Faculty of Information Technology, BUT

Publication Details

PLLR Features in Language Recognition System for RATS

PLCHOT Oldřich, DIEZ Sánchez Mireia, SOUFIFAR Mehdi and BURGET Lukáš. PLLR Features in Language Recognition System for RATS. In: Proceedings of Interspeech 2014. Singapore: International Speech Communication Association, 2014, pp. 3048-3051. ISBN 978-1-63439-435-2. Available from: http://www.isca-speech.org/archive/interspeech_2014/i14_3047.html
Czech title
PLLR příznaky v systému rozpoznávání jazyka pro RATS
Type
conference paper
Language
english
Authors
Plchot Oldřich, Ing., Ph.D. (DCGM FIT BUT)
Diez Sánchez Mireia (UPV)
Soufifar Mehdi (NTNU)
Burget Lukáš, doc. Ing., Ph.D. (DCGM FIT BUT)
URL
Keywords
language recognition, PLLR, iVector, phone posterior, neural network, RATS
Abstract
This article is about PLLR Features in Language Recognition System for RATS (Robust Automatic Transcription of Speech).
Annotation
In this paper, we study the use of features based on frame-byframe phone posteriors (PLLRs) for language recognition. The results are reported on the datasets developed for 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 show that systems based on the PLLRs outperform the standard acoustic system based on PLP2 features. By experimenting with the system combinations, we also demonstrate that the PLLR-based systems contain complementary information with respect to the PLP2 system. Finally we make a comparison between the PLLR and phonotactic systems with the outcome favorable to the PLLR.
Published
2014
Pages
3048-3051
Proceedings
Proceedings of Interspeech 2014
Conference
Interspeech 2014, Singapur, SG
ISBN
978-1-63439-435-2
Publisher
International Speech Communication Association
Place
Singapore, SG
BibTeX
@INPROCEEDINGS{FITPUB10748,
   author = "Old\v{r}ich Plchot and Mireia S\'{a}nchez Diez and Mehdi Soufifar and Luk\'{a}\v{s} Burget",
   title = "PLLR Features in Language Recognition System for RATS",
   pages = "3048--3051",
   booktitle = "Proceedings of Interspeech 2014",
   year = 2014,
   location = "Singapore, SG",
   publisher = "International Speech Communication Association",
   ISBN = "978-1-63439-435-2",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/10748"
}
Back to top