Applying EEND Diarization to Telephone Recordings from a Call Center

dc.contributor.authorZajíc, Zbyněk
dc.contributor.authorKunešová, Marie
dc.contributor.authorMüller, Luděk
dc.date.accessioned2022-03-28T10:00:28Z
dc.date.available2022-03-28T10:00:28Z
dc.date.issued2021
dc.description.abstract-translatedIn this paper, we focus on the issue of speaker diarization of data from a real call center. We have previously proposed a specialized solution to the problem, which employed additional knowledge about the identities of the phone operators (in our case, the language counselors from the Language Consulting Center), thus improving performance over the baseline. But a recent end-to-end diarization method, EEND, has since proven very successful on other data and was shown to surpass the previous state of the art in the field. Thus, we chose to compare this new method with our own previous approach. Using an existing implementation of the EEND method (adapted using a small amount of the target data from the Language Consulting Center), we successfully surpass the performance of our previous approach (17.42% vs. 19.39% DER), without the need for any additional information about speaker identities. The majority of the remaining diarization error of the EEND system is due to incorrect decisions between speech and silence, rather than speaker confusion. For comparison, we also show the results of a more standard diarization approach, represented by the method used in the Kaldi toolkit.en
dc.format11 s.cs
dc.format.mimetypeapplication/pdf
dc.identifier.citationZAJÍC, Z. KUNEŠOVÁ, M. MÜLLER, L. Applying EEND Diarization to Telephone Recordings from a Call Center. In 23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27–30, 2021, Proceedings. Cham: Springer, 2021. s. 807-817. ISBN: 978-3-030-87801-6 , ISSN: 0302-9743cs
dc.identifier.doi10.1007/978-3-030-87802-3_72
dc.identifier.isbn978-3-030-87801-6
dc.identifier.issn0302-9743
dc.identifier.obd43933458
dc.identifier.uri2-s2.0-85116359179
dc.identifier.urihttp://hdl.handle.net/11025/47255
dc.language.isoenen
dc.project.IDLM2018101/LINDAT/CLARIAH-CZ – Digitální výzkumná infrastruktura pro jazykové technologie, umění a humanitní vědycs
dc.project.ID90042/Velká výzkumná infrastruktura povinnost (J) - CESNET IIcs
dc.publisherSpringeren
dc.relation.ispartofseries23rd International Conference, SPECOM 2021, St. Petersburg, Russia, September 27–30, 2021, Proceedingsen
dc.rightsPlný text je přístupný v rámci univerzity přihlášeným uživatelům.cs
dc.rights© Springeren
dc.rights.accessrestrictedAccessen
dc.subject.translatedDiarizationen
dc.subject.translatedEnd-to-enden
dc.subject.translatedX-vectoren
dc.subject.translatedEENDen
dc.titleApplying EEND Diarization to Telephone Recordings from a Call Centeren
dc.typekonferenční příspěvekcs
dc.typeConferenceObjecten
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen

Files

Original bundle
Showing 1 - 1 out of 1 results
No Thumbnail Available
Name:
Zajíc2021_Chapter_ApplyingEENDDiarizationToTelep.pdf
Size:
377.54 KB
Format:
Adobe Portable Document Format