The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Nesta carta, um algoritmo de agrupamento proposto recentemente denominado propagação de afinidade é apresentado para a tarefa de agrupamento de falantes. Este novo algoritmo exibe rápida velocidade de execução e encontra clusters com baixo erro. No entanto, experimentos mostram que a pureza do alto-falante na propagação de afinidade não é satisfatória. Assim, propomos uma abordagem híbrida que combina propagação de afinidade com agrupamento hierárquico aglomerativo para melhorar o desempenho do agrupamento. Experimentos mostram que, comparado ao agrupamento hierárquico aglomerativo tradicional, o método híbrido alcança melhor desempenho nos corpora de teste.
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Xiang ZHANG, Ping LU, Hongbin SUO, Qingwei ZHAO, Yonghong YAN, "Robust Speaker Clustering Using Affinity Propagation" in IEICE TRANSACTIONS on Information,
vol. E91-D, no. 11, pp. 2739-2741, November 2008, doi: 10.1093/ietisy/e91-d.11.2739.
Abstract: In this letter, a recently proposed clustering algorithm named affinity propagation is introduced for the task of speaker clustering. This novel algorithm exhibits fast execution speed and finds clusters with low error. However, experiments show that the speaker purity of affinity propagation is not satisfying. Thus, we propose a hybrid approach that combines affinity propagation with agglomerative hierarchical clustering to improve the clustering performance. Experiments show that compared with traditional agglomerative hierarchical clustering, the hybrid method achieves better performance on the test corpora.
URL: https://global.ieice.org/en_transactions/information/10.1093/ietisy/e91-d.11.2739/_p
Copiar
@ARTICLE{e91-d_11_2739,
author={Xiang ZHANG, Ping LU, Hongbin SUO, Qingwei ZHAO, Yonghong YAN, },
journal={IEICE TRANSACTIONS on Information},
title={Robust Speaker Clustering Using Affinity Propagation},
year={2008},
volume={E91-D},
number={11},
pages={2739-2741},
abstract={In this letter, a recently proposed clustering algorithm named affinity propagation is introduced for the task of speaker clustering. This novel algorithm exhibits fast execution speed and finds clusters with low error. However, experiments show that the speaker purity of affinity propagation is not satisfying. Thus, we propose a hybrid approach that combines affinity propagation with agglomerative hierarchical clustering to improve the clustering performance. Experiments show that compared with traditional agglomerative hierarchical clustering, the hybrid method achieves better performance on the test corpora.},
keywords={},
doi={10.1093/ietisy/e91-d.11.2739},
ISSN={1745-1361},
month={November},}
Copiar
TY - JOUR
TI - Robust Speaker Clustering Using Affinity Propagation
T2 - IEICE TRANSACTIONS on Information
SP - 2739
EP - 2741
AU - Xiang ZHANG
AU - Ping LU
AU - Hongbin SUO
AU - Qingwei ZHAO
AU - Yonghong YAN
PY - 2008
DO - 10.1093/ietisy/e91-d.11.2739
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E91-D
IS - 11
JA - IEICE TRANSACTIONS on Information
Y1 - November 2008
AB - In this letter, a recently proposed clustering algorithm named affinity propagation is introduced for the task of speaker clustering. This novel algorithm exhibits fast execution speed and finds clusters with low error. However, experiments show that the speaker purity of affinity propagation is not satisfying. Thus, we propose a hybrid approach that combines affinity propagation with agglomerative hierarchical clustering to improve the clustering performance. Experiments show that compared with traditional agglomerative hierarchical clustering, the hybrid method achieves better performance on the test corpora.
ER -