Logo do repositório
 
Publicação

Acoustic Similarity Scores for Keyword Spotting

2014Comunicação em conferência Acesso aberto
Ver registo simples
datacite.subject.fosCiências Naturais::Ciências da Computação e da Informação
datacite.subject.sdg09:Indústria, Inovação e Infraestruturas
dc.contributor.authorVeiga, Arlindo
dc.contributor.authorLopes, Carla
dc.contributor.authorSá, Luís
dc.contributor.authorPerdigão, Fernando
dc.date.accessioned2026-05-05T15:08:36Z
dc.date.available2026-05-05T15:08:36Z
dc.date.issued2014
dc.descriptionArtigo integrado no Volume Editors: Mamede, N. et al.
dc.descriptionArticle number - LNAI 8775.
dc.descriptionConference name: 11th International Conference on Computational Processing of Portuguese, PROPOR 2014 Conference city: Sao Carlos/SP Conference date: 6 October 2014 - 8 October 2014 Conference code: 109139
dc.description.abstractThis paper presents a study on keyword spotting systems based on acoustic similarity between a filler model and keyword model. The ratio between the keyword model likelihood and the generic (filler) model likelihood is used by the classifier to detect relevant peaks values that indicate keyword occurrences. We have changed the standard scheme of keyword spotting system to allow keyword detection in a single forward step. We propose a new loglikelihood ratio normalization to minimize the effect of word length on the classifier performance. Tests show the effectiveness of our normalization method against two other methods. Experiments were performed on continuous speech utterances of the Portuguese TECNOVOZ database (read sentences) with keywords of several lengths.eng
dc.description.sponsorship
dc.identifier.citationVeiga, A., Lopes, C., Sá, L., & Perdigão, F. (2014). Acoustic Similarity Scores for Keyword Spotting. In J. Baptista, N. Mamede, S. Candeias, I. Paraboni, T. A. S. Pardo, & M. G. V. Nunes (Eds.), Computational Processing of the Portuguese Language: 11th International Conference, PROPOR 2014 (Vol. 8775, pp. 48–58). Springer. https://doi.org/10.1007/978-3-319-09761-9_5.
dc.identifier.doi10.1007/978-3-319-09761-9_5
dc.identifier.issn978-889070184-9
dc.identifier.urihttp://hdl.handle.net/10400.8/16230
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer
dc.relation.hasversionhttps://link.springer.com/chapter/10.1007/978-3-319-09761-9_5
dc.relation.ispartofseriesLecture Notes in Computer Science
dc.rights.uriN/A
dc.subjectKeyword spotting
dc.subjectLoglikelihood ratio normalization
dc.subjectPhonetic features
dc.subjectSpoken term detection
dc.titleAcoustic Similarity Scores for Keyword Spottingeng
dc.typeconference paper
dspace.entity.typePublication
oaire.citation.conferenceDate2014-10
oaire.citation.conferencePlaceSão Carlos, SP, Brasil
oaire.citation.endPage58
oaire.citation.startPage48
oaire.citation.titleComputational Processing of the Portuguese Language (PROPOR 2014)
oaire.citation.volume8775
oaire.versionhttp://purl.org/coar/version/c_970fb48d4fbd8a85
person.familyNameLopes
person.givenNameCarla
person.identifier.ciencia-idAF14-3048-F510
person.identifier.orcid0000-0002-5366-0016
relation.isAuthorOfPublication4dfbaf0a-8c0b-4eaf-b1ad-0e590a5f3524
relation.isAuthorOfPublication.latestForDiscovery4dfbaf0a-8c0b-4eaf-b1ad-0e590a5f3524

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura
Nome:
[abstract]Acoustic Similarity Scores for Keyword Spotting_.pdf
Tamanho:
268.41 KB
Formato:
Adobe Portable Document Format
Ver/Abrir
Licença
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
license.txt
Tamanho:
1.32 KB
Formato:
Item-specific license agreed upon to submission
Descrição:
Ver/Abrir

Coleções

ESTG - Comunicações em conferências e congressos internacionais