Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer

dc.contributor.authorŠvec, Jan
dc.contributor.authorLehečka, Jan
dc.contributor.authorŠmídl, Luboš
dc.date.accessioned2023-01-30T11:00:27Z
dc.date.available2023-01-30T11:00:27Z
dc.date.issued2022
dc.description.abstract-translatedIn recent years, the standard hybrid DNN-HMM speech recognizers are outperformed by the end-to-end speech recognition systems. One of the very promising approaches is the grapheme Wav2Vec 2.0 model, which uses the self-supervised pretraining approach combined with transfer learning of the fine-tuned speech recognizer. Since it lacks the pronunciation vocabulary and language model, the approach is suitable for tasks where obtaining such models is not easy or almost impossible. In this paper, we use the Wav2Vec speech recognizer in the task of spoken term detection over a large set of spoken documents. The method employs a deep LSTM network which maps the recognized hypothesis and the searched term into a shared pronunciation embedding space in which the term occurrences and the assigned scores are easily computed. The paper describes a bootstrapping approach that allows the transfer of the knowledge contained in traditional pronunciation vocabulary of DNN-HMM hybrid ASR into the context of grapheme-based Wav2Vec. The proposed method outperforms the previously published system based on the combination of the DNN-HMM hybrid ASR and phoneme recognizer by a large margin on the MALACH data in both English and Czech languages.en
dc.format5 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationŠVEC, J. LEHEČKA, J. ŠMÍDL, L. Deep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizer. In Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. New York: International Speech Communication Association, 2022. s. 1886-1890. ISBN: neuvedeno , ISSN: 2308-457Xcs
dc.identifier.doi10.21437/Interspeech.2022-10409
dc.identifier.isbnneuvedeno
dc.identifier.issn2308-457X
dc.identifier.obd43936704
dc.identifier.uri2-s2.0-85140064214
dc.identifier.urihttp://hdl.handle.net/11025/51162
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© 2022 ISCAen
dc.rights.accessclosedAccessen
dc.subject.translatedSpoken Term Detection, Wav2Vecen
dc.titleDeep LSTM Spoken Term Detection using Wav2Vec 2.0 Recognizeren
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:
Svec_Lehecka_Smidl-Deep_LSTM_Interspeech_2022.pdf
Size:
405.58 KB
Format:
Adobe Portable Document Format