๐”– Bobbio Scriptorium
โœฆ   LIBER   โœฆ

Evaluation of word confidence for speech recognition systems

โœ Scribed by Manhung Siu; Herbert Gish

Publisher
Elsevier Science
Year
1999
Tongue
English
Weight
195 KB
Volume
13
Category
Article
ISSN
0885-2308

No coin nor oath required. For personal study only.

โœฆ Synopsis

Confidence measures enable us to assess the output of a speech recognition system. The confidence measure provides us with an estimate of the probability that a word in the recognizer output is either correct or incorrect. In this paper we discuss ways in which to quantify the performance of confidence measures in terms of their discrimination power and bias. In particular, we analyze two different performance metrics: the classification equal error rate and the normalized mutual information metric. We then report experimental results of using these metrics to compare four different confidence measure estimation schemes. We also discuss the relationship between these metrics and the operating point of the speech recognition system and develop an approach to the robust estimation of normalized mutual information.

๐Ÿ“œ SIMILAR VOLUMES

Comparison of continuous speech recognit
Comparison of continuous speech recognition systems with unknown-word processing for speech disfluencies
โœ Atsuhiko Kai; Seiichi Nakagawa ๐Ÿ“‚ Article ๐Ÿ“… 1998 ๐Ÿ› John Wiley and Sons ๐ŸŒ English โš– 594 KB

This paper describes speech recognition systems for dealing with spontaneous speech, in which an unknownword processing method based on subword sequence decoding is employed. We propose an efficient algorithm for unknown-word processing that employs an independent process of subword sequence decodin

Recognition confidence scoring and its u
Recognition confidence scoring and its use in speech understanding systems
โœ Timothy J. Hazen; Stephanie Seneff; Joseph Polifroni ๐Ÿ“‚ Article ๐Ÿ“… 2002 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 145 KB

In this paper we present an approach to recognition confidence scoring and a set of techniques for integrating confidence scores into the understanding and dialogue components of a speech understanding system. The recognition component uses a multi-tiered approach where confidence scores are compute

A word graph algorithm for large vocabul
A word graph algorithm for large vocabulary continuous speech recognition
โœ Stefan Ortmanns; Hermann Ney; Xavier Aubert ๐Ÿ“‚ Article ๐Ÿ“… 1997 ๐Ÿ› Elsevier Science ๐ŸŒ English โš– 360 KB

This paper describes a method for the construction of a word graph (or lattice) for large vocabulary, continuous speech recognition. The advantage of a word graph is that a fairly good degree of decoupling between acoustic recognition at the 10-ms level and the final search at the word level using a