Consistent speaker identification via Wigner smoothing techniques

Author

Wilbur, JoEllen ; Taylor, Fred J.

Author_Institution

Dept. of Electr. & Comput. Eng., Clemson Univ., SC, USA

fYear

1988

fDate

11-14 Apr 1988

Firstpage

591

Abstract

A voiceprint database for automatic speaker identification is proposed. With traditional short-time Fourier transform techniques system limitations arise not from discrimination between two different speakers but from single-speaker variations. The proposed estimator uses a derivative of the Wigner distribution (WD) function called the smoothed-discrete-WD (SDWD). The SDWD is shown to produce a significantly more consistent estimate over the differing samples of a given word utterance when the DWD kernel has been averaged over the entire window. The formant frequencies are well identified and remain consistent over the samples

Keywords

fast Fourier transforms; spectral analysis; speech recognition; FFT; Wigner distribution function; Wigner smoothing techniques; automatic speaker identification; formant frequencies; speaker identification; spectral analysis; voiceprint database; word utterance; Databases; Discrete Fourier transforms; Frequency domain analysis; Frequency estimation; Kernel; Signal resolution; Smoothing methods; Spectrogram; Time frequency analysis; Tires;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 1988. ICASSP-88., 1988 International Conference on

Conference_Location

New York, NY

ISSN

1520-6149

Type

conf

DOI

10.1109/ICASSP.1988.196654

Filename

196654