Informatics Report Series


Report   

EDI-INF-RR-0658


Related Pages

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

Home
Title:Automatic summarization of voicemail messages using lexical and prosodic features
Authors: Steve Renals ; Konstantinos Koumpis
Date:Feb 2005
Publication Title:ACM Transactions on Speech and Language Processing
Publisher:ACM Press
Publication Type:Journal Article Publication Status:Published
Volume No:2(1) Page Nos:1-24
DOI:10.1145/1075389.1075390
Abstract:
This paper presents trainable methods for extracting principal content words from voicemail messages. The short text summaries generated are suitable for mobile messaging applications. The system uses a set of classifiers to identify the summary words, with each word being identified by a vector of lexical and prosodic features. We use an ROC-based algorithm, Parcel, to select input features (and classifiers). We have performed a series of objective and subjective evaluations using unseen data from two different speech recognition systems, as well as human transcriptions of voicemail speech.
Links To Paper
1st Link
2nd Link
Bibtex format
@Article{EDI-INF-RR-0658,
author = { Steve Renals and Konstantinos Koumpis },
title = {Automatic summarization of voicemail messages using lexical and prosodic features},
journal = {ACM Transactions on Speech and Language Processing},
publisher = {ACM Press},
year = 2005,
month = {Feb},
volume = {2(1)},
pages = {1-24},
doi = {10.1145/1075389.1075390},
url = {http://doi.acm.org/10.1145/1075389.1075390},
}


Home : Publications : Report 

Please mail <reports@inf.ed.ac.uk> with any changes or corrections.
Unless explicitly stated otherwise, all material is copyright The University of Edinburgh