Performance Analysis of Speaker Features Extracted from High-order Fractional Domains
An evaluation of the feature set of the vector difference(VD) based on fractional cosine and sine transform focusing on the high-order fractional domains for text-independent speaker recognition is elucidated in this paper. The experiments have been done following the principles varying the number o...
Bewaard in:
| Hoofdauteur: | |
|---|---|
| Andere auteurs: | |
| Formaat: | article |
| Taal: | eng |
| Gepubliceerd in: |
2007
|
| Onderwerpen: | |
| Online toegang: | http://bibdigital.epn.edu.ec/handle/15000/9288 |
| Tags: |
Voeg label toe
Geen labels, Wees de eerste die dit record labelt!
|
Voeg label toe | _version_ | 1827332047323004928 |
|---|---|
| author | Jinfang, Wang |
| author2 | Jinbao, Wang |
| author2_role | author |
| author_facet | Jinfang, Wang Jinbao, Wang |
| author_role | author |
| collection | Repositorio Escuela Politécnica Nacional |
| dc.creator.none.fl_str_mv | Jinfang, Wang Jinbao, Wang |
| dc.date.none.fl_str_mv | 2007-03-21T15:20:04Z 2007-03-21T15:20:04Z 2007-03-21T15:20:04Z 2010-09-07T16:32:45Z 2010-09-07T16:32:45Z 2011-03-10T14:33:29Z 2011-03-10T14:33:29Z |
| dc.identifier.none.fl_str_mv | http://bibdigital.epn.edu.ec/handle/15000/9288 |
| dc.language.none.fl_str_mv | eng |
| dc.rights.none.fl_str_mv | https://creativecommons.org/licenses/by-nc-nd/4.0/ info:eu-repo/semantics/openAccess |
| dc.source.none.fl_str_mv | reponame:Repositorio Escuela Politécnica Nacional instname:Escuela Politécnica Nacional instacron:EPN |
| dc.subject.none.fl_str_mv | RECONOCIMIENTO DEL HABLA SPEECH RECOGNITION |
| dc.title.none.fl_str_mv | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| dc.type.none.fl_str_mv | info:eu-repo/semantics/publishedVersion info:eu-repo/semantics/article |
| description | An evaluation of the feature set of the vector difference(VD) based on fractional cosine and sine transform focusing on the high-order fractional domains for text-independent speaker recognition is elucidated in this paper. The experiments have been done following the principles varying the number of the vector dimension and the power of the output parameters of fractional cosine and sine transform separately. The recognition results show that when the order of primary fractional domain is fixed to be 1 and the one of secondary fractional domain is 0.98, the correct recognition rate of the VD feature matches the one of the previous MFCC feature. |
| eu_rights_str_mv | openAccess |
| format | article |
| id | EPN_2f4df2d59ac3bc3af11e962fe1350120 |
| instacron_str | EPN |
| institution | EPN |
| instname_str | Escuela Politécnica Nacional |
| language | eng |
| network_acronym_str | EPN |
| network_name_str | Repositorio Escuela Politécnica Nacional |
| oai_identifier_str | oai:bibdigital.epn.edu.ec:15000/9288 |
| publishDate | 2007 |
| reponame_str | Repositorio Escuela Politécnica Nacional |
| repository.mail.fl_str_mv | . |
| repository.name.fl_str_mv | Repositorio Escuela Politécnica Nacional - Escuela Politécnica Nacional |
| repository_id_str | 1553 |
| rights_invalid_str_mv | https://creativecommons.org/licenses/by-nc-nd/4.0/ |
| spelling | Performance Analysis of Speaker Features Extracted from High-order Fractional DomainsJinfang, WangJinbao, WangRECONOCIMIENTO DEL HABLASPEECH RECOGNITIONAn evaluation of the feature set of the vector difference(VD) based on fractional cosine and sine transform focusing on the high-order fractional domains for text-independent speaker recognition is elucidated in this paper. The experiments have been done following the principles varying the number of the vector dimension and the power of the output parameters of fractional cosine and sine transform separately. The recognition results show that when the order of primary fractional domain is fixed to be 1 and the one of secondary fractional domain is 0.98, the correct recognition rate of the VD feature matches the one of the previous MFCC feature.2007-03-21T15:20:04Z2010-09-07T16:32:45Z2011-03-10T14:33:29Z2007-03-21T15:20:04Z2010-09-07T16:32:45Z2011-03-10T14:33:29Z2007-03-21T15:20:04Zinfo:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articlehttp://bibdigital.epn.edu.ec/handle/15000/9288enghttps://creativecommons.org/licenses/by-nc-nd/4.0/info:eu-repo/semantics/openAccessreponame:Repositorio Escuela Politécnica Nacionalinstname:Escuela Politécnica Nacionalinstacron:EPN2019-04-07T19:12:26Zoai:bibdigital.epn.edu.ec:15000/9288Institucionalhttps://bibdigital.epn.edu.ec/Universidad públicahttps://www.epn.edu.ec/https://bibdigital.epn.edu.ec/oai.Ecuador...opendoar:15532019-04-07T19:12:26Repositorio Escuela Politécnica Nacional - Escuela Politécnica Nacionalfalse |
| spellingShingle | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains Jinfang, Wang RECONOCIMIENTO DEL HABLA SPEECH RECOGNITION |
| status_str | publishedVersion |
| title | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| title_full | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| title_fullStr | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| title_full_unstemmed | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| title_short | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| title_sort | Performance Analysis of Speaker Features Extracted from High-order Fractional Domains |
| topic | RECONOCIMIENTO DEL HABLA SPEECH RECOGNITION |
| url | http://bibdigital.epn.edu.ec/handle/15000/9288 |