TY - GEN
T1 - Multidimensional scaling for fast speaker clustering
AU - Hsia, Chi Chun
AU - Lee, Kuo Yuan
AU - Chuang, Chih Chieh
AU - Chiu, Yu-Hsien
PY - 2010/12/1
Y1 - 2010/12/1
N2 - This study presents a fast speaker clustering method based on multidimensional scaling. Speech segments are trained as initial acoustic models. MDS is utilized to transform acoustic models to a space with the coordinate best preserve the distances or dissimilarity between models. Speaker clusters are clustered using vector quantization on the MDS coordinates and the acoustic speaker models are trained on MFCCs features for each cluster. Experimental results show the proposed method outperforms the baseline speaker clustering method in lower execution time.
AB - This study presents a fast speaker clustering method based on multidimensional scaling. Speech segments are trained as initial acoustic models. MDS is utilized to transform acoustic models to a space with the coordinate best preserve the distances or dissimilarity between models. Speaker clusters are clustered using vector quantization on the MDS coordinates and the acoustic speaker models are trained on MFCCs features for each cluster. Experimental results show the proposed method outperforms the baseline speaker clustering method in lower execution time.
UR - http://www.scopus.com/inward/record.url?scp=79851479262&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=79851479262&partnerID=8YFLogxK
U2 - 10.1109/ISCSLP.2010.5684888
DO - 10.1109/ISCSLP.2010.5684888
M3 - Conference contribution
AN - SCOPUS:79851479262
SN - 9781424462469
T3 - 2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings
SP - 296
EP - 299
BT - 2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010 - Proceedings
T2 - 2010 7th International Symposium on Chinese Spoken Language Processing, ISCSLP 2010
Y2 - 29 November 2010 through 3 December 2010
ER -