Publication detail

Discriminative Training Techniques for Acoustic Language Identification

BURGET, L. MATĚJKA, P. ČERNOCKÝ, J.

Original Title

Discriminative Training Techniques for Acoustic Language Identification

Type

article in a collection out of WoS and Scopus

Language

English

Original Abstract

This paper presents comparison of Maximum Likelihood (ML) and  discriminative Maximum Mutual Information (MMI) training  for acoustic modeling in language identification (LID). Clear  advantage of MMI over ML training is shown. The final error rate compares favorably to other results published on NIST 2003 data.

Keywords

language identification, language recognition, acoustic modeling, disriminative training, maximum mutual information

Authors

BURGET, L.; MATĚJKA, P.; ČERNOCKÝ, J.

RIV year

2006

Released

9. 8. 2006

Location

Toulouse

Pages from

209

Pages to

212

Pages count

4

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2006/burget_mmi_lid_icassp2006.pdf

BibTex

@inproceedings{BUT22218,
  author="Lukáš {Burget} and Pavel {Matějka} and Jan {Černocký}",
  title="Discriminative Training Techniques for Acoustic Language Identification",
  booktitle="Proceedings of ICASSP 2006",
  year="2006",
  pages="209--212",
  address="Toulouse",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2006/burget_mmi_lid_icassp2006.pdf"
}