{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T03:37:52Z","timestamp":1778643472426,"version":"3.51.4"},"publisher-location":"Cham","reference-count":22,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783319108155","type":"print"},{"value":"9783319108162","type":"electronic"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2014]]},"DOI":"10.1007\/978-3-319-10816-2_46","type":"book-chapter","created":{"date-parts":[[2014,9,1]],"date-time":"2014-09-01T05:25:37Z","timestamp":1409549137000},"page":"382-389","source":"Crossref","is-referenced-by-count":8,"title":["Speaker Identification by Combining Various Vocal Tract and Vocal Source Features"],"prefix":"10.1007","author":[{"given":"Yuta","family":"Kawakami","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longbiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsuhiko","family":"Kai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seiichi","family":"Nakagawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","reference":[{"issue":"1","key":"46_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1016\/j.specom.2009.08.009","volume":"52","author":"T. Kinnunen","year":"2010","unstructured":"Kinnunen, T., Li, H.: An overview of text-independent speaker recognition: From features to supervectors. Speech Communication\u00a052(1), 12\u201340 (2010)","journal-title":"Speech Communication"},{"issue":"4","key":"46_CR2","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S. Davis","year":"1980","unstructured":"Davis, S., Santa, B., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. on Acoustics, Speech and Signal Processing\u00a028(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. on Acoustics, Speech and Signal Processing"},{"issue":"4","key":"46_CR3","doi-asserted-by":"publisher","first-page":"561","DOI":"10.1109\/PROC.1975.9792","volume":"63","author":"J. Makhoul","year":"1975","unstructured":"Makhoul, J., Bolt, B.: Linear prediction: A tutorial review. Proc. of IEEE\u00a063(4), 561\u2013580 (1975)","journal-title":"Proc. of IEEE"},{"key":"46_CR4","doi-asserted-by":"publisher","first-page":"58","DOI":"10.1109\/79.536825","volume":"13","author":"R.J. Mammone","year":"1996","unstructured":"Mammone, R.J., Zhang, X., Ramachandran, R.P.: Robust speaker recognition: A feature-based approach. IEEE Signal Processing Magazine\u00a013, 58\u201371 (1996)","journal-title":"IEEE Signal Processing Magazine"},{"key":"46_CR5","volume-title":"Spoken Language Processing: A Guide to Theory, Algorithm, and System Development","author":"X. Huang","year":"2001","unstructured":"Huang, X., Acero, A., Hon, H.W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development. Prentice-Hall, New Jersey (2001)"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Hermansky, H.: Perceptual linear predictive (PLP) analysis of speech. The Journal of the Acoustical Society of America\u00a087(4), 1738\u20131752","DOI":"10.1121\/1.399423"},{"key":"46_CR7","doi-asserted-by":"crossref","unstructured":"Wang, L., Kitaoka, N., Nakagawa, S.: Robust Distant Speaker Recognition Based on Position Dependent Cepstral Mean Normalization. In: Proceedings of the 9th European Conference on Speech Communication and Technology (Interspeech 2005-Eurospeech), pp. 1977\u20131980 (2005)","DOI":"10.21437\/Interspeech.2005-622"},{"key":"46_CR8","doi-asserted-by":"publisher","first-page":"501","DOI":"10.1016\/j.specom.2007.04.004","volume":"49","author":"L. Wang","year":"2007","unstructured":"Wang, L., Kitaoka, N., Nakagawa, S.: Robust distant speaker recognition based on position dependent CMN by combining speaker-specific GMM with speaker-adapted HMM. Speech Communication\u00a049, 501\u2013513 (2007)","journal-title":"Speech Communication"},{"issue":"4","key":"46_CR9","first-page":"281","volume":"20","author":"K.P. Markov","year":"1999","unstructured":"Markov, K.P., Nakagawa, S.: Integrating pitch and LPC-residual information with LPC-cepstrum for text-independent speaker recognition. Jour. ASJ (E)\u00a020(4), 281\u2013291 (1999)","journal-title":"Jour. ASJ (E)"},{"issue":"3","key":"46_CR10","doi-asserted-by":"publisher","first-page":"181","DOI":"10.1109\/LSP.2006.884031","volume":"14","author":"N. Zheng","year":"2007","unstructured":"Zheng, N., Lee, T., Ching, P.C.: Integration of complementary acoustic features for speaker recognition. IEEE Signal Processing Letters\u00a014(3), 181\u2013184 (2007)","journal-title":"IEEE Signal Processing Letters"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"Hedge, R.M., Murthy, H.A., Rao, G.V.R.: Application of the modified group delay function to speaker identification and discrimination. In: Proc. ICASSP 2004, vol.\u00a01, pp. 517\u2013520 (2004)","DOI":"10.1109\/ICASSP.2004.1326036"},{"key":"46_CR12","doi-asserted-by":"crossref","unstructured":"Padmanabhan, R., Parthasarathi, S., Murthy, H.: Robustness of phase based features for speaker recognition. In: Proc. Interspeech, pp. 2355\u20132358 (2009)","DOI":"10.21437\/Interspeech.2009-397"},{"key":"46_CR13","doi-asserted-by":"crossref","unstructured":"Kua, J., Epps, J., Ambikairajah, E., Choi, E.: LS regularization of group delay features for speaker recognition. In: Proc. Interspeech, pp. 2887\u20132890 (2009)","DOI":"10.21437\/Interspeech.2009-46"},{"key":"46_CR14","doi-asserted-by":"crossref","unstructured":"Nakagawa, S., Asakawa, K., Wang, L.: Speaker recognition by combining MFCC and phase information. In: Proc. InterSpeech, pp. 2005\u20132008 (2007)","DOI":"10.21437\/Interspeech.2007-161"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Wang, L., Ohtsuka, S., Nakagawa, S.: High improvement of speaker identification and verification by combining MFCC and phase information. In: Proc. ICASSP, pp. 4529\u20134532 (2009)","DOI":"10.1109\/ICASSP.2009.4960637"},{"key":"46_CR16","doi-asserted-by":"crossref","unstructured":"Wang, L., Minami, K., Yamamoto, K., Nakagawa, S.: Speaker identification by combining MFCC and phase information in noisy environments. In: Proc. ICASSP, pp. 4502\u20134505 (2010)","DOI":"10.1109\/ICASSP.2010.5495586"},{"issue":"9","key":"46_CR17","doi-asserted-by":"publisher","first-page":"2397","DOI":"10.1587\/transinf.E93.D.2397","volume":"E93-Dd","author":"L. Wang","year":"2010","unstructured":"Wang, L., Minami, K., Yamamoto, K., Nakagawa, S.: Speaker recognition by combining MFCC and phase information in noisy conditions. IEICE Transactions on Information and Systems\u00a0E93-Dd(9), 2397\u20132406 (2010)","journal-title":"IEICE Transactions on Information and Systems"},{"key":"46_CR18","unstructured":"Hirano, Y., Wang, L., Kai, A., Nakagawa, S.: On the Use of Phase Information-based Joint Factor Analysis for Speaker Verification under Channel Mismatch Condition. In: Proc. of APSIPA ASC 2012, 4 pages (2012)"},{"issue":"4","key":"46_CR19","doi-asserted-by":"publisher","first-page":"1085","DOI":"10.1109\/TASL.2011.2172422","volume":"20","author":"S. Nakagawa","year":"2012","unstructured":"Nakagawa, S., Wang, L., Ohtsuka, S.: Speaker Identification and Verification by Combining MFCC and Phase Information. IEEE Trans. on Audio, Speech, and Language Processing\u00a020(4), 1085\u20131095 (2012)","journal-title":"IEEE Trans. on Audio, Speech, and Language Processing"},{"key":"46_CR20","unstructured":"Shimada, K., Yamamoto, K., Nakagawa, S.: Speaker identification using pseudo pitch\/synchronized phase information in voiced sound. In: Proc. APSIPA ASC 2011, pp. 1\u20136 (2011)"},{"key":"46_CR21","doi-asserted-by":"crossref","unstructured":"Kawakami, Y., Wang, L., Nakagawa, S.: Speaker Identification Using Pseudo Pitch Synchronized Phase Information in Noisy Environments. In: Proc. APSIPA ASC 2012, 5 pages (2013)","DOI":"10.1109\/APSIPA.2013.6694385"},{"issue":"13","key":"46_CR22","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1250\/ast.20.199","volume":"20","author":"K. Itou","year":"1999","unstructured":"Itou, K., Yamamoto, M., Takeda, K., Takezawa, T., Matsuoka, T., Kobayashi, T., Shikano, K., Itahashi, S.: JNAS:Japanese speech coupus for large vocabulary continuous speech recognition research. J. Acoust. Soc. Jpn. (E)\u00a020(13), 199\u2013206 (1999)","journal-title":"J. Acoust. Soc. Jpn. (E)"}],"container-title":["Lecture Notes in Computer Science","Text, Speech and Dialogue"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-10816-2_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,4]],"date-time":"2025-05-04T12:15:36Z","timestamp":1746360936000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-319-10816-2_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2014]]},"ISBN":["9783319108155","9783319108162"],"references-count":22,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-10816-2_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2014]]}}}