{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,12,19]],"date-time":"2024-12-19T05:27:32Z","timestamp":1734586052934,"version":"3.30.2"},"reference-count":35,"publisher":"Elsevier BV","issue":"2","license":[{"start":{"date-parts":[[2005,4,1]],"date-time":"2005-04-01T00:00:00Z","timestamp":1112313600000},"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 & Language"],"published-print":{"date-parts":[[2005,4]]},"DOI":"10.1016\/j.csl.2004.08.001","type":"journal-article","created":{"date-parts":[[2004,9,16]],"date-time":"2004-09-16T14:10:39Z","timestamp":1095343839000},"page":"205-225","source":"Crossref","is-referenced-by-count":17,"title":["A multiple-level linear\/linear segmental HMM with a formant-based intermediate layer"],"prefix":"10.1016","volume":"19","author":[{"given":"Martin J.","family":"Russell","sequence":"first","affiliation":[]},{"given":"Philip J.B.","family":"Jackson","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"year":"1995","series-title":"Neural Networks for Pattern Recognition","author":"Bishop","key":"10.1016\/j.csl.2004.08.001_bib1"},{"key":"10.1016\/j.csl.2004.08.001_bib2","doi-asserted-by":"crossref","first-page":"167","DOI":"10.1049\/ree.1983.0034","article-title":"Continuous connected word recognition using whole-word templates","volume":"53","author":"Bridle","year":"1983","journal-title":"Radio Engineer"},{"issue":"4","key":"10.1016\/j.csl.2004.08.001_bib3","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1016\/S0167-6393(98)00023-5","article-title":"A dynamic, feature-based approach to the interface between phonology and phonetics for speech modeling and recognition","volume":"24","author":"Deng","year":"1998","journal-title":"Speech Commun."},{"issue":"4","key":"10.1016\/j.csl.2004.08.001_bib4","doi-asserted-by":"crossref","first-page":"2008","DOI":"10.1121\/1.410144","article-title":"Context-dependent markov model structured by locus equations: applications to phonetic classification","volume":"96","author":"Deng","year":"1994","journal-title":"J. Acoust. Soc. Am."},{"issue":"6","key":"10.1016\/j.csl.2004.08.001_bib5","doi-asserted-by":"crossref","first-page":"3036","DOI":"10.1121\/1.1315288","article-title":"Spontaneous speech recognition using a statistical coarticulatory model for the vocal-tract-resonance dynamics","volume":"108","author":"Deng","year":"2000","journal-title":"J. Acoust. Soc. Am."},{"key":"10.1016\/j.csl.2004.08.001_bib6","unstructured":"Digalakis, V., 1992. Segment-based stochastic models of spectral dynamics for continuous speech recognition. Ph.D. Thesis, Boston University, MA"},{"key":"10.1016\/j.csl.2004.08.001_bib7","doi-asserted-by":"crossref","unstructured":"Frankel, J., Richmond, K., King, S., Taylor, P., 2000. An automatic speech recognition system using neural networks and linear dynamic models to recover the model articulatory traces. In: Proceedings of the International Conference on Spoken Language Proc., Beijing","DOI":"10.21437\/ICSLP.2000-799"},{"key":"10.1016\/j.csl.2004.08.001_bib8","doi-asserted-by":"crossref","unstructured":"Gales, M.J.F., Young, S.J., 1993. Segmental hidden markov models. In: Proceedings of Eurospeech\u201993, Berlin, Germany, pp. 1579\u20131582","DOI":"10.21437\/Eurospeech.1993-354"},{"key":"10.1016\/j.csl.2004.08.001_bib9","doi-asserted-by":"crossref","unstructured":"Gao, Y., Bakis, R., Huang, J., Zhang, B., 2000. Multistage coarticulation model combining articulatory, formant and cepstral features. In: Proceedings of the International Conference on Spoken Language Proc., Beijing, vol. 1, pp. 25\u201328","DOI":"10.21437\/ICSLP.2000-7"},{"key":"10.1016\/j.csl.2004.08.001_bib10","doi-asserted-by":"crossref","unstructured":"Garner, P.N. Holmes, W.J., 1998. On the robust incorporation of formant features into hidden Markov models for automatic speech recognition. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Seattle, WA","DOI":"10.1109\/ICASSP.1998.674352"},{"year":"1993","series-title":"TIMIT Acoustic\u2013Phonetic Continuous Speech Corpus","author":"Garofolo","key":"10.1016\/j.csl.2004.08.001_bib11"},{"key":"10.1016\/j.csl.2004.08.001_bib12","doi-asserted-by":"crossref","first-page":"101","DOI":"10.1006\/csla.1993.1005","article-title":"Hidden markov models with templates as non-stationary states: an application to speech recognition","volume":"2","author":"Ghitza","year":"1993","journal-title":"Comput. Speech Lang."},{"issue":"2\u20133","key":"10.1016\/j.csl.2004.08.001_bib13","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1016\/S0885-2308(03)00006-8","article-title":"A probabilistic framework for segment-based speech recognition","volume":"17","author":"Glass","year":"2003","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2004.08.001_bib14","doi-asserted-by":"crossref","unstructured":"Halberstadt, A., Glass, J., 1998. Heterogeneous measurements and multiple classifiers for speech recognition. In: Proceedings of the Intertnational Conference on Spoken Language Proc., Sydney, Australia, pp. 995\u2013998","DOI":"10.21437\/ICSLP.1998-522"},{"key":"10.1016\/j.csl.2004.08.001_bib15","unstructured":"Holmes, J.N., 2001. Speech processing system using formant analysis. US Patent US6292775"},{"key":"10.1016\/j.csl.2004.08.001_bib16","unstructured":"Holmes, J.N., Garner, P.N., 2000. Using formant frequencies in speech recognition. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Istanbul, Turkey, vol. 3, pp. 1347\u20131350"},{"year":"2001","series-title":"Speech Synthesis and Recognition","author":"Holmes","key":"10.1016\/j.csl.2004.08.001_bib17"},{"issue":"1","key":"10.1016\/j.csl.2004.08.001_bib18","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1006\/csla.1998.0048","article-title":"Probablistic-trajectory segmental HMMs","volume":"13","author":"Holmes","year":"1999","journal-title":"Comput. Speech Lang."},{"key":"10.1016\/j.csl.2004.08.001_bib19","doi-asserted-by":"crossref","unstructured":"Holmes, J.N., Holmes, W.J., Garner, P.N., 1997. Using formant frequencies in speech recognition. In: Proceedings of Eurospeech\u201997, Rhodes, Greece, pp. 2083\u20132086","DOI":"10.21437\/Eurospeech.1997-551"},{"key":"10.1016\/j.csl.2004.08.001_bib20","doi-asserted-by":"crossref","first-page":"127","DOI":"10.1177\/002383096400700301","article-title":"Speech synthesis by rule","volume":"7","author":"Holmes","year":"1964","journal-title":"Lang. Speech"},{"key":"10.1016\/j.csl.2004.08.001_bib21","doi-asserted-by":"crossref","first-page":"121","DOI":"10.1016\/0167-8655(87)90093-6","article-title":"Delayed decision making in speech recognition the case of formants","volume":"6","author":"Hunt","year":"1987","journal-title":"Pattern Recognition Lett."},{"key":"10.1016\/j.csl.2004.08.001_bib22","unstructured":"Jackson, P.J.B., 2003. Improvements in classification accuracy through modelling duration. In: Proceedings of the ICPhS, Barcelona"},{"key":"10.1016\/j.csl.2004.08.001_bib23","doi-asserted-by":"crossref","unstructured":"Jackson, P.J.B., Russell, M.J., 2002. Models of speech dynamics in a segmental-HMM recogniser using intermediate linear representations. In: Proceedings of the International Conference on Spoken Language Proc., Denver, CO, pp. 1253\u20131256","DOI":"10.21437\/ICSLP.2002-386"},{"issue":"13","key":"10.1016\/j.csl.2004.08.001_bib24","doi-asserted-by":"crossref","first-page":"667","DOI":"10.1049\/el:20020436","article-title":"Data-driven, nonlinear, formant-to-acoustic mapping for ASR","volume":"38","author":"Jackson","year":"2002","journal-title":"Electron. Lett."},{"key":"10.1016\/j.csl.2004.08.001_bib25","doi-asserted-by":"crossref","unstructured":"Lamel, L.F., Gauvain, J.L. (1993). High performance speaker-independent phone recognition using cdhmm. In: Proceedings of Eurospeech\u201993, Berlin, Germany, pp. 121\u2013124","DOI":"10.21437\/Eurospeech.1993-49"},{"key":"10.1016\/j.csl.2004.08.001_bib26","unstructured":"Lo, B.H., Russell, M.J., 2003. Speech recognition using an intermediate articulatory layer and non-linear articulatory-to-acoustie mapping. One day meeting for young speech researchers. University College, London"},{"key":"10.1016\/j.csl.2004.08.001_bib27","unstructured":"NIST 2000. Benchmark tests: Significance Tests for ASR. National Institute of Standards and Technology (Speech Group), Gaithersburg, MD. Available from: "},{"issue":"5","key":"10.1016\/j.csl.2004.08.001_bib28","doi-asserted-by":"crossref","first-page":"360","DOI":"10.1109\/89.536930","article-title":"From HMM\u2019s to segmental models: a unified view of stochastic modeling for speech recognition","volume":"4","author":"Ostendorf","year":"1996","journal-title":"IEEE Trans. Speech. Audio Process."},{"key":"10.1016\/j.csl.2004.08.001_bib29","doi-asserted-by":"crossref","unstructured":"Richards, H.B., Bridle, J.S., 1999. The HDM: a segmental Hidden Dynamic Model of coarticulation. In: Proceedings of the IEEE-ICASSP, Phoenix, AZ, pp. 357\u2013360","DOI":"10.1109\/ICASSP.1999.758136"},{"key":"10.1016\/j.csl.2004.08.001_bib30","doi-asserted-by":"crossref","unstructured":"Russell, M.J., 1993. A segmental HMM for speech pattern modelling. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Minneapolis, MN, pp. 499\u2013502","DOI":"10.1109\/ICASSP.1993.319351"},{"key":"10.1016\/j.csl.2004.08.001_bib31","unstructured":"Russell, M.J., Jackson, P.J.B., Wong, L.P., 2003. Development of articulatory-based multi-level segmental HMMs for phonetic classification in ASR. In: Proceedings of the EC-VIP-MC\u201903, Zagreb, Croatia"},{"issue":"9","key":"10.1016\/j.csl.2004.08.001_bib32","first-page":"201","article-title":"Exponential interpolation of states in a hidden Markov model","volume":"18","author":"Wiewiorka","year":"1996","journal-title":"Proc. Inst. Acoust."},{"key":"10.1016\/j.csl.2004.08.001_bib33","doi-asserted-by":"crossref","unstructured":"Wilkinson, N., Russell, M.J., 2002. Improved phone recognition on TIMIT using formant frequency data and confidence measures. In: Proceedings of the International Conference on Spoken Language Proc., Denver, CO, pp. 2121\u20132124","DOI":"10.21437\/ICSLP.2002-580"},{"year":"1997","series-title":"The HTK Book","author":"Young","key":"10.1016\/j.csl.2004.08.001_bib34"},{"key":"10.1016\/j.csl.2004.08.001_bib35","doi-asserted-by":"crossref","unstructured":"Zhou, J., Seide, F., Deng, L., 2003. Coarticulation modeling by embedding a target-directed hidden trajectory model into hmm-modeling and training. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing, Hong Kong, vol. 1, pp. 744\u2013747","DOI":"10.1109\/ICASSP.2003.1198888"}],"container-title":["Computer Speech & Language"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230804000348?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0885230804000348?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T16:49:28Z","timestamp":1734540568000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0885230804000348"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2005,4]]},"references-count":35,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2005,4]]}},"alternative-id":["S0885230804000348"],"URL":"https:\/\/doi.org\/10.1016\/j.csl.2004.08.001","relation":{},"ISSN":["0885-2308"],"issn-type":[{"type":"print","value":"0885-2308"}],"subject":[],"published":{"date-parts":[[2005,4]]}}}