Publication Details

Ivector-Based Prosodic System For Language Identification

MARTÍNEZ GONZÁLEZ, D.; BURGET, L.; FERRER, L.; SCHEFFER, N. Ivector-Based Prosodic System For Language Identification. Proc. International Conference on Acoustics, Speec. Kyoto: IEEE Signal Processing Society, 2012. p. 4861-4864. ISBN: 978-1-4673-0044-5.
Czech title
I-vektorový prozodický systém pro rozpoznávání jazyka
Type
conference paper
Language
English
Authors
Martínez González David (FIT)
Burget Lukáš, doc. Ing., Ph.D. (DCGM)
Ferrer Luciana
Scheffer Nicolas
URL
Keywords

Language Identification, Prosody, iVectors, Joint Factor Analysis

Abstract

This paper is on a LID system based on prosodic features. Extraction of the pitch, energy, and duration allows us to represent the three components of prosody.

Annotation

Prosody is the part of speech where rhythm, stress, and intonation are reflected. In language identification tasks, these characteristics are assumed to be language dependent, and thus the language can be identified from them. In this paper, an automatic language recognition system that extracts prosody information from speech and makes decisions about the language with a generative classifier based on iVectors is built. The system is tested on the NIST LRE09 dataset. The results are still not comparable to state-of-the-art acoustic and phonotactic systems. However, they are promising and the fusion of the new approach with an iVector-based acoustic system is found to bring further improvements over the latter.

Published
2012
Pages
4861–4864
Proceedings
Proc. International Conference on Acoustics, Speec
ISBN
978-1-4673-0044-5
Publisher
IEEE Signal Processing Society
Place
Kyoto
DOI
10.1109/ICASSP.2012.6289008
BibTeX 
@inproceedings{BUT91504,
  author="David {Martínez González} and Lukáš {Burget} and Luciana {Ferrer} and Nicolas {Scheffer}",
  title="Ivector-Based Prosodic System For Language Identification",
  booktitle="Proc. International Conference on Acoustics, Speec",
  year="2012",
  pages="4861--4864",
  publisher="IEEE Signal Processing Society",
  address="Kyoto",
  doi="10.1109/ICASSP.2012.6289008",
  isbn="978-1-4673-0044-5",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2012/martinez_icassp2012_0004861.pdf"
}
Back to top