Edinburgh Research Explorer

Extractive Summarization of Voicemail using Lexical and Prosodic Feature Subset Selection

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Original languageEnglish
Title of host publication7th European Conference on Speech Communication and Technology
Subtitle of host publicationEurospeech 2001 Scandinavia
EditorsPaul Dalsgaard, Børge Lindberg, Henrik Benner, Zheng-Hua Tan
Place of PublicationAalborg, Denmark
Publisher Kommunik Grafiske Løsninger
Pages2377-2380
ISBN (Print)87-90834-10-0
Publication statusPublished - 2001
Event7th European Conference on Speech Communication and Technology (Eurospeech 2001 Scandinavia) - Aalborg Congress and Culture Centre, Aalborg, Denmark
Duration: 3 Sep 20017 Sep 2001

Conference

Conference7th European Conference on Speech Communication and Technology (Eurospeech 2001 Scandinavia)
CountryDenmark
CityAalborg
Period3/09/017/09/01

Abstract

This paper presents a novel data-driven approach to summarizing spoken audio transcripts utilizing lexical and prosodic features. The former are obtained from a speech recognizer and the latter are extracted automatically from speech waveforms. We employ a feature subset selection algorithm, based on ROC curves, which examines different combinations of features at different target operating conditions. The approach is evaluated on the IBM Voicemail corpus, demonstrating that it is possible and desirable to avoid complete commitment to a single best classifier or feature set.

ID: 27435147