DC Field | Value | Language |
---|---|---|
dc.contributor.author | Jung, Youngmoon | ko |
dc.contributor.author | Eom, Youngsik | ko |
dc.contributor.author | Lee, Yeonghyeon | ko |
dc.contributor.author | Kim, Hoirin | ko |
dc.date.accessioned | 2021-10-31T06:43:48Z | - |
dc.date.available | 2021-10-31T06:43:48Z | - |
dc.date.created | 2021-10-31 | - |
dc.date.created | 2021-10-31 | - |
dc.date.created | 2021-10-31 | - |
dc.date.created | 2021-10-31 | - |
dc.date.created | 2021-10-31 | - |
dc.date.issued | 2021-09 | - |
dc.identifier.citation | JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA, v.40, no.5, pp.496 - 502 | - |
dc.identifier.issn | 1225-4428 | - |
dc.identifier.uri | http://hdl.handle.net/10203/288484 | - |
dc.description.abstract | Recently, deep speaker embedding approach has been widely used in text-independent speaker verification, which shows better performance than the traditional i-vector approach. In this work, to improve the deep speaker embedding approach, we propose a novel method called group-based speaker embedding which incorporates group information. We cluster all speakers of the training data into a predefined number of groups in an unsupervised manner, so that a fixed-length group embedding represents the corresponding group. A Group Decision Network (GDN) produces a group weight, and an aggregated group embedding is generated from the weighted sum of the group embeddings and the group weights. Finally, we generate a group-based embedding by adding the aggregated group embedding to the deep speaker embedding. In this way, a speaker embedding can reduce the search space of the speaker identity by incorporating group information, and thereby can flexibly represent a significant number of speakers. We conducted experiments using the VoxCeleb1 database to show that our proposed approach can improve the previous approaches. | - |
dc.language | Korean | - |
dc.publisher | ACOUSTICAL SOC KOREA | - |
dc.title | Group-based speaker embeddings for text-independent speaker verification | - |
dc.title.alternative | 문장 독립 화자 검증을 위한 그룹기반 화자 임베딩 | - |
dc.type | Article | - |
dc.identifier.scopusid | 2-s2.0-85124827123 | - |
dc.type.rims | ART | - |
dc.citation.volume | 40 | - |
dc.citation.issue | 5 | - |
dc.citation.beginningpage | 496 | - |
dc.citation.endingpage | 502 | - |
dc.citation.publicationname | JOURNAL OF THE ACOUSTICAL SOCIETY OF KOREA | - |
dc.identifier.doi | 10.7776/ASK.2021.40.5.496 | - |
dc.identifier.kciid | ART002761148 | - |
dc.contributor.localauthor | Kim, Hoirin | - |
dc.description.isOpenAccess | Y | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | Deep speaker embedding | - |
dc.subject.keywordAuthor | Group-based speaker embedding | - |
dc.subject.keywordAuthor | Text-independent speaker verification | - |
dc.subject.keywordAuthor | Clustering | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.