Publication detail

iVector-Based Discriminative Adaptation for Automatic Speech Recognition

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

Original Title

iVector-Based Discriminative Adaptation for Automatic Speech Recognition

English Title

iVector-Based Discriminative Adaptation for Automatic Speech Recognition

Type

conference paper

Language

en

Original Abstract

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.

English abstract

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.

Keywords

Automatic speech recognition, I-vector, Discriminative adaptation

RIV year

2011

Released

11.12.2011

Publisher

IEEE Signal Processing Society

Location

Hilton Waikoloa Village, Big Island, Hawaii

ISBN

978-1-4673-0366-8

Book

Proceedings of ASRU 2011

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

152

Pages to

157

Pages count

6

URL

Documents

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",
  annote="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.",
  address="IEEE Signal Processing Society",
  booktitle="Proceedings of ASRU 2011",
  chapter="76442",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2011",
  month="december",
  pages="152--157",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}