEE International Conference on Acoustic, Speech, and Signal Processing ; Conference date: 13-05-2002 Through 17-05-2002",

}

TY - JOUR

T1 - Time-aligned SVD analysis for speaker identification

AU - Clemins, Patrick

AU - Ewalt, Heather

AU - Johnson, Michael

PY - 2002

Y1 - 2002

N2 - This paper presents a time-aligned singular value decomposition (SVD) analysis for speaker identification. SVD analysis has been used for fast spectral matching based on a global representation of an entire utterance. We incorporate temporal normalization directly into the decomposition by using a dynamic time warping (DTW) path to time-align the rows of the feature matrix prior to SVD analysis. Speaker identification results using the TI-46 database indicates that the time-aligned SVD significantly improves accuracy for most threshold choices.

AB - This paper presents a time-aligned singular value decomposition (SVD) analysis for speaker identification. SVD analysis has been used for fast spectral matching based on a global representation of an entire utterance. We incorporate temporal normalization directly into the decomposition by using a dynamic time warping (DTW) path to time-align the rows of the feature matrix prior to SVD analysis. Speaker identification results using the TI-46 database indicates that the time-aligned SVD significantly improves accuracy for most threshold choices.

UR - http://www.scopus.com/inward/record.url?scp=0036294069&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0036294069&partnerID=8YFLogxK

M3 - Conference article

AN - SCOPUS:0036294069

SN - 1520-6149

VL - 4

SP - IV/4160

JO - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

JF - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

T2 - 2002 IEEE International Conference on Acoustic, Speech, and Signal Processing

Y2 - 13 May 2002 through 17 May 2002

ER -

Time-aligned SVD analysis for speaker identification

Resumen

ASJC Scopus subject areas

Otros archivos y enlaces

Huella

Citar esto