- 著者
- Ronald Rosenfeld, Xuedong Huang, Merrick Furst
- タイトル
- Exploiting Correlations Among Models with Application to
Large Vocabulary Speech Recognition
- 日時
- May 1991
- 概要
- In a typical speech recognition system, computing the match
between an incoming acoustic string and many competing models
is computationally expensive.
Once the highest ranking models are identified, all other match
scores are discarded.
We propose to make use of all computed scores by means of
statistical inference.
We view the match between an incoming acoustic string s and a
model Mi as a random variable Yi.
The class-conditional distributions of (Y1,...,YN) can be
studied offline by sampling, and then used in a variety of
ways.
For example, the means of these distributions give rise to a
natural measure of distance between models.
One of the most useful applications of these distributions is
as a basis for a new Bayesian classifier.
The latter can be used to significantly reduce search effort
in large vocabularies, and to quickly obtain a short list of
candidate words.
An example HMM-based system shows promising results.
- カテゴリ
- CMUTR

Category: CMUTR
Institution: Department of Computer Science, Carnegie
Mellon University
Abstract: In a typical speech recognition system, computing the match
between an incoming acoustic string and many competing models
is computationally expensive.
Once the highest ranking models are identified, all other match
scores are discarded.
We propose to make use of all computed scores by means of
statistical inference.
We view the match between an incoming acoustic string s and a
model Mi as a random variable Yi.
The class-conditional distributions of (Y1,...,YN) can be
studied offline by sampling, and then used in a variety of
ways.
For example, the means of these distributions give rise to a
natural measure of distance between models.
One of the most useful applications of these distributions is
as a basis for a new Bayesian classifier.
The latter can be used to significantly reduce search effort
in large vocabularies, and to quickly obtain a short list of
candidate words.
An example HMM-based system shows promising results.
Number: CMU-CS-91-148
Bibtype: TechReport
Month: May
Author: Ronald Rosenfeld
Xuedong Huang
Merrick Furst
Title: Exploiting Correlations Among Models with Application to
Large Vocabulary Speech Recognition
Year: 1991
Address: Pittsburgh, PA
Super: @CMUTR