Publication Details

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

KARAFIÁT Martin, BURGET Lukáš and ČERNOCKÝ Jan. Using Smoothed Heteroscedastic Linear Discriminant Analysis in Large Vocabulary Continuous Speech Recognition System. In: 2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms. tento článek nebyl zařazen mezi Revised Selected Papers, nevyšel v LNCS 3869. Edinbourgh, Scotland: University of Edinburgh, 2005, p. 8.
Czech title
Užití SHLDA pro rozpoznávání řeči s velkým slovníkem
Type
conference paper
Language
english
Authors
URL
Keywords

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

Abstract

In this work, we verify that SHLDA can be advantageously used also for Large Vocabulary
Continuous Speech Recognition.

Annotation

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.

Published
2005
Pages
8
Proceedings
2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms
Series
tento článek nebyl zařazen mezi Revised Selected Papers, nevyšel v LNCS 3869
Conference
2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms, Edinburgh, GB
Publisher
University of Edinburgh
Place
Edinbourgh, Scotland, GB
BibTeX
@INPROCEEDINGS{FITPUB7929,
   author = "Martin Karafi\'{a}t and Luk\'{a}\v{s} Burget and Jan \v{C}ernock\'{y}",
   title = "Using Smoothed Heteroscedastic Linear Discriminant Analysis in Large  Vocabulary Continuous Speech Recognition System",
   pages = 8,
   booktitle = "2nd Joint Workshop on Multimodal Interaction and Related Machine Learning Algorithms",
   series = "tento \v{c}l\'{a}nek nebyl za\v{r}azen mezi Revised Selected Papers, nevy\v{s}el v LNCS 3869",
   year = 2005,
   location = "Edinbourgh, Scotland, GB",
   publisher = "University of Edinburgh",
   language = "english",
   url = "https://www.fit.vut.cz/research/publication/7929"
}
Back to top