Publication detail

Region Dependent Linear Transforms in Multilingual Speech Recognition

KARAFIÁT, M. JANDA, M. ČERNOCKÝ, J. BURGET, L.

Original Title

Region Dependent Linear Transforms in Multilingual Speech Recognition

English Title

Region Dependent Linear Transforms in Multilingual Speech Recognition

Type

conference paper

Language

en

Original Abstract

In today's speech recognition systems, linear or nonlinear transformations are usually applied to post-process speech features forming input to HMM based acoustic models. In this work, we experiment with three popular transforms: HLDA,MPE-HLDA and Region Dependent Linear Transforms (RDLT), which are trained jointly with the acoustic model to extract maximum of the discriminative information from the raw features and to represent it in a form suitable for the following GMM-HMM based acoustic model. We focus on multi-lingual environments, where limited resources are available for training recognizers of many languages. Using data from GlobalPhone database, we show that, under such restrictive conditions, the feature transformations can be advantageously shared across languages and robustly trained using data from several languages.

English abstract

In today's speech recognition systems, linear or nonlinear transformations are usually applied to post-process speech features forming input to HMM based acoustic models. In this work, we experiment with three popular transforms: HLDA,MPE-HLDA and Region Dependent Linear Transforms (RDLT), which are trained jointly with the acoustic model to extract maximum of the discriminative information from the raw features and to represent it in a form suitable for the following GMM-HMM based acoustic model. We focus on multi-lingual environments, where limited resources are available for training recognizers of many languages. Using data from GlobalPhone database, we show that, under such restrictive conditions, the feature transformations can be advantageously shared across languages and robustly trained using data from several languages.

Keywords

HLDA, Region Dependent Transforms, Minimum Phone Error, fMPE, multilingual speech recognition

RIV year

2012

Released

25.03.2012

Publisher

IEEE Signal Processing Society

Location

Kyoto

ISBN

978-1-4673-0044-5

Book

Proc. International Conference on Acoustics, Speech, and Signal Processing 2012

Edition

NEUVEDEN

Edition number

NEUVEDEN

Pages from

4885

Pages to

4888

Pages count

4

URL

Documents

BibTex


@inproceedings{BUT91480,
  author="Martin {Karafiát} and Miloš {Janda} and Jan {Černocký} and Lukáš {Burget}",
  title="Region Dependent Linear Transforms in Multilingual Speech Recognition",
  annote="In today's speech recognition systems, linear or nonlinear transformations are
usually applied to post-process speech features forming input to HMM based
acoustic models. In this work, we experiment with three popular transforms:
HLDA,MPE-HLDA and Region Dependent Linear Transforms (RDLT), which are trained
jointly with the acoustic model to extract maximum of the discriminative
information from the raw features and to represent it in a form suitable for the
following GMM-HMM based acoustic model. We focus on multi-lingual environments,
where limited resources are available for training recognizers of many languages.
Using data from GlobalPhone database, we show that, under such restrictive
conditions, the feature transformations can be advantageously shared across
languages and robustly trained using data from several languages.",
  address="IEEE Signal Processing Society",
  booktitle="Proc. International Conference on Acoustics, Speech, and Signal Processing 2012",
  chapter="91480",
  doi="10.1109/ICASSP.2012.6289014",
  edition="NEUVEDEN",
  howpublished="print",
  institution="IEEE Signal Processing Society",
  year="2012",
  month="march",
  pages="4885--4888",
  publisher="IEEE Signal Processing Society",
  type="conference paper"
}