Experiments on speech tracking in audio documents using Gaussian mixture modeling

Author

Seck, Mouhamadou ; Magrin-Chagnolleau, Ivan ; Bimbot, Frédéric

Author_Institution

IRISA, Rennes, France

Volume

1

fYear

2001

fDate

2001

Firstpage

601

Abstract

This paper deals with the tracking of speech segments in audio documents. We use a cepstral-based acoustic analysis and Gaussian mixture models for the representation of the training data. Three ways of scoring an audio document based on a frame-level likelihood calculation are proposed and compared. Our experiments are done on a database composed of television programs including news reports, advertisements, and documentaries. The best equal error rate obtained is approximately 12%

Keywords

Gaussian processes; acoustic signal processing; audio signal processing; cepstral analysis; signal representation; speech processing; tracking; Gaussian mixture modeling; advertisements; audio document scoring; audio documents; cepstral-based acoustic analysis; covariance matrices; database; equal error rate; frame-level likelihood; music; news reports; noise segments; smoothed log-likelihood ratio; speech segments tracking; television programs; training data representation; Cepstral analysis; Covariance matrix; Databases; Error analysis; Indexing; Smoothing methods; Speech enhancement; TV; Testing; Training data;

fLanguage

English

Publisher

ieee

Conference_Titel

Acoustics, Speech, and Signal Processing, 2001. Proceedings. (ICASSP '01). 2001 IEEE International Conference on

Conference_Location

Salt Lake City, UT

ISSN

1520-6149

Print_ISBN

0-7803-7041-4

Type

conf

DOI

10.1109/ICASSP.2001.940903

Filename

940903