The BBN Byblos 1997 large vocabulary conversational speech recognition system

This paper presents the 1997 BBN Byblos large vocabulary speech recognition (LVCSR) system. We give an outline of the algorithms and procedures used to train the system, describe the recognizer configuration and present the major technological innovations that lead to the performance improvements. T...

Full description

Saved in:
Bibliographic Details
Main Authors: Zavaliagkos, G., McDonough, J., Miller, D., El-Jaroudi, A., Billa, J., Richardson, F., Ma, K., Siu, M., Gish, H.
Format: Conference Proceeding
Language:English
Subjects:
Error analysis
Maximum likelihood decoding
Natural languages
Signal processing
Signal processing algorithms
Speech recognition
Technological innovation
Telephony
Testing
Vocabulary
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:This paper presents the 1997 BBN Byblos large vocabulary speech recognition (LVCSR) system. We give an outline of the algorithms and procedures used to train the system, describe the recognizer configuration and present the major technological innovations that lead to the performance improvements. The major testbed we present our results for is the Switchboard corpus, where current word error rates vary from 27% to 34% depending on the test set. In addition, we present results on the CallHome Spanish and Arabic tests, where we demonstrate that technology developed on English corpora is very much portable to other problems and languages.
ISSN:1520-6149
2379-190X
DOI:10.1109/ICASSP.1998.675412