Attentional parallel RNNs for generating punctuation in transcribed speech

Mostra el registre complet Registre parcial de l'ítem

• dc.contributor.author Öktem, Alpca
• dc.contributor.author Farrús, Mireiaca
• dc.contributor.author Wanner, Leoca
• dc.date.accessioned 2018-02-20T11:30:28Z
• dc.date.available 2018-02-20T11:30:28Z
• dc.date.issued 2017
• dc.description.abstract Until very recently, the generation of punctuation marks for automatic speech recognition (ASR) output has been mostly done by looking at the syntactic structure of the recognized utterances. Prosodic cues such as breaks, speech rate, pitch intonation that influence placing of punctuation marks on speech transcripts have been seldom used. We propose a method that uses recurrent neural networks, taking prosodic and lexical information into account in order to predict punctuation marks for raw ASR output. Our experiments show that an attention mechanism over parallel sequences of prosodic cues aligned with transcribed speech improves accuracy of punctuation generation.
• dc.description.sponsorship We would like to thank Francesco Barbieri for offering his technical insights throughout this work. This work is part of the KRISTINA project, which has received funding from the European Union’s Horizon 2020 Research and Innovation Programme under the Grant Agreement number H2020-RIA-645012. The second author is partially funded by the Spanish Ministry of Economy, Industry and Competitiveness through the Ramón y Cajal program.
• dc.format.mimetype application/pdf
• dc.identifier.citation Öktem A, Farrús M, Wanner L. Attentional parallel RNNs for generating punctuation in transcribed speech. In: Camelin N, Estève Y, Martín-Vide C. Statistical Language and Speech Processing. 5th International Conference SLSP 2017; 2017 Oct 23-25; Le Mans, France. Cham: Springer, 2017. p. 131-42. (LNCS; no. 10583 ). DOI: 10.1007/978-3-319-68456-7_11
• dc.identifier.doi http://dx.doi.org/10.1007/978-3-319-68456-7_11
• dc.identifier.issn 0302-9743
• dc.identifier.uri http://hdl.handle.net/10230/33936
• dc.language.iso eng
• dc.publisher Springerca
• dc.relation.ispartof Camelin N, Estève Y, Martín-Vide C. Statistical Language and Speech Processing. 5th International Conference SLSP 2017; 2017 Oct 23-25; Le Mans, France. Cham: Springer, 2017. p. 131-42. (LNCS; no. 10583).
• dc.relation.isreferencedby http://hdl.handle.net/10230/33981
• dc.relation.isreferencedby http://hdl.handle.net/10230/33982
• dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/645012
• dc.rights © Springer The final publication is available at Springer via http://dx.doi.org/10.1007/978-3-319-68456-7_11
• dc.rights.accessRights info:eu-repo/semantics/openAccess
• dc.subject.keyword Speech transcription
• dc.subject.keyword Recurrent neural networks
• dc.subject.keyword Prosody
• dc.subject.keyword Punctuation generation
• dc.subject.keyword Automatic speech recognition
• dc.title Attentional parallel RNNs for generating punctuation in transcribed speechca
• dc.type info:eu-repo/semantics/conferenceObject
• dc.type.version info:eu-repo/semantics/acceptedVersion