A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data. Tawara, N., Ogawa, T., Watanabe, S., Nakamura, A., & Kobayashi, T. APSIPA Transactions on Signal and Information Processing, 2015.
![A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data [pdf]](https://bibbase.org/img/filetypes/pdf.svg "pdf")
Paper doi abstract bibtex
Paper doi abstract bibtex An infinite mixture model is applied to model-based speaker clustering with sampling-based optimization to make it possible to estimate the number of speakers. For this purpose, a framework of non-parametric Bayesian modeling is implemented with the Markov chain Monte Carlo and incorporated in the utterance-oriented speaker model. The proposed model is called the utterance-oriented Dirichlet process mixture model (UO-DPMM). The present paper demonstrates that UO-DPMM is successfully applied on large-scale data and outperforms the conventional hierarchical agglomerative clustering, especially for large amounts of utterances.
@article{
title = {A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data},
type = {article},
year = {2015},
keywords = {Gibbs sampling,Non-parametric Bayesian model,Sampling approach,Speaker clustering,Utterance-oriented Dirichlet process mixture model},
volume = {4},
id = {cbbf79c3-241e-3029-87be-da58bb27f3ba},
created = {2022-09-19T10:49:11.236Z},
file_attached = {true},
profile_id = {276016a7-2c9d-3507-8888-093db7c54774},
group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},
last_modified = {2022-09-19T10:49:45.966Z},
read = {false},
starred = {false},
authored = {false},
confirmed = {true},
hidden = {false},
folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},
private_publication = {false},
abstract = {An infinite mixture model is applied to model-based speaker clustering with sampling-based optimization to make it possible to estimate the number of speakers. For this purpose, a framework of non-parametric Bayesian modeling is implemented with the Markov chain Monte Carlo and incorporated in the utterance-oriented speaker model. The proposed model is called the utterance-oriented Dirichlet process mixture model (UO-DPMM). The present paper demonstrates that UO-DPMM is successfully applied on large-scale data and outperforms the conventional hierarchical agglomerative clustering, especially for large amounts of utterances.},
bibtype = {article},
author = {Tawara, Naohiro and Ogawa, Tetsuji and Watanabe, Shinji and Nakamura, Atsushi and Kobayashi, Tetsunori},
doi = {10.1017/ATSIP.2015.19},
journal = {APSIPA Transactions on Signal and Information Processing}
}Downloads: 0
{"_id":"4LsyAmfrvLTPDoD5o","bibbaseid":"tawara-ogawa-watanabe-nakamura-kobayashi-asamplingbasedspeakerclusteringusingutteranceorienteddirichletprocessmixturemodelanditsevaluationonlargescaledata-2015","author_short":["Tawara, N.","Ogawa, T.","Watanabe, S.","Nakamura, A.","Kobayashi, T."],"bibdata":{"title":"A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data","type":"article","year":"2015","keywords":"Gibbs sampling,Non-parametric Bayesian model,Sampling approach,Speaker clustering,Utterance-oriented Dirichlet process mixture model","volume":"4","id":"cbbf79c3-241e-3029-87be-da58bb27f3ba","created":"2022-09-19T10:49:11.236Z","file_attached":"true","profile_id":"276016a7-2c9d-3507-8888-093db7c54774","group_id":"5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1","last_modified":"2022-09-19T10:49:45.966Z","read":false,"starred":false,"authored":false,"confirmed":"true","hidden":false,"folder_uuids":"02fb5526-03ff-44ad-8d5c-42bd496c3100","private_publication":false,"abstract":"An infinite mixture model is applied to model-based speaker clustering with sampling-based optimization to make it possible to estimate the number of speakers. For this purpose, a framework of non-parametric Bayesian modeling is implemented with the Markov chain Monte Carlo and incorporated in the utterance-oriented speaker model. The proposed model is called the utterance-oriented Dirichlet process mixture model (UO-DPMM). The present paper demonstrates that UO-DPMM is successfully applied on large-scale data and outperforms the conventional hierarchical agglomerative clustering, especially for large amounts of utterances.","bibtype":"article","author":"Tawara, Naohiro and Ogawa, Tetsuji and Watanabe, Shinji and Nakamura, Atsushi and Kobayashi, Tetsunori","doi":"10.1017/ATSIP.2015.19","journal":"APSIPA Transactions on Signal and Information Processing","bibtex":"@article{\n title = {A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data},\n type = {article},\n year = {2015},\n keywords = {Gibbs sampling,Non-parametric Bayesian model,Sampling approach,Speaker clustering,Utterance-oriented Dirichlet process mixture model},\n volume = {4},\n id = {cbbf79c3-241e-3029-87be-da58bb27f3ba},\n created = {2022-09-19T10:49:11.236Z},\n file_attached = {true},\n profile_id = {276016a7-2c9d-3507-8888-093db7c54774},\n group_id = {5ec9cc91-a5d6-3de5-82f3-3ef3d98a89c1},\n last_modified = {2022-09-19T10:49:45.966Z},\n read = {false},\n starred = {false},\n authored = {false},\n confirmed = {true},\n hidden = {false},\n folder_uuids = {02fb5526-03ff-44ad-8d5c-42bd496c3100},\n private_publication = {false},\n abstract = {An infinite mixture model is applied to model-based speaker clustering with sampling-based optimization to make it possible to estimate the number of speakers. For this purpose, a framework of non-parametric Bayesian modeling is implemented with the Markov chain Monte Carlo and incorporated in the utterance-oriented speaker model. The proposed model is called the utterance-oriented Dirichlet process mixture model (UO-DPMM). The present paper demonstrates that UO-DPMM is successfully applied on large-scale data and outperforms the conventional hierarchical agglomerative clustering, especially for large amounts of utterances.},\n bibtype = {article},\n author = {Tawara, Naohiro and Ogawa, Tetsuji and Watanabe, Shinji and Nakamura, Atsushi and Kobayashi, Tetsunori},\n doi = {10.1017/ATSIP.2015.19},\n journal = {APSIPA Transactions on Signal and Information Processing}\n}","author_short":["Tawara, N.","Ogawa, T.","Watanabe, S.","Nakamura, A.","Kobayashi, T."],"urls":{"Paper":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c/file/76f0fc3c-6107-56c0-0694-5347f53dfae2/csurka_eccv_04.pdf.pdf"},"biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","bibbaseid":"tawara-ogawa-watanabe-nakamura-kobayashi-asamplingbasedspeakerclusteringusingutteranceorienteddirichletprocessmixturemodelanditsevaluationonlargescaledata-2015","role":"author","keyword":["Gibbs sampling","Non-parametric Bayesian model","Sampling approach","Speaker clustering","Utterance-oriented Dirichlet process mixture model"],"metadata":{"authorlinks":{}},"downloads":0},"bibtype":"article","biburl":"https://bibbase.org/service/mendeley/bfbbf840-4c42-3914-a463-19024f50b30c","dataSources":["2252seNhipfTmjEBQ"],"keywords":["gibbs sampling","non-parametric bayesian model","sampling approach","speaker clustering","utterance-oriented dirichlet process mixture model"],"search_terms":["sampling","based","speaker","clustering","using","utterance","oriented","dirichlet","process","mixture","model","evaluation","large","scale","data","tawara","ogawa","watanabe","nakamura","kobayashi"],"title":"A sampling-based speaker clustering using utterance-oriented Dirichlet process mixture model and its evaluation on large-scale data","year":2015}