Show simple item record

dc.contributor.authorREILLY, RICHARD
dc.date.accessioned2008-06-20T17:19:43Z
dc.date.available2008-06-20T17:19:43Z
dc.date.issued2007
dc.date.submitted2007en
dc.identifier.citationScanlon, P. and Ellis, D. and Reilly, R. B. 'Using broad phonetic group experts for improved speech recognition' in IEEE Transactions on Audio Speech and Language Processing, 15, (3), 2007, pp. 803 ? 812.en
dc.identifier.issn51842
dc.identifier.issn51842
dc.identifier.otherYen
dc.identifier.otherY
dc.identifier.urihttp://hdl.handle.net/2262/17559
dc.descriptionPUBLISHEDen
dc.description.abstractIn phoneme recognition experiments, it was found that approximately 75% of misclassified frames were assigned labels within the same broad phonetic group (BPG). While the phoneme can be described as the smallest distinguishable unit of speech, phonemes within BPGs contain very similar characteristics and can be easily confused. However, different BPGs, such as vowels and stops, possess very different spectral and temporal characteristics. In order to accommodate the full range of phonemes, acoustic models of speech recognition systems calculate input features from all frequencies over a large temporal context window. A new phoneme classifier is proposed consisting of a modular arrangement of experts, with one expert assigned to each BPG and focused on discriminating between phonemes within that BPG. Due to the different temporal and spectral structure of each BPG, novel feature sets are extracted using mutual information, to select a relevant time-frequency (TF) feature set for each expert. To construct a phone recognition system, the output of each expert is combined with a baseline classifier under the guidance of a separate BPG detector. Considering phoneme recognition experiments using the TIMIT continuous speech corpus, the proposed architecture afforded significant error rate reductions up to 5% relative.en
dc.format.extent1147615 bytes
dc.format.extent803en
dc.format.extent812en
dc.format.mimetypeapplication/pdf
dc.language.isoenen
dc.publisherIEEEen
dc.relation.ispartofseries15en
dc.relation.ispartofseries3en
dc.rightsYen
dc.subjectAutomatic speech recognition, broad phoneticen
dc.titleUsing broad phonetic group experts for improved speech recognitionen
dc.typeJournal Articleen
dc.contributor.sponsorEnterprise Ireland
dc.type.supercollectionscholarly_publicationsen
dc.type.supercollectionrefereed_publicationsen
dc.identifier.peoplefinderurlhttp://people.tcd.ie/reillyri
dc.identifier.rssurihttp://ieeexplore.ieee.org/iel5/10376/4100662/04100697.pdf?tp=&arnumber=4100697&isnumber=4100662


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record