|
Edinburgh Research Archive >
Centre for Speech Technology Research >
CSTR publications >
Please use this identifier to cite or link to this item:
http://hdl.handle.net/1842/1036
|
| Title: | Automatic summarization of voicemail messages using lexical and prosodic features |
| Authors: | Koumpis, Konstantinos
Renals, Steve |
| Keywords: | Voicemail
automatic summarization
feature subset selection
prosody
receiver operating characteristic
short message service |
| Issue Date: | Feb-2005 |
| Publisher: | ACM Press. New York, NY, USA |
| Citation: | ACM Transactions on Speech and Language Processing (TSLP). Volume 2 , Issue 1 (February 2005) |
| Abstract: | This article 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 described 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. |
| URI: | http://doi.acm.org/10.1145/1075389.1075390
http://hdl.handle.net/1842/1036 |
| ISSN: | 1550-4875 |
| Type: | Research Paper |
| Appears in Collections: | CSTR publications
|
Files in This Item:
| File |
Description |
Size | Format |
|---|
| tslp05.pdf | | 287Kb | Adobe PDF | View/Open | | tslp05.ps.gz | | 321Kb | Gzipped PostScript | View/Open |
|
All items in ERA are protected by copyright, with all rights reserved.
|
