{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T22:10:18Z","timestamp":1735942218722,"version":"3.32.0"},"reference-count":36,"publisher":"Elsevier BV","issue":"2-3","license":[{"start":{"date-parts":[[2006,4,1]],"date-time":"2006-04-01T00:00:00Z","timestamp":1143849600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Computer Speech &amp; Language"],"published-print":{"date-parts":[[2006,4]]},"DOI":"10.1016\/j.csl.2005.07.004","type":"journal-article","created":{"date-parts":[[2005,9,1]],"date-time":"2005-09-01T11:13:06Z","timestamp":1125573186000},"page":"276-302","source":"Crossref","is-referenced-by-count":3,"title":["A syllable-scale framework for language identification"],"prefix":"10.1016","volume":"20","author":[{"given":"Terrence","family":"Martin","sequence":"first","affiliation":[]},{"given":"Brendan","family":"Baker","sequence":"additional","affiliation":[]},{"given":"Eddie","family":"Wong","sequence":"additional","affiliation":[]},{"given":"Sridha","family":"Sridharan","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.csl.2005.07.004_bib1","doi-asserted-by":"crossref","unstructured":"Adami, A., Hermansky, H., 2003. Segmentation of speech for speaker and language recognition. In: Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Geneva, pp. 841\u2013844.","DOI":"10.21437\/Eurospeech.2003-189"},{"key":"10.1016\/j.csl.2005.07.004_bib2","unstructured":"Baker, B., Vogt, R., Mason, M., Sridharan, S., 2004. Improved phonetic and lexical speaker recognition through MAP adaptation. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 94\u201399."},{"key":"10.1016\/j.csl.2005.07.004_bib3","unstructured":"Berkling, K.M., 1996. Automatic language identification with sequences of language independent phoneme clusters. Ph.D. Thesis, Oregon Graduate Institute of Science and Technology."},{"key":"10.1016\/j.csl.2005.07.004_bib4","doi-asserted-by":"crossref","unstructured":"Doddington, G., 2001. Speaker recognition based on idiolectal differences between speakers. In: Eurospeech, vol. 4, Denmark, pp. 2517\u20132520.","DOI":"10.21437\/Eurospeech.2001-417"},{"key":"10.1016\/j.csl.2005.07.004_bib5","doi-asserted-by":"crossref","unstructured":"Wong, E., Martin, T., Svendsen, T., Sridharan, S., 2003. Multilingual phone clustering for recognition of spontaneous Indonesian speech utilising pronunciation modeling techniques. In: Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Geneva, pp. 3133\u20133136.","DOI":"10.21437\/Eurospeech.2003-783"},{"key":"10.1016\/j.csl.2005.07.004_bib6","doi-asserted-by":"crossref","unstructured":"Foil, J., 1986. Language identification using noisy speech. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 861\u2013864.","DOI":"10.1109\/ICASSP.1986.1168879"},{"key":"10.1016\/j.csl.2005.07.004_bib7","doi-asserted-by":"crossref","unstructured":"Goodman, F., Martin, A.F., Wohlford, R.E., 1989. Improved automatic language identification in noisy speech. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 528\u2013531.","DOI":"10.1109\/ICASSP.1989.266480"},{"issue":"4","key":"10.1016\/j.csl.2005.07.004_bib8","doi-asserted-by":"crossref","first-page":"2323","DOI":"10.1121\/1.418211","article-title":"Segment-based automatic language identification","volume":"101","author":"Hazen","year":"1997","journal-title":"J. Acoust. Soc. Am."},{"issue":"4","key":"10.1016\/j.csl.2005.07.004_bib9","doi-asserted-by":"crossref","first-page":"1738","DOI":"10.1121\/1.399423","article-title":"Perceptual linear predictive (PLP) analysis of speech","volume":"87","author":"Hermansky","year":"1990","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2005.07.004_bib10","doi-asserted-by":"crossref","unstructured":"Hieronymus, J., Kadambe, S., 1996. Spoken language identification using large vocabulary speech recognition. In: Proceedings of the International Conference on Spoken Language Processing, vol. 3, pp. 1780\u20131783.","DOI":"10.1109\/ICSLP.1996.607974"},{"issue":"3","key":"10.1016\/j.csl.2005.07.004_bib11","doi-asserted-by":"crossref","first-page":"708","DOI":"10.1121\/1.381582","article-title":"Toward automatic identification of the language of an utterance. i. Preliminary methodological considerations","volume":"62","author":"House","year":"1977","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2005.07.004_bib12","unstructured":"Hutchins, S., Thyme-Gobbel, A., 1994. The role of prosody in language identification. In: Proceedings of the 15th Annual Speech Research Symposium, pp. 76\u201383."},{"key":"10.1016\/j.csl.2005.07.004_bib13","unstructured":"Kajarekar, S., 2002. Analysis of variabilty in speech with applications to speech and speaker recognition. Ph.D. Thesis, Oregon Graduate Institute of Science and Technology, Portland, USA."},{"key":"10.1016\/j.csl.2005.07.004_bib14","doi-asserted-by":"crossref","unstructured":"Li, K.P., Edwards, T.J., 1980. Statistical models for automatic language identification. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 884\u2013887.","DOI":"10.1109\/ICASSP.1980.1170832"},{"key":"10.1016\/j.csl.2005.07.004_bib15","unstructured":"Linguistic Data Consortium, 1996. CallFriend corpus. Available from: <http:\/\/www.ldc.upenn.edu\/>."},{"key":"10.1016\/j.csl.2005.07.004_bib16","doi-asserted-by":"crossref","unstructured":"Martin, A., Doddington, G., Kamm, T., Ordowski, M., Przybocki, M., 1997. The DET curve in assessment of detection task performance. In: Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), vol. 4, pp. 1895\u20131898.","DOI":"10.21437\/Eurospeech.1997-504"},{"key":"10.1016\/j.csl.2005.07.004_bib17","unstructured":"Martin, T., Wong, E., Baker, B., Mason, M., Sridharan, S., 2004. Pitch and energy trajectory modelling in a syllable length temporal framework for language identification. In: Odyssey: The Speaker and Language Recognition Workshop, pp. 289\u2013296."},{"key":"10.1016\/j.csl.2005.07.004_bib18","unstructured":"Massachusetts Institute of Technology Lincoln Laboratory, 2004. LNKnet Pattern Classification Software. Available from: <http:\/\/www.ll.mit.edu\/IST\/lnknet\/>."},{"key":"10.1016\/j.csl.2005.07.004_bib19","doi-asserted-by":"crossref","unstructured":"Mendoza, S., Gillick, L., Ito, Y., Lowe, S., Newman, M., 1996. Automatic language identification using large vocabulary continuous speech recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 2, pp. 785\u2013788.","DOI":"10.1109\/ICASSP.1996.543238"},{"key":"10.1016\/j.csl.2005.07.004_bib20","doi-asserted-by":"crossref","unstructured":"Muthusamy, Y., Cole, R., Oshika, B., 1992. The OGI multi-language telephone speech corpus. In: International Conference on Spoken Language Processing, pp. 895\u2013898.","DOI":"10.21437\/ICSLP.1992-276"},{"key":"10.1016\/j.csl.2005.07.004_bib21","unstructured":"Muthusamy, Y.K., 1993. July A segmental approach to automatic language identification. Ph.D. Thesis, Oregon Graduate Institute of Science and Technology."},{"issue":"6","key":"10.1016\/j.csl.2005.07.004_bib22","doi-asserted-by":"crossref","first-page":"70","DOI":"10.1002\/ecjc.4430770607","article-title":"Spoken language identification by ergodic HMM\u2019s and its state sequences","volume":"77","author":"Nakagawa","year":"1994","journal-title":"Electron. Commun. Jpn."},{"issue":"9","key":"10.1016\/j.csl.2005.07.004_bib23","doi-asserted-by":"crossref","first-page":"678","DOI":"10.1109\/89.943345","article-title":"Spoken language recognition \u2013 a step towards multilinguality in speech processing","volume":"9","author":"Navratil","year":"2001","journal-title":"IEEE Trans. Speech Audio Process."},{"key":"10.1016\/j.csl.2005.07.004_bib24","doi-asserted-by":"crossref","unstructured":"Parris, E., Carey, M., 1995. Language identification using multiple knowledge sources. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 3519\u20133522.","DOI":"10.1109\/ICASSP.1995.479745"},{"key":"10.1016\/j.csl.2005.07.004_bib25","doi-asserted-by":"crossref","unstructured":"Reynolds, D., 1997. Comparison of background normalization methods for text-independent speaker verification. In: Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Vol. 2, pp. 963\u2013966.","DOI":"10.21437\/Eurospeech.1997-337"},{"key":"10.1016\/j.csl.2005.07.004_bib26","doi-asserted-by":"crossref","unstructured":"Savic, M., Acosta, E., Gupta, S.K., 1991. An automatic language identification system. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 528\u2013531.","DOI":"10.1109\/ICASSP.1991.150462"},{"key":"10.1016\/j.csl.2005.07.004_bib27","doi-asserted-by":"crossref","unstructured":"Singer, E., Torres-Carrasquillo, P., Gleason, T., Campbell, W., Reynolds, D., 2003. Acoustic and discriminative approaches to automatic language identification. In: Proceedings of the European Conference on Speech Communication and Technology (Eurospeech), Geneva, pp. 1345\u20131349.","DOI":"10.21437\/Eurospeech.2003-417"},{"year":"1995","series-title":"Speech Coding and Synthesis","author":"Talkin","key":"10.1016\/j.csl.2005.07.004_bib28"},{"key":"10.1016\/j.csl.2005.07.004_bib29","doi-asserted-by":"crossref","unstructured":"Torres-Carrasquillo, P., Singer, E., Kohler, M., Green, R., Reynolds, D., 2002. Approaches to language identification using Gaussian mixture models and shifted delta cepstral features. In: Proceedings of the International Conference on Spoken Language Processing, vol. 1, Denver, pp. 89\u201392.","DOI":"10.1109\/ICASSP.2002.1005850"},{"key":"10.1016\/j.csl.2005.07.004_bib30","doi-asserted-by":"crossref","unstructured":"Tucker, R., Carey, M., Parris, E., 1994. Automatic language identification using sub-word models. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 301\u2013304.","DOI":"10.1109\/ICASSP.1994.389295"},{"key":"10.1016\/j.csl.2005.07.004_bib31","unstructured":"Wong, E., Sridharan, S., 2003. Spoken language identification utilising both acoustic and phonetic information. In: International Symposium on Digital Signal Processing and Communication Systems, pp. 520\u2013526."},{"key":"10.1016\/j.csl.2005.07.004_bib32","doi-asserted-by":"crossref","unstructured":"Yan, Y., Barnard, E., 1995. An approach to automatic language identification based on language-dependent phone recognition. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 3511\u20133514.","DOI":"10.1109\/ICASSP.1995.479743"},{"key":"10.1016\/j.csl.2005.07.004_bib33","doi-asserted-by":"crossref","first-page":"37","DOI":"10.1006\/csla.1996.0003","article-title":"Development of an approach to automatic language identification based on phone recognition","volume":"10","author":"Yan","year":"1996","journal-title":"Computer Speech Lang."},{"key":"10.1016\/j.csl.2005.07.004_bib34","unstructured":"Young, S., Evermann, G., Hain, T., Kershaw, D., Moore, G., Odell, J., Ollason, D., Povey, D., Valtchev, V., Woodland, P., 2002. The HTK Book for Version 3.2. Entropic."},{"key":"10.1016\/j.csl.2005.07.004_bib35","doi-asserted-by":"crossref","unstructured":"Zissman, M., Singer, E., 1994. Automatic language identification of telephone speech messages using phoneme recognition and n-gram modelling. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 1, pp. 305\u2013308.","DOI":"10.1109\/ICASSP.1994.389377"},{"key":"10.1016\/j.csl.2005.07.004_bib36","doi-asserted-by":"crossref","unstructured":"Zissman, M., Singer, E., 1995. Language identification using phoneme recognition and phonotactic language modeling. In: Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing, vol. 5, pp. 3503\u20133506.","DOI":"10.1109\/ICASSP.1995.479741"}],"container-title":["Computer Speech &amp; Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230805000343?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230805000343?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T21:36:31Z","timestamp":1735940191000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230805000343"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2006,4]]},"references-count":36,"journal-issue":{"issue":"2-3","published-print":{"date-parts":[[2006,4]]}},"alternative-id":["S0885230805000343"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2005.07.004","relation":{},"ISSN":["0885-2308"],"issn-type":[{"type":"print","value":"0885-2308"}],"subject":[],"published":{"date-parts":[[2006,4]]}}}