Show simple record

dc.contributor.authorSharifzadeh, Hamid
dc.contributor.authorHajiRassouliha, Amir
dc.contributor.authorMcLoughlin, I.V.
dc.contributor.authorArdekani, Iman
dc.contributor.authorAllen, Jacqueline E.
dc.date.accessioned2016-04-29T22:33:29Z
dc.date.available2016-04-29T22:33:29Z
dc.date.issued2015-12
dc.identifier.urihttps://hdl.handle.net/10652/3352
dc.description.abstractComputational speech reconstruction algorithms have the ultimate aim of returning natural sounding speech to aphonic and dysphonic individuals. These algorithms can also be used by unimpaired speakers for communicating sensitive or private information. When the glottis loses function due to disease or surgery, aphonic and dysphonic patients retain the power of vocal tract modulation to some degree but they are unable to speak anything more than hoarse whispers without prosthetic aid. While whispering can be seen as a natural and secondary aspect of speech communications for most people, it becomes the primary mechanism of communications for those who have impaired voice production mechanisms, such as laryngectomees. In this paper, by considering the current limitations of speech reconstruction methods, a novel algorithm for converting whispers to normal speech is proposed and the efficiency of the algorithm is discussed. The proposed algorithm relies upon twin mapping models and makes use of artificially generated whispers (called whisperised speech) to regenerate natural phonated speech from whispers. Through a training-based approach, the mapping models exploit whisperised speech to overcome frame to frame time alignment problem in the speech reconstruction process.en_NZ
dc.language.isoenen_NZ
dc.publisherIEEE Communications Societyen_NZ
dc.relation.urihttp://ece.adu.ac.ae/ISSPIT2015/index.htmlen_NZ
dc.subjectspeech reconstructionen_NZ
dc.subjectimpaired speechen_NZ
dc.subjectaphonic patientsen_NZ
dc.subjectdysphonic patientsen_NZ
dc.subjectvoice productionen_NZ
dc.subjectcomputational speech reconstruction algorithmsen_NZ
dc.titlePhonated speech reconstruction using twin mapping modelsen_NZ
dc.typeConference Contribution - Paper in Published Proceedingsen_NZ
dc.rights.holderIEEE Communications Societyen_NZ
dc.subject.marsden200402 Computational Linguisticsen_NZ
dc.identifier.bibliographicCitationSharifzadeh, H. R., HajiRassouliha, A., McLoughlin, I. V., Ardekani, I. T., & Allen, J. E. (2015, December) Phonated Speech Reconstruction Using Twin Mapping Models. IEEE (Ed.), Proceedings of the 15th IEEE International Symposium on Signal Processing and Information Technology (pp.1-6)en_NZ
unitec.institutionUnitec Institute of Technologyen_NZ
unitec.institutionUniversity of Kent (Kent, United Kingdom)en_NZ
unitec.institutionNorth Shore Hospital (Auckland, N.Z.)en_NZ
unitec.publication.titleProceedings 15th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2015)en_NZ
unitec.conference.title15th IEEE International Symposium on Signal Processing and Information Technology (ISSPIT 2015)en_NZ
unitec.conference.orgIEEE Signal Processing Societyen_NZ
unitec.conference.orgIEEE Computer Societyen_NZ
unitec.conference.locationAbu Dhabi (United Arab Emirates)en_NZ
unitec.conference.sdate2015-12-07
unitec.conference.edate2015-12-10
unitec.peerreviewedyesen_NZ
dc.contributor.affiliationUnitec Institute of Technologyen_NZ
dc.contributor.affiliationUniversity of Kenten_NZ
dc.contributor.affiliationNorth Shore Hospital (Auckland N.Z.)en_NZ
unitec.identifier.roms58296en_NZ
unitec.identifier.roms58529
unitec.institution.studyareaComputing


Files in this item

Thumbnail

This item appears in

Show simple record


© Unitec Institute of Technology, Private Bag 92025, Victoria Street West, Auckland 1142