Show simple item record

dc.contributor.authorShulz, Henrik
dc.contributor.authorRodríguez Fonollosa, José Adrián
dc.contributor.otherUniversitat Politècnica de Catalunya. Departament de Teoria del Senyal i Comunicacions
dc.date.accessioned2013-09-25T13:06:43Z
dc.date.available2013-09-25T13:06:43Z
dc.date.created2013
dc.date.issued2013
dc.identifier.citationShulz, H.; Fonollosa, José A. R. Modelling the effects of spontaneous speech in speech recognition. A: Speech Processing Conference. "2013 Speech Processing Conference: conference proceedings: July 1-2, 2013: AFEKA, Tel-Aviv Academic College of Engineering". Tel-Aviv: 2013.
dc.identifier.urihttp://hdl.handle.net/2117/20204
dc.description.abstractIntrinsic variability of the speaker in spontaneous speech remains a challenge to state of the art Automatic speech recognition (ASR). While planned speech exhibits a moderate variability, the significant variability of spontaneous speech is caused by situation, context, intention, emotion and listeners. This conditioning of speech is observable in terms of speaking rate and in feature space. We analysed broadcast news (BN) and broadcast conversational (BC) speech in terms of phoneme rate (PR) and feature space reduction (FSR), and contrasted both with the planned speech data. Strong statistically significant differences were revealed. We cluster the speech segments with respect to their degree of PR and FSR forming a set of variability classes, and induce the variability classes into the Hidden-Markov-Model (HMM) based acoustic model (AM). In recognition we follow two approaches: the first considers the variability class as context variable, the second relies on prior estimation of the variability class after the first pass of a multi-pass recognition system. Beside explicit modelling of the intrinsic speech variability of the speaker, we furthermore segregate the general speaker specific characteristics by means of speaker adaptive training (SAT) into feature space transforms using ConstrainedMaximumLikelihood Linear Regression (CMLLR), and apply the adaptive approach in third pass recognition. By approaching to model both within speaker variation and between speaker variation in spontaneous speech, we address two fundamental sources of speech variability that determine the performance of ASR systems.
dc.language.isoeng
dc.rightsAttribution-NonCommercial-NoDerivs 3.0 Spain
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subjectÀrees temàtiques de la UPC::Enginyeria de la telecomunicació::Processament del senyal::Processament de la parla i del senyal acústic
dc.subject.lcshAutomatic speech recognition
dc.titleModelling the effects of spontaneous speech in speech recognition
dc.typeConference report
dc.subject.lemacReconeixement automàtic de la parla
dc.contributor.groupUniversitat Politècnica de Catalunya. VEU - Grup de Tractament de la Parla
dc.description.peerreviewedPeer Reviewed
dc.relation.publisherversionhttps://events.eventact.com/afeka/aclp2012/Modelling%20the%20Effects%20of%20Spontaneous%20Speech%20in%20Speech%20Recognition_Schulz%20et%20al.pdf
dc.rights.accessOpen Access
drac.iddocument12674265
dc.description.versionPostprint (published version)
upcommons.citation.authorShulz, H.; Fonollosa, José A. R.
upcommons.citation.contributorSpeech Processing Conference
upcommons.citation.pubplaceTel-Aviv
upcommons.citation.publishedtrue
upcommons.citation.publicationName2013 Speech Processing Conference: conference proceedings: July 1-2, 2013: AFEKA, Tel-Aviv Academic College of Engineering


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record

Except where otherwise noted, content on this work is licensed under a Creative Commons license: Attribution-NonCommercial-NoDerivs 3.0 Spain