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 a low-dimensional fixed-length representation of information about speaker and acoustic environment. To utilize iVectors for adaptation, region dependent linear transforms (RDLT) are discriminatively trained using the MPE criterion on large amounts of annotated data to extract the relevant information from iVectors and to compensate speech features. The approach was tested on standard CTS data. We found it to be complementary to common adaptation techniques. On a well-tuned RDLT system with standard CMLLR adaptation we 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"
}