Publication detail

Using Smoothed Heteroscedastic Linear Discriminant Analysis in Large Vocabulary Continuous Speech Recognition System

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

Original Title

Using Smoothed Heteroscedastic Linear Discriminant Analysis in Large Vocabulary Continuous Speech Recognition System

Type

conference paper

Language

English

Original Abstract

In the state-of-the-art speech recognition systems, Heteroscedastic Linear Discriminant Analysis (HLDA)
is becoming popular technique allowing for feature decorrelation and dimensionality reduction.
However, HLDA relies on statistics, which may not be reliably estimated when only limited amount of
training data is available. Recently, Smoothed HLDA (SHLDA) was proposed
as a robust modification of
HLDA. Previously, SHLDA was successfully used for feature combination in
small vocabulary recognition
experiments. In this work, we verify that SHLDA can be advantageously used also for Large Vocabulary
Continuous Speech Recognition.

Keywords

speech recognition, LVCSR, HLDA, feature transform, dimensionality reduction

Authors

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

RIV year

2005

Released

20. 9. 2005

Location

Edinbourgh

Pages from

1

Pages to

8

Pages count

8

URL

BibTex

@inproceedings{BUT18264,
  author="Martin {Karafiát} and Lukáš {Burget} and Jan {Černocký}",
  title="Using Smoothed Heteroscedastic Linear Discriminant Analysis in Large Vocabulary Continuous Speech Recognition System",
  booktitle="2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms",
  year="2005",
  pages="8",
  address="Edinbourgh",
  url="https://www.fit.vutbr.cz/~karafiat/publi/2005/karafiat_mlmi2005.pdf"
}