Classification of time delay estimates for robust speaker localization

Strobel N, Rabenstein R (1999)

Publication Status: Published

Publication Type: Conference contribution, Original article

Publication year: 1999

Publisher: IEEE

City/Town: Piscataway, NJ, United States

Book Volume: 6

Pages Range: 3081-3084

Conference Proceedings Title: Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99)

Event location: Phoenix, AZ US

URI: https://www.scopus.com/inward/record.uri?partnerID=HzOxMe3b&scp=0032626650&origin=inward

Abstract

This paper proposes a solution to the problem of robust speaker localization under adverse acoustic conditions. The approach is based on the classification of time delay estimates. Two classification techniques are investigated in detail: maximum likelihood (ML) classification and classification based on histogram comparison. Their performance under adverse acoustic conditions is compared to outcomes obtained with the traditional approach which uses time delay estimates directly to infer speaker positions. Experiments indicate that the ML classification method provides little improvement over the traditional method. On the other hand, using histogram classification, we can improve the probability of correct speaker localization by more than 60% compared to either the traditional approach or the ML classification technique.

Authors with CRIS profile

Rudolf Rabenstein Lehrstuhl für Multimediakommunikation und Signalverarbeitung (LMS)

Involved external institutions

Siemens AG DE Germany (DE)

How to cite

APA:

Strobel, N., & Rabenstein, R. (1999). Classification of time delay estimates for robust speaker localization. In Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99) (pp. 3081-3084). Phoenix, AZ, US: Piscataway, NJ, United States: IEEE.

MLA:

Strobel, Norbert, and Rudolf Rabenstein. "Classification of time delay estimates for robust speaker localization." Proceedings of the Proceedings of the 1999 IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP-99), Phoenix, AZ Piscataway, NJ, United States: IEEE, 1999. 3081-3084.

BibTeX: Download