1. OAR@UM
  2. Faculty of Information and Communication Technology
  3. Department of Microelectronics and Nanoelectronics
  4. Scholarly Works - FacICTMN
Please use this identifier to cite or link to this item: https://www.um.edu.mt/library/oar/handle/123456789/17804
Full metadata record
DC FieldValueLanguage
dc.contributor.authorCutajar, Michelle-
dc.contributor.authorGatt, Edward-
dc.contributor.authorGrech, Ivan-
dc.contributor.authorCasha, Owen-
dc.contributor.authorMicallef, Joseph-
dc.date.accessioned2017-03-25T17:03:35Z-
dc.date.available2017-03-25T17:03:35Z-
dc.date.issued2011-
dc.identifier.citationCutajar, M., Gatt, E., Grech, I., Casha, O., & Micallef, J. (2012). Support vector machines with the priorities method for speaker independent phoneme recognition. IEEE International Symposium on Signal Processing and Information Technology (ISSPIT), Bilbao. 409-414.en_GB
dc.identifier.urihttps://www.um.edu.mt/library/oar//handle/123456789/17804-
dc.description.abstractA speaker independent phoneme recognition system, based on Support Vector Machines (SVMs) method was improved by adding a priority scheme to forecast the three most likely phonemes. The system helps improve the obtained recognitions rate . For the phoneme recognition system, four multiclass SVMs methods, the All- at-once, One-against-all, One-against-one, and the Directed Acyclic Graph SVM (DAGSVM), were designed. The One-against-one method performed best, achieving an accuracy of 53.70%. This accuracy was further increased to 75.41%, when the second and third priorities were considered in the priorities method. All tests were carried out on the TIMIT database.en_GB
dc.language.isoenen_GB
dc.publisherInstitute of Electrical and Electronics Engineers Inc.en_GB
dc.rightsinfo:eu-repo/semantics/restrictedAccessen_GB
dc.subjectSupport vector machinesen_GB
dc.subjectAutomatic speech recognitionen_GB
dc.subjectWavelets (Mathematics)en_GB
dc.subjectKernel functionsen_GB
dc.subjectDirected graphsen_GB
dc.titleSupport vector machines with the priorities method for speaker independent phoneme recognitionen_GB
dc.typeconferenceObjecten_GB
dc.rights.holderThe copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder.en_GB
dc.bibliographicCitation.conferencenameIEEE International Symposium on Signal Processing and Information Technology (ISSPIT)en_GB
dc.bibliographicCitation.conferenceplaceBilbao, Spain, 14-17/12/2011en_GB
dc.description.reviewedpeer-revieweden_GB
dc.identifier.doi10.1109/ISSPIT.2011.6151597-
Appears in Collections:Scholarly Works - FacICTMN

Files in This Item:
File Description SizeFormat 
Support Vector Machines with the Priorities Method for Speaker Independent Phoneme Recognition.pdf
  Restricted Access		Support vector machines with the priorities method for speaker independent phoneme recognition2.17 MBAdobe PDFView/Open Request a copy
Show simple item record Statistics


Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.