{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T16:11:09Z","timestamp":1746115869414,"version":"3.40.4"},"publisher-location":"Berlin, Heidelberg","reference-count":15,"publisher":"Springer Berlin Heidelberg","isbn-type":[{"type":"print","value":"9783642420566"},{"type":"electronic","value":"9783642420573"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2013]]},"DOI":"10.1007\/978-3-642-42057-3_8","type":"book-chapter","created":{"date-parts":[[2013,11,16]],"date-time":"2013-11-16T14:28:04Z","timestamp":1384612084000},"page":"54-61","source":"Crossref","is-referenced-by-count":0,"title":["Text-Independent Phoneme Segmentation via Learning Critical Acoustic Change Points"],"prefix":"10.1007","author":[{"given":"Peng","family":"Teng","sequence":"first","affiliation":[]},{"given":"Xiabi","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Yunde","family":"Jia","sequence":"additional","affiliation":[]}],"member":"297","reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Lee, C.-H., et al.: An overview on automatic speech attribute transcription (ASAT). In: Proc. Interspeech, pp. 1825\u20131828 (2007)","DOI":"10.21437\/Interspeech.2007-509"},{"key":"8_CR2","doi-asserted-by":"crossref","unstructured":"Aversano, G., et al.: A new text-independent method for phoneme segmentation. In: Proc. IEEE Midwest Symposium on Circuits and Systems, vol.\u00a02, pp. 516\u2013519 (2001)","DOI":"10.1109\/MWSCAS.2001.986241"},{"key":"8_CR3","doi-asserted-by":"crossref","unstructured":"Dusan, S., Rabiner, L.: On the relation between maximum spectral transition positions and phone boundaries. In: Proc. InterSpeech, pp. 17\u201321 (2006)","DOI":"10.21437\/Interspeech.2006-230"},{"key":"8_CR4","doi-asserted-by":"crossref","unstructured":"Estevan, Y., et al.: Finding maximum margin segments in speech. In: Proc. ICASSP, vol.\u00a04, pp. IV\u2013937 (2007)","DOI":"10.1109\/ICASSP.2007.367225"},{"key":"8_CR5","doi-asserted-by":"crossref","unstructured":"Scharenborg, O., et al.: Segmentation of speech: Childs play? In: Proc. International Conference on Spoken Language Processing, pp. 1953\u20131956 (2007)","DOI":"10.21437\/Interspeech.2007-47"},{"key":"8_CR6","doi-asserted-by":"crossref","unstructured":"Qiao, Y., et al.: Unsupervised optimal phoneme segmentation: objectives, algorithm and comparisons. In: Proc. ICASSP, pp. 3989\u20133992 (2008)","DOI":"10.1109\/ICASSP.2008.4518528"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Minematsu, N.: Metric learning for unsupervised phoneme segmentation. In: Proc. Interspeech (2008)","DOI":"10.21437\/Interspeech.2008-328"},{"issue":"2","key":"8_CR8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1109\/TASL.2008.2009162","volume":"17","author":"G. Almpanidis","year":"2009","unstructured":"Almpanidis, G., et al.: Robust detection of phone boundaries using model selection criteria with few observations. IEEE Transactions on Audio, Speech, and Language Processing\u00a017(2), 287\u2013298 (2009)","journal-title":"IEEE Transactions on Audio, Speech, and Language Processing"},{"key":"8_CR9","doi-asserted-by":"publisher","first-page":"1084","DOI":"10.1121\/1.3277194","volume":"127","author":"O. Scharenborg","year":"2010","unstructured":"Scharenborg, O., et al.: Unsupervised speech segmentation: An analysis of the hypothesized phone boundaries. The Journal of the Acoustical Society of America\u00a0127, 1084 (2010)","journal-title":"The Journal of the Acoustical Society of America"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Khanagha, V., et al.: Improving text-independent phonetic segmentation based on the microcanonical multiscale formalism. In: Proc. ICASSP, pp. 4484\u20134487 (2011)","DOI":"10.1109\/ICASSP.2011.5947350"},{"issue":"11","key":"8_CR11","doi-asserted-by":"publisher","first-page":"831","DOI":"10.1038\/nrn1533","volume":"5","author":"P.K. Kuhl","year":"2004","unstructured":"Kuhl, P.K.: Early language acquisition: cracking the speech code. Nature Reviews Neuroscience\u00a05(11), 831\u2013843 (2004)","journal-title":"Nature Reviews Neuroscience"},{"key":"8_CR12","doi-asserted-by":"crossref","unstructured":"Morency, L.-P., et al.: Latent-dynamic discriminative models for continuous gesture recognition. In: CVPR, pp. 1\u20138 (2007)","DOI":"10.1109\/CVPR.2007.383299"},{"key":"8_CR13","first-page":"207","volume":"10","author":"K.Q. Weinberger","year":"2009","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. The Journal of Machine Learning Research\u00a010, 207\u2013244 (2009)","journal-title":"The Journal of Machine Learning Research"},{"key":"8_CR14","unstructured":"Garofolo, J.S.: TIMIT: acoustic-phonetic continuous speech corpus. Linguistic Data Consortium (1993)"},{"key":"8_CR15","unstructured":"Lafferty, J., et al.: Conditional random fields: probabilistic models for segmenting and labeling sequence data. In: ICML (2001)"}],"container-title":["Lecture Notes in Computer Science","Intelligence Science and Big Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-642-42057-3_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,30]],"date-time":"2025-04-30T20:50:52Z","timestamp":1746046252000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-642-42057-3_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2013]]},"ISBN":["9783642420566","9783642420573"],"references-count":15,"URL":"https:\/\/doi.org\/10.1007\/978-3-642-42057-3_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2013]]}}}