Publication: Comparison of spectrum estimators in speaker verification: Mismatch conditions induced by vocal effort
dc.contributor.author | Kinnunen, Tomi | |
dc.contributor.author | Rajan, Padmanabhan | |
dc.contributor.author | Pohjalainen, Jouni | |
dc.contributor.author | Alku, Paavo | |
dc.contributor.author | Bimbot, F. | |
dc.contributor.author | Cerisara, C. | |
dc.contributor.author | Fougeron, C. | |
dc.contributor.author | Gravier, G. | |
dc.contributor.author | Lamel, L. | |
dc.contributor.author | Pellegrino, F. | |
dc.contributor.author | Perrier, P. | |
dc.contributor.buuauthor | Hanilçi, Cemal | |
dc.contributor.buuauthor | Ertaş, Figen | |
dc.contributor.department | Mühendislik Fakültesi | |
dc.contributor.department | Elektrik ve Elektronik Mühendisliği Bölümü | |
dc.contributor.researcherid | AAH-4188-2021 | |
dc.contributor.researcherid | S-4967-2016 | |
dc.contributor.scopusid | 35781455400 | |
dc.contributor.scopusid | 24724154500 | |
dc.date.accessioned | 2023-05-09T11:34:10Z | |
dc.date.available | 2023-05-09T11:34:10Z | |
dc.date.issued | 2013 | |
dc.description | Bu çalışma, 25-29 Ağustos 2013 tarihleri arasında Lyon[Fransa]’da düzenlenen 14. Annual Conference of the International-Speech-Communication-Association (INTERSPEECH 2013)’da bildiri olarak sunulmuştur. | |
dc.description.abstract | We study the problem of vocal effort mismatch in speaker verification. Changes in speaker's vocal effort induce changes in fundamental frequency (F0) and formant structure which introduce unwanted intra-speaker variations to features. We compare seven alternative spectrum estimators in the context of melfrequency cepstral coefficient (MFCC) extraction for speaker verification. The compared variants include traditional FFT spectrum and six parametric all-pole models. Experimental results on the NIST 2010 speaker recognition evaluation (SRE) corpus utilizing both GMM-UBM and more recent GMM supervector classifier indicate that spectrum estimation has a considerable impact on speaker verification accuracy under mismatched vocal effort conditions. The highest recognition accuracy was achieved using a particular variant of temporally weighted all-pole model, stabilized weighted linear prediction (SWLP). | |
dc.description.sponsorship | Academy of Finland (253120) | |
dc.description.sponsorship | Int Speech Commun Assoc | |
dc.description.sponsorship | Europa org | |
dc.description.sponsorship | Amazon | |
dc.description.sponsorship | Microsoft | |
dc.description.sponsorship | ||
dc.description.sponsorship | TcL SYTRAL | |
dc.description.sponsorship | European Language Resources Assoc | |
dc.description.sponsorship | Ouaero | |
dc.description.sponsorship | Imaginove | |
dc.description.sponsorship | VOCAPIA res | |
dc.description.sponsorship | Acapela | |
dc.description.sponsorship | Speech ocean | |
dc.description.sponsorship | ALDEBARAN | |
dc.description.sponsorship | Orange | |
dc.description.sponsorship | Vecsys | |
dc.description.sponsorship | IBM Res | |
dc.description.sponsorship | Raytheon BBN Technol | |
dc.description.sponsorship | Voxygen | |
dc.identifier.citation | Hanilçi, C. vd. (2013). “Comparison of spectrum estimators in speaker verification: Mismatch conditions induced by vocal effort”. Interspeech, 14th Annual Conference of the International Speech Communication Association, 1-5, 2880-2884. | |
dc.identifier.endpage | 2884 | |
dc.identifier.issn | 2308-457X | |
dc.identifier.issn | 978-1-62993-443-3 | |
dc.identifier.scopus | 2-s2.0-84906242097 | |
dc.identifier.startpage | 2880 | |
dc.identifier.uri | http://hdl.handle.net/11452/32597 | |
dc.identifier.volume | 1-5 | |
dc.identifier.wos | 000395050001119 | |
dc.indexed.wos | CPCIS | |
dc.language.iso | en | |
dc.publisher | Isca-Int Speech Communication Assoc | |
dc.relation.collaboration | Yurt dışı | |
dc.relation.journal | Interspeech, 14th Annual Conference of the International Speech Communication Association | |
dc.relation.publicationcategory | Konferans Öğesi - Uluslararası | |
dc.rights | info:eu-repo/semantics/closedAccess | |
dc.subject | Computer science | |
dc.subject | Engineering | |
dc.subject | Speaker recognition | |
dc.subject | Vocal effort mismatch | |
dc.subject | Spectrum estimation | |
dc.subject | Linear Prediction | |
dc.subject | Models | |
dc.subject | Poles | |
dc.subject | Spectrum analysis | |
dc.subject | Fundamental frequencies | |
dc.subject | Mel-frequency cepstral coefficients | |
dc.subject | Recognition accuracy | |
dc.subject | Speaker recognition | |
dc.subject | Speaker recognition evaluations | |
dc.subject | Speaker verification | |
dc.subject | Spectrum estimation | |
dc.subject | Vocal efforts | |
dc.subject | Speech recognition | |
dc.subject.scopus | Speech Recognition; Language Recognition; Utterance | |
dc.subject.wos | Computer science, artificial intelligence | |
dc.subject.wos | Engineering, electrical & electronic | |
dc.title | Comparison of spectrum estimators in speaker verification: Mismatch conditions induced by vocal effort | |
dc.type | Proceedings Paper | |
dc.wos.quartile | Q2 | |
dspace.entity.type | Publication | |
local.contributor.department | Mühendislik Fakültesi/Elektrik ve Elektronik Mühendisliği Bölümü | |
local.indexed.at | Scopus | |
local.indexed.at | WOS |
Files
License bundle
1 - 1 of 1
- Name:
- license.txt
- Size:
- 1.71 KB
- Format:
- Item-specific license agreed upon to submission
- Description: