Detail publikace

Region Dependent Linear Transforms in Multilingual Speech Recognition

Originální název

Region Dependent Linear Transforms in Multilingual Speech Recognition

Anglický název

Region Dependent Linear Transforms in Multilingual Speech Recognition

Jazyk

en

Originální abstrakt

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.

Anglický abstrakt

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.

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"
}