Detail publikace

iVector-Based Discriminative Adaptation for Automatic Speech Recognition

KARAFIÁT, M. BURGET, L. MATĚJKA, P. GLEMBEK, O. ČERNOCKÝ, J.

Originální název

iVector-Based Discriminative Adaptation for Automatic Speech Recognition

Typ

článek ve sborníku mimo WoS a Scopus

Jazyk

angličtina

Originální abstrakt

The iVector is alow-dimensional fixed-length representation of information about speaker and acoustic environment. Toutilize iVectors for adaptation, region dependent linear transforms(RDLT) are discriminatively trained using the MPE criterion on largeamounts of annotated data to extract the relevant information fromiVectors and to compensate speech features. The approach was tested onstandard CTS data. We found it to be complementary to common adaptationtechniques. On a well-tuned RDLT system with standard CMLLR adaptationwe reached an 0.8% additive absolute WER improvement.

Klíčová slova

Automatic speech recognition, I-vector, Discriminative adaptation

Autoři

KARAFIÁT, M.; BURGET, L.; MATĚJKA, P.; GLEMBEK, O.; ČERNOCKÝ, J.

Rok RIV

2011

Vydáno

11. 12. 2011

Nakladatel

IEEE Signal Processing Society

Místo

Hilton Waikoloa Village, Big Island, Hawaii

ISBN

978-1-4673-0366-8

Kniha

Proceedings of ASRU 2011

Strany od

152

Strany do

157

Strany počet

6

URL

http://www.fit.vutbr.cz/research/groups/speech/publi/2011/karafiat_asru2011_00152.pdf

BibTex

@inproceedings{BUT76442,
  author="Martin {Karafiát} and Lukáš {Burget} and Pavel {Matějka} and Ondřej {Glembek} and Jan {Černocký}",
  title="iVector-Based Discriminative Adaptation for Automatic Speech Recognition",
  booktitle="Proceedings of ASRU 2011",
  year="2011",
  pages="152--157",
  publisher="IEEE Signal Processing Society",
  address="Hilton Waikoloa Village, Big Island, Hawaii",
  isbn="978-1-4673-0366-8",
  url="http://www.fit.vutbr.cz/research/groups/speech/publi/2011/karafiat_asru2011_00152.pdf"
}