A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets. Ghaemmaghami, H., Dean, D., & Sridharan, S. In 2014 22nd European Signal Processing Conference (EUSIPCO), pages 1272-1276, Sep., 2014.
Paper abstract bibtex In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.
@InProceedings{6952454,
author = {H. Ghaemmaghami and D. Dean and S. Sridharan},
booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},
title = {A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets},
year = {2014},
pages = {1272-1276},
abstract = {In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.},
keywords = {error statistics;iterative methods;speaker recognition;speaker rediarization scheme;two-speaker telephone datasets;two-speaker telephone conversation recordings;NIST 2008 SRE summed telephone corpora;intersession speaker information;diarization error rate;DER;Joining processes;Density estimation robust algorithm;Adaptation models;NIST;Measurement;Computational modeling;Hidden Markov models;Speaker rediarization;diarization;speaker linking;complete-linkage clustering;cross-likelihood ratio},
issn = {2076-1465},
month = {Sep.},
url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926145.pdf},
}
Downloads: 0
{"_id":"NGQb2SF88B6KmotXz","bibbaseid":"ghaemmaghami-dean-sridharan-aspeakerrediarizationschemeforimprovingdiarizationinlargetwospeakertelephonedatasets-2014","authorIDs":[],"author_short":["Ghaemmaghami, H.","Dean, D.","Sridharan, S."],"bibdata":{"bibtype":"inproceedings","type":"inproceedings","author":[{"firstnames":["H."],"propositions":[],"lastnames":["Ghaemmaghami"],"suffixes":[]},{"firstnames":["D."],"propositions":[],"lastnames":["Dean"],"suffixes":[]},{"firstnames":["S."],"propositions":[],"lastnames":["Sridharan"],"suffixes":[]}],"booktitle":"2014 22nd European Signal Processing Conference (EUSIPCO)","title":"A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets","year":"2014","pages":"1272-1276","abstract":"In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.","keywords":"error statistics;iterative methods;speaker recognition;speaker rediarization scheme;two-speaker telephone datasets;two-speaker telephone conversation recordings;NIST 2008 SRE summed telephone corpora;intersession speaker information;diarization error rate;DER;Joining processes;Density estimation robust algorithm;Adaptation models;NIST;Measurement;Computational modeling;Hidden Markov models;Speaker rediarization;diarization;speaker linking;complete-linkage clustering;cross-likelihood ratio","issn":"2076-1465","month":"Sep.","url":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926145.pdf","bibtex":"@InProceedings{6952454,\n author = {H. Ghaemmaghami and D. Dean and S. Sridharan},\n booktitle = {2014 22nd European Signal Processing Conference (EUSIPCO)},\n title = {A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets},\n year = {2014},\n pages = {1272-1276},\n abstract = {In this paper we propose a novel scheme for carrying out speaker diarization in an iterative manner. We aim to show that the information obtained through the first pass of speaker diarization can be reused to refine and improve the original diarization results. We call this technique speaker rediarization and demonstrate the practical application of our rediarization algorithm using a large archive of two-speaker telephone conversation recordings. We use the NIST 2008 SRE summed telephone corpora for evaluating our speaker rediarization system. This corpus contains recurring speaker identities across independent recording sessions that need to be linked across the entire corpus. We show that our speaker rediarization scheme can take advantage of inter-session speaker information, linked in the initial diarization pass, to achieve a 30% relative improvement over the original diarization error rate (DER) after only two iterations of rediarization.},\n keywords = {error statistics;iterative methods;speaker recognition;speaker rediarization scheme;two-speaker telephone datasets;two-speaker telephone conversation recordings;NIST 2008 SRE summed telephone corpora;intersession speaker information;diarization error rate;DER;Joining processes;Density estimation robust algorithm;Adaptation models;NIST;Measurement;Computational modeling;Hidden Markov models;Speaker rediarization;diarization;speaker linking;complete-linkage clustering;cross-likelihood ratio},\n issn = {2076-1465},\n month = {Sep.},\n url = {https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926145.pdf},\n}\n\n","author_short":["Ghaemmaghami, H.","Dean, D.","Sridharan, S."],"key":"6952454","id":"6952454","bibbaseid":"ghaemmaghami-dean-sridharan-aspeakerrediarizationschemeforimprovingdiarizationinlargetwospeakertelephonedatasets-2014","role":"author","urls":{"Paper":"https://www.eurasip.org/proceedings/eusipco/eusipco2014/html/papers/1569926145.pdf"},"keyword":["error statistics;iterative methods;speaker recognition;speaker rediarization scheme;two-speaker telephone datasets;two-speaker telephone conversation recordings;NIST 2008 SRE summed telephone corpora;intersession speaker information;diarization error rate;DER;Joining processes;Density estimation robust algorithm;Adaptation models;NIST;Measurement;Computational modeling;Hidden Markov models;Speaker rediarization;diarization;speaker linking;complete-linkage clustering;cross-likelihood ratio"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"inproceedings","biburl":"https://raw.githubusercontent.com/Roznn/EUSIPCO/main/eusipco2014url.bib","creationDate":"2021-02-13T17:43:41.681Z","downloads":0,"keywords":["error statistics;iterative methods;speaker recognition;speaker rediarization scheme;two-speaker telephone datasets;two-speaker telephone conversation recordings;nist 2008 sre summed telephone corpora;intersession speaker information;diarization error rate;der;joining processes;density estimation robust algorithm;adaptation models;nist;measurement;computational modeling;hidden markov models;speaker rediarization;diarization;speaker linking;complete-linkage clustering;cross-likelihood ratio"],"search_terms":["speaker","rediarization","scheme","improving","diarization","large","two","speaker","telephone","datasets","ghaemmaghami","dean","sridharan"],"title":"A speaker rediarization scheme for improving diarization in large two-speaker telephone datasets","year":2014,"dataSources":["A2ezyFL6GG6na7bbs","oZFG3eQZPXnykPgnE"]}