Informatics Report Series



Related Pages

Report (by Number) Index
Report (by Date) Index
Author Index
Institute Index

Title:Prosodic and Other Cues to Speech Recognition Failures
Authors: Julia Hirschberg ; Diane Litman ; Marc Swerts
Date:Jun 2004
Publication Title:Speech Communication
Publication Type:Journal Article
Volume No:43 Page Nos:155-175
In spoken dialogue systems, it is important for the system to know how likely a speech recognition hypothesis is to be correct, so it can reject misrecognized user turns, or, in cases where many errors have occurred, change its interaction strategy or switch the caller to a human attendant. We have identified prosodic features which predict more accurately when a recognition hypothesis contains errors than the acoustic confidence scores traditionally used in automatic speech recogntition in spoken dialogue systems. We describe statistical comparisons of features of correctly and incorrectly recognized turns in the TOOT train information corpus and the W99 conference registration corpus, which reveal significant prosodic differences between the two sets of turns. We then present machine learning results showing that the use of prosodic features, alone and in combination with other automatically available features, can predict more accurately whether or not a user turn was correctly recognized, when cmopared to the use of acoustic confidence scores alone.
Links To Paper
No links available
Bibtex format
author = { Julia Hirschberg and Diane Litman and Marc Swerts },
title = {Prosodic and Other Cues to Speech Recognition Failures},
journal = {Speech Communication},
publisher = {Elsevier},
year = 2004,
month = {Jun},
volume = {43},
pages = {155-175},
doi = {10.1016/j.specom.2004.01.006},

Home : Publications : Report 

Please mail <> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh