A Novel Discriminative Method for Pruning Pronunciation Dictionary Entries

Loading...
Thumbnail Image

Access rights

openAccess

URL

Journal Title

Journal ISSN

Volume Title

A4 Artikkeli konferenssijulkaisussa

Date

2013

Major/Subject

Mcode

Degree programme

Language

en

Pages

113-116

Series

7th Conference on Speech Technology and Human-Computer Dialogue, (SpeD 2013), Cluj-Napoca, 16 Oct 2013 - 19 Oct 2013

Abstract

In this paper we describe a novel discriminative method for pruning pronunciation dictionary. The algorithm removes those entries from the dictionary that affect negatively on speech recognition word error rate. The implementation is simple and requires no tunable parameters. We have carried out preliminary speech recognition experiments, pruning multiword pronunciations created by a phonetician. With the task in hand, we achieved only minimal improvements in recognition results. We are optimistic that the algorithm will prove to be useful in pruning larger dictionaries containing automatically generated pronunciations.

Description

VK: coin hiit

Keywords

speech recognition, pronunciation modeling, discriminative learning, dictionary pruning

Other note

Citation

Enarvi, S & Kurimo, M 2013, A Novel Discriminative Method for Pruning Pronunciation Dictionary Entries . in 7th Conference on Speech Technology and Human-Computer Dialogue, (SpeD 2013), Cluj-Napoca, 16 Oct 2013 - 19 Oct 2013 . IEEE, pp. 113-116 . https://doi.org/10.1109/SpeD.2013.6682659