A Novel Discriminative Method for Pruning Pronunciation Dictionary Entries

Seppo Enarvi, Mikko Kurimo

Research output: Chapter in Book/Report/Conference proceedingConference contributionScientificpeer-review

151 Downloads (Pure)

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.
Original languageEnglish
Title of host publication7th Conference on Speech Technology and Human-Computer Dialogue, (SpeD 2013), Cluj-Napoca, 16 Oct 2013 - 19 Oct 2013
PublisherIEEE
Pages113-116
ISBN (Electronic)978-1-4799-1065-6
ISBN (Print)978-1-4799-1064-9
DOIs
Publication statusPublished - 2013
MoE publication typeA4 Article in a conference publication

Keywords

  • speech recognition
  • pronunciation modeling
  • discriminative learning
  • dictionary pruning

Fingerprint Dive into the research topics of 'A Novel Discriminative Method for Pruning Pronunciation Dictionary Entries'. Together they form a unique fingerprint.

Cite this