Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings

dc.contributor.authorŠvec, Jan
dc.contributor.authorŠmídl, Luboš
dc.contributor.authorPsutka, Josef
dc.contributor.authorPražák, Aleš
dc.date.accessioned2022-03-28T10:00:28Z
dc.date.available2022-03-28T10:00:28Z
dc.date.issued2021
dc.description.abstract-translatedThe paper describes a novel approach to Spoken Term Detection (STD) in large spoken archives using deep LSTM networks. The work is based on the previous approach of using Siamese neural networks for STD and naturally extends it to directly localize a spoken term and estimate its relevance score. The phoneme confusion network generated by a phoneme recognizer is processed by the deep LSTM network which projects each segment of the confusion network into an embedding space. The searched term is projected into the same embedding space using another deep LSTM network. The relevance score is then computed using a simple dot-product in the embedding space and calibrated using a sigmoid function to predict the probability of occurrence. The location of the searched term is then estimated from the sequence of output probabilities. The deep LSTM networks are trained in a self-supervised manner from paired recognition hypotheses on word and phoneme levels. The method is experimentally evaluated on MALACH data in English and Czech languages.en
dc.format5 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationŠVEC, J. ŠMÍDL, L. PSUTKA, J. PRAŽÁK, A. Spoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddings. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Red Hook, NY: International Speech Communication Association, 2021. s. 851-855. ISBN: 978-1-71383-690-2 , ISSN: 2308-457Xcs
dc.identifier.doi10.21437/Interspeech.2021-1704
dc.identifier.isbn978-1-71383-690-2
dc.identifier.issn2308-457X
dc.identifier.obd43933416
dc.identifier.uri2-s2.0-85119207187
dc.identifier.urihttp://hdl.handle.net/11025/47251
dc.language.isoenen
dc.project.IDVJ01010108/Robustní zpracování nahrávek pro operativu a bezpečnostcs
dc.project.ID90140/Velká výzkumná infrastruktura_(J) - e-INFRA CZcs
dc.publisherInternational Speech Communication Associationen
dc.relation.ispartofseriesProceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECHen
dc.rightsPlný text není přístupný.cs
dc.rights© ISCAen
dc.rights.accessclosedAccessen
dc.subject.translatedspoken term detectionen
dc.subject.translatedrelevance-score estimationen
dc.subject.translatedspeech embeddingsen
dc.titleSpoken Term Detection and Relevance Score Estimation Using Dot-Product of Pronunciation Embeddingsen
dc.typekonferenční příspěvekcs
dc.typeConferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
svec21_interspeech.pdf
Size:
307.53 KB
Format:
Adobe Portable Document Format