Publication Details

Developing A Speaker Identification System For The DARPA RATS Project

PLCHOT Oldřich, MATSOUKAS Spyros, MATĚJKA Pavel, DEHAK Najim, MA Jeff, CUMANI Sandro, GLEMBEK Ondřej, HEŘMANSKÝ Hynek, MESGARANI Nima, SOUFIFAR Mehdi Mohammad, THOMAS Samuel, ZHANG Bing and ZHOU Xinhui et al. Developing A Speaker Identification System For The DARPA RATS Project. In: Proceedings of ICASSP 2013. Vancouver: IEEE Signal Processing Society, 2013, pp. 6768-6772. ISBN 978-1-4799-0355-9.
Czech title
Vývoj systému identifikace řečníka pro DARPA RATS projekt
Type
conference paper
Language
english
Authors
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Matsoukas Spyros (Raytheon BBN)
Matějka Pavel, Ing., Ph.D. (DCGM FIT BUT)
Dehak Najim (JHU)
Ma Jeff (Raytheon BBN)
Cumani Sandro, Mgr., Ph.D. (DCGM FIT BUT)
Glembek Ondřej, Ing., Ph.D. (DCGM FIT BUT)
Heřmanský Hynek, prof. Ing., Dr.Eng. (DCGM FIT BUT)
Mesgarani Nima (UMD)
Soufifar Mehdi Mohammad, Ing. (FIT BUT)
Thomas Samuel (JHU)
Zhang Bing (Raytheon BBN)
and others
URL
Keywords

speaker identification, noisy speech processing

Abstract

This paper is focusing on the development of a speaker identification system for the DARPA RATS Project.

Annotation

This paper describes the speaker identification (SID) system developed by the Patrol team for the first phase of the DARPA RATS (Robust Automatic Transcription of Speech) program, which seeks to advance state of the art detection capabilities on audio from highly degraded communication channels. We present results using multiple SID systems differing mainly in the algorithm used for voice activity detection (VAD) and feature extraction. We show that (a) unsupervised VAD performs as well supervised methods in terms of downstream SID performance, (b) noise-robust feature extraction methods such as CFCCs out-perform MFCC front-ends on noisy audio, and (c) fusion of multiple systems provides 24% relative improvement in EER compared to the single best system when using a novel SVM-based fusion algorithm that uses side information such as gender, language, and channel id.

Published
2013
Pages
6768-6772
Proceedings
Proceedings of ICASSP 2013
Conference
38th International Conference on Acoustics, Speech, and Signal Processing, Vancouver, CA
ISBN
978-1-4799-0355-9
Publisher
IEEE Signal Processing Society
Place
Vancouver, CA
BibTeX
@INPROCEEDINGS{FITPUB10313,
   author = "Old\v{r}ich Plchot and Spyros Matsoukas and Pavel Mat\v{e}jka and Najim Dehak and Jeff Ma and Sandro Cumani and Ond\v{r}ej Glembek and Hynek He\v{r}mansk\'{y} and Nima Mesgarani and Mohammad Mehdi Soufifar and Samuel Thomas and Bing Zhang and Xinhui Zhou and et al.",
   title = "Developing A Speaker Identification System For The DARPA RATS Project",
   pages = "6768--6772",
   booktitle = "Proceedings of ICASSP 2013",
   year = 2013,
   location = "Vancouver, CA",
   publisher = "IEEE Signal Processing Society",
   ISBN = "978-1-4799-0355-9",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10313"
}
Back to top