DMCA
A Fast Lattice-Based Approach to Vocabulary Independent Wordspotting (1994)
| Venue: | In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing |
| Citations: | 50 - 7 self |
BibTeX
@INPROCEEDINGS{James94afast,
author = {D. A. James and S.J. Young and Cb Pz},
title = {A Fast Lattice-Based Approach to Vocabulary Independent Wordspotting},
booktitle = {In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing},
year = {1994},
pages = {377--380},
publisher = {IEEE}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Practical applications of wordspotting, such as spoken message retrieval and browsing, require the ability to process large amounts of speech data at speeds many times faster than real-time. This paper presents a novel approach to this problem in which all of the stored audio material is preprocessed off-line to generate a phoneme lattice. At search time, putative word matches are found in this lattice using symmetric dynamic programming. The paper presents the details of the algorithms used and compares performance with a number of conventional approaches using a 20 keyword vocabulary on the DARPA Resource Management Task. The results show that the proposed method is very much faster yet performs acceptably compared to conventional systems which depend on keyword-specific training or prior knowledge of the test set vocabulary. 1. INTRODUCTION In recent years, computers have become increasingly able to manipulate non-textual data, and applications such as video and voice mail have ari...
Keyphrases
fast lattice-based approach vocabulary independent wordspotting symmetric dynamic programming recent year phoneme lattice speech data novel approach conventional system conventional approach keyword vocabulary speed many time keyword-specific training practical application prior knowledge search time putative word match spoken message retrieval non-textual data stored audio material voice mail large amount darpa resource management task
