{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,18]],"date-time":"2025-06-18T04:19:51Z","timestamp":1750220391282,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":20,"publisher":"ACM","license":[{"start":{"date-parts":[[2021,7,23]],"date-time":"2021-07-23T00:00:00Z","timestamp":1626998400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2021,7,23]]},"DOI":"10.1145\/3478905.3478915","type":"proceedings-article","created":{"date-parts":[[2021,9,28]],"date-time":"2021-09-28T15:56:17Z","timestamp":1632844577000},"page":"49-54","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Cantonese speaker recognition system based on EM algorithm in noisy environments"],"prefix":"10.1145","author":[{"given":"Yu","family":"Fan","sequence":"first","affiliation":[{"name":"ZhaoQing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chin-Ta","family":"Chen","sequence":"additional","affiliation":[{"name":"ZhaoQing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chih-Chung","family":"Yang","sequence":"additional","affiliation":[{"name":"ZhaoQing University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2021,9,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Bo Tang Zhen Chen Gerald Hefferman Tao Wei Haibo He Qing Yang. 2015. A Hierarchical Distributed Fog Computing Architecture for Big Data Analysis in Smart Cities. Ase Bigdata & Socialinformatics Kaohsiung Taiwan. https:\/\/dl.acm.org\/doi\/epdf\/10.1145\/2818869.2818898.  Bo Tang Zhen Chen Gerald Hefferman Tao Wei Haibo He Qing Yang. 2015. A Hierarchical Distributed Fog Computing Architecture for Big Data Analysis in Smart Cities. Ase Bigdata & Socialinformatics Kaohsiung Taiwan. https:\/\/dl.acm.org\/doi\/epdf\/10.1145\/2818869.2818898.","DOI":"10.1145\/2818869.2818898"},{"volume-title":"Springer handbook of speech processing","author":"Sondhi M.M.","key":"e_1_3_2_1_2_1","unstructured":"M.M. Sondhi . 2009. Springer handbook of speech processing . Springer-Verlag , New Yoork , Inc. https:\/\/doi.org\/10.1007\/978-3-540-49127-9. 10.1007\/978-3-540-49127-9 M.M.Sondhi. 2009. Springer handbook of speech processing. Springer-Verlag, New Yoork, Inc. https:\/\/doi.org\/10.1007\/978-3-540-49127-9."},{"key":"e_1_3_2_1_3_1","volume-title":"Alex Acero and Hsiao-Wuen Hon","author":"Huang Xuedong","year":"2001","unstructured":"Xuedong Huang , Alex Acero and Hsiao-Wuen Hon . 2001 . Spoken Language Processing , New York . https:\/\/dl.acm.org\/doi\/book\/10.5555\/560905. Xuedong Huang, Alex Acero and Hsiao-Wuen Hon. 2001. Spoken Language Processing, New York. https:\/\/dl.acm.org\/doi\/book\/10.5555\/560905."},{"key":"e_1_3_2_1_4_1","first-page":"72","volume-title":"1995. Robust text-independent speaker identification using Gaussian mixture speaker models","author":"Reynolds","unstructured":"Reynolds D.A. and Rose R.C . 1995. Robust text-independent speaker identification using Gaussian mixture speaker models . IEEE Transactions on Speech and Audio Processing, Vol. 3 , Issue :1, Page(s): 72 - 83 . https:\/\/doi.org\/10.1109\/89.365379. 10.1109\/89.365379 Reynolds D.A. and Rose R.C.1995. Robust text-independent speaker identification using Gaussian mixture speaker models. IEEE Transactions on Speech and Audio Processing, Vol.3, Issue:1, Page(s):72-83. https:\/\/doi.org\/10.1109\/89.365379."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2018.8486441"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639585"},{"key":"e_1_3_2_1_7_1","volume-title":"Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments","author":"Wu Bing-Fei","year":"2005","unstructured":"Bing-Fei Wu , Kun-Ching Wang . 2005. Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments . IEEE Transactions on Speech and Audio Processing , Vol. 13 . https:\/\/doi.org\/10.1109\/TSA. 2005 .851909. 10.1109\/TSA.2005.851909 Bing-Fei Wu, Kun-Ching Wang. 2005. Robust endpoint detection algorithm based on the adaptive band-partitioning spectral entropy in adverse environments. IEEE Transactions on Speech and Audio Processing, Vol.13. https:\/\/doi.org\/10.1109\/TSA.2005.851909."},{"key":"e_1_3_2_1_8_1","volume-title":"Han","author":"Thakur Nirmalya","year":"2018","unstructured":"Nirmalya Thakur and Chia Y . Han . 2018 . An Activity Analysis Model for Enhancing User Experiences in Affect Aware Systems. 2018 IEEE 5G World Forum(5GWF).Silicon Valley ,CA,USA. https:\/\/doi.org\/10.1109\/5GWF.2018.8517032. 10.1109\/5GWF.2018.8517032 Nirmalya Thakur and Chia Y. Han. 2018. An Activity Analysis Model for Enhancing User Experiences in Affect Aware Systems. 2018 IEEE 5G World Forum(5GWF).Silicon Valley,CA,USA. https:\/\/doi.org\/10.1109\/5GWF.2018.8517032."},{"key":"#cr-split#-e_1_3_2_1_9_1.1","doi-asserted-by":"crossref","unstructured":"Khamis A.Al-Karawi Ahmed H.Al-Noori Francis F.Li and Tim Ritchings. 2015. Automatic speaker recognition system in adverse conditions-implication of noise and reverberation on system performance. Information and Electronics Engineering.https:\/\/doi.org\/10.7763\/IJIEE.2015.V5.571. 10.7763\/IJIEE.2015.V5.571","DOI":"10.7763\/IJIEE.2015.V5.571"},{"key":"#cr-split#-e_1_3_2_1_9_1.2","doi-asserted-by":"crossref","unstructured":"Khamis A.Al-Karawi Ahmed H.Al-Noori Francis F.Li and Tim Ritchings. 2015. Automatic speaker recognition system in adverse conditions-implication of noise and reverberation on system performance. Information and Electronics Engineering.https:\/\/doi.org\/10.7763\/IJIEE.2015.V5.571.","DOI":"10.7763\/IJIEE.2015.V5.571"},{"key":"e_1_3_2_1_10_1","first-page":"1163530","article-title":"Cepstral analysis technique for automatic speaker verification","volume":"1981","author":"Furui","year":"1981","unstructured":"Furui S. 1981 . Cepstral analysis technique for automatic speaker verification . IEEE Transactions on Acoustics, Speech and Signal Processing. https:\/\/doi.org\/10.1109\/TASSP. 1981 . 1163530 . 10.1109\/TASSP.1981.1163530 Furui S.1981. Cepstral analysis technique for automatic speaker verification. IEEE Transactions on Acoustics, Speech and Signal Processing. https:\/\/doi.org\/10.1109\/TASSP.1981.1163530.","journal-title":"IEEE Transactions on Acoustics, Speech and Signal Processing. https:\/\/doi.org\/10.1109\/TASSP."},{"key":"e_1_3_2_1_11_1","first-page":"326616","article-title":"RASTA processing of speech","volume":"1109","author":"Hermansky H.","year":"1994","unstructured":"H. Hermansky , N. Morgan . 1994 . RASTA processing of speech . IEEE Transactions on Speech and Audio Porcessing.https:\/\/doi.org\/10. 1109\/89 . 326616 . 10.1109\/89.326616 H.Hermansky,N. Morgan.1994. RASTA processing of speech. IEEE Transactions on Speech and Audio Porcessing.https:\/\/doi.org\/10.1109\/89.326616.","journal-title":"IEEE Transactions on Speech and Audio Porcessing.https:\/\/doi.org\/10."},{"key":"#cr-split#-e_1_3_2_1_12_1.1","doi-asserted-by":"crossref","unstructured":"Khamis A.Al-Karawi. 2019. Robustness Speaker Recognition based on feature space in clean and noisy condition. International Journal of Sensors Wireless Communications and Control. https:\/\/doi.org\/10.2174\/2210327909666181219143918. 10.2174\/2210327909666181219143918","DOI":"10.2174\/2210327909666181219143918"},{"key":"#cr-split#-e_1_3_2_1_12_1.2","doi-asserted-by":"crossref","unstructured":"Khamis A.Al-Karawi. 2019. Robustness Speaker Recognition based on feature space in clean and noisy condition. International Journal of Sensors Wireless Communications and Control. https:\/\/doi.org\/10.2174\/2210327909666181219143918.","DOI":"10.2174\/2210327909666181219143918"},{"key":"e_1_3_2_1_13_1","first-page":"784104","article-title":"Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition","volume":"1109","author":"Vergin R.","year":"1999","unstructured":"R. Vergin , D. O'Shaughnessy , and A. Farhat . 1999 . Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition . IEEE Transactions on Speech and Audio Processing.https:\/\/doi.org\/10. 1109\/89 . 784104 . 10.1109\/89.784104 R.Vergin, D.O'Shaughnessy, and A.Farhat.1999. Generalized mel frequency cepstral coefficients for large-vocabulary speaker-independent continuous-speech recognition. IEEE Transactions on Speech and Audio Processing.https:\/\/doi.org\/10.1109\/89.784104.","journal-title":"IEEE Transactions on Speech and Audio Processing.https:\/\/doi.org\/10."},{"volume-title":"Proceedings of the 3rd International Conference on Electrical & Computer Engineering. Dhaka, Bangladesh.https:\/\/www.researchgate.net\/publication\/255574793","author":"Hassan Rashidul","key":"e_1_3_2_1_14_1","unstructured":"Md. Rashidul Hassan , M Jamil , Md. Golam Rabbani and Md.Saifur Rahman.2004. Speaker identification using Mel frequency cepstral coefficients . In Proceedings of the 3rd International Conference on Electrical & Computer Engineering. Dhaka, Bangladesh.https:\/\/www.researchgate.net\/publication\/255574793 . Md.Rashidul Hassan, M Jamil, Md.Golam Rabbani and Md.Saifur Rahman.2004. Speaker identification using Mel frequency cepstral coefficients. In Proceedings of the 3rd International Conference on Electrical & Computer Engineering. Dhaka, Bangladesh.https:\/\/www.researchgate.net\/publication\/255574793."},{"key":"e_1_3_2_1_15_1","volume-title":"An efficient digital VLSI implementation of Gaussian mixture models-based classifier","author":"Shi Minghua","year":"2006","unstructured":"Minghua Shi and Amine Bermak .2006. An efficient digital VLSI implementation of Gaussian mixture models-based classifier . IEEE Transactions on Very Large Scale Integration (VLSI) Systems . https:\/\/doi.org\/10.1109\/TVSLI. 2006 .884048. 10.1109\/TVSLI.2006.884048 Minghua Shi and Amine Bermak.2006. An efficient digital VLSI implementation of Gaussian mixture models-based classifier. IEEE Transactions on Very Large Scale Integration (VLSI) Systems. https:\/\/doi.org\/10.1109\/TVSLI.2006.884048."},{"key":"#cr-split#-e_1_3_2_1_16_1.1","doi-asserted-by":"crossref","unstructured":"Ing-Jr Ding and Chih-Ta Yen. 2015. Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech application. Multimedia Tools and Applications.https:\/\/doi.org\/10.1007\/s11042-013-1587-5. 10.1007\/s11042-013-1587-5","DOI":"10.1007\/s11042-013-1587-5"},{"key":"#cr-split#-e_1_3_2_1_16_1.2","doi-asserted-by":"crossref","unstructured":"Ing-Jr Ding and Chih-Ta Yen. 2015. Enhancing GMM speaker identification by incorporating SVM speaker verification for intelligent web-based speech application. Multimedia Tools and Applications.https:\/\/doi.org\/10.1007\/s11042-013-1587-5.","DOI":"10.1007\/s11042-013-1587-5"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Qian Feng Guang-min Hu and Xing-miao Yao.2008. Semi-supervised internet network traffic classification using a Gaussian mixture model. International Journal of Electronics and Communications. https:\/\/doi.org\/10.1016\/j.aeue.2007.07.006.    10.1016\/j.aeue.2007.07.006\nQian Feng Guang-min Hu and Xing-miao Yao.2008. Semi-supervised internet network traffic classification using a Gaussian mixture model. International Journal of Electronics and Communications. https:\/\/doi.org\/10.1016\/j.aeue.2007.07.006.","DOI":"10.1016\/j.aeue.2007.07.006"}],"event":{"name":"DSIT 2021: 2021 4th International Conference on Data Science and Information Technology","acronym":"DSIT 2021","location":"Shanghai China"},"container-title":["2021 4th International Conference on Data Science and Information Technology"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478905.3478915","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3478905.3478915","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T20:18:37Z","timestamp":1750191517000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3478905.3478915"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,23]]},"references-count":20,"alternative-id":["10.1145\/3478905.3478915","10.1145\/3478905"],"URL":"https:\/\/doi.org\/10.1145\/3478905.3478915","relation":{},"subject":[],"published":{"date-parts":[[2021,7,23]]},"assertion":[{"value":"2021-09-28","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}