{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T23:43:24Z","timestamp":1742946204275,"version":"3.40.3"},"publisher-location":"Cham","reference-count":20,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319642055"},{"type":"electronic","value":"9783319642062"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-64206-2_44","type":"book-chapter","created":{"date-parts":[[2017,7,28]],"date-time":"2017-07-28T14:21:48Z","timestamp":1501251708000},"page":"393-401","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Phonetic Segmentation Using Knowledge from\u00a0Visual and Perceptual Domain"],"prefix":"10.1007","author":[{"given":"Bhavik","family":"Vachhani","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chitralekha","family":"Bhat","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil","family":"Kopparapu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,7,29]]},"reference":[{"key":"44_CR1","unstructured":"Adell, J., Bonafonte, A.: Towards phone segmentation for concatenative speech synthesis. In: Proceedings of the 5th ISCA Speech Snthesis Workshop, pp. 139\u2013144 (2004)"},{"key":"44_CR2","doi-asserted-by":"crossref","unstructured":"Dusan, S., Rabiner, L.R.: On the relation between maximum spectral transition positions and phone boundaries. In: INTERSPEECH- ICSLP, Ninth International Conference on Spoken Language Processing, 17\u201321 September 2006, Pittsburgh, PA, USA (2006)","DOI":"10.21437\/Interspeech.2006-230"},{"key":"44_CR3","unstructured":"Garofolo, J.S.: Getting started with the darpa timit cd-rom: an acoustic phonetic continuous speech database. In: National Institute of Standards and Technology (NIST) (1988)"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Golipour, L., O\u2019Shaughnessy, D.D.: A new approach for phoneme segmentation of speech signals. In: INTERSPEECH, pp. 1933\u20131936. ISCA (2007)","DOI":"10.21437\/Interspeech.2007-42"},{"key":"44_CR5","doi-asserted-by":"crossref","unstructured":"Kalinli, O.: Automatic phoneme segmentation using auditory attention features. In: Proceedings of the INTERSPEECH, pp. 2270\u20132273 (2012)","DOI":"10.21437\/Interspeech.2012-596"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Keshet, J., Shalev-Shwartz, S., Singer, Y., Chazan, D.: Phoneme alignment based on discriminative learning. In: INTERSPEECH 2005, pp. 2961\u20132964 (2005)","DOI":"10.21437\/Interspeech.2005-129"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"King, S., Hasegawa-Johnson, M.: Accurate speech segmentation by mimicking human auditory processing. In: IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2013, 26\u201331 May, Vancouver, BC, Canada, pp. 8096\u20138100 (2013)","DOI":"10.1109\/ICASSP.2013.6639242"},{"key":"44_CR8","doi-asserted-by":"crossref","unstructured":"Leow, S.J., Chng, E.S., Lee, C.H.: Language-resource independent speech segmentation using cues from a spectrogram image. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5813\u20135817, April 2015","DOI":"10.1109\/ICASSP.2015.7179086"},{"key":"44_CR9","doi-asserted-by":"crossref","unstructured":"Lo, H.Y., Wang, H.M.: Phonetic boundary refinement using support vector machine. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), vol. 4, pp. 933\u2013936, April 2007","DOI":"10.1109\/ICASSP.2007.367224"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Patil, V., Joshi, S., Rao, P.: Improving the robustness of phonetic segmentation to accent and style variation with a two-staged approach. In: INTERSPEECH, pp. 2543\u20132546 (2009)","DOI":"10.21437\/Interspeech.2009-670"},{"key":"44_CR11","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1016\/j.specom.2004.09.001","volume":"45","author":"MA Pitt","year":"2005","unstructured":"Pitt, M.A., Johnson, K., Hume, E., Kiesling, S., Raymond, W.: The buckeye corpus of conversational speech: labeling conventions and a test of transcriber reliability. Speech Commun. 45, 89\u201395 (2005)","journal-title":"Speech Commun."},{"key":"44_CR12","first-page":"1269","volume-title":"Reducing the Bias of Multitaper Spectrum Estimates","author":"GA Prieto","year":"2007","unstructured":"Prieto, G.A., Parker, R.L., Thomson, D.J., Vernon, F.L., Graham, R.L.: Reducing the Bias of Multitaper Spectrum Estimates, vol. 171, pp. 1269\u20131281. Oxford University Press, Oxford (2007)"},{"key":"44_CR13","doi-asserted-by":"crossref","unstructured":"Qiao, Y., Shimomura, N., Minematsu, N.: Unsupervised optimal phoneme segmentation: objectives, algorithm and comparisons. In: ICASSP, pp. 3989\u20133992 (2008)","DOI":"10.21437\/Interspeech.2008-328"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Raymond, W.D., Pitt, M.A., Johnson, K., Hume, E., Makashay, M.J., Dautricourt, R., Hilts, C.: An analysis of transcription consistency in spontaneous speech from the buckeye corpus. In: INTERSPEECH (2002)","DOI":"10.21437\/ICSLP.2002-371"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Shah, N.J., Vachhani, B.B., Sailor, H.B., Patil, H.A.: Effectiveness of PLP-based phonetic segmentation for speech synthesis. In: Proceedings of the ICASSP, Florence, Italy, pp. 270\u2013274 (2014)","DOI":"10.1109\/ICASSP.2014.6853600"},{"key":"44_CR16","doi-asserted-by":"crossref","unstructured":"Stolcke, A., Ryant, N., Mitra, V., Yuan, J., Wang, W., Liberman, M.: Highly accurate phonetic segmentation using boundary correction models and system fusion. In: Proceedings of the ICASSP, Florence, Italy, pp. 5552\u20135556 (2014)","DOI":"10.1109\/ICASSP.2014.6854665"},{"key":"44_CR17","doi-asserted-by":"publisher","first-page":"1055","DOI":"10.1109\/PROC.1982.12433","volume":"70","author":"D Thomson","year":"1982","unstructured":"Thomson, D.: Spectrum estimation and harmonic analysis. Proc. IEEE 70, 1055\u20131096 (1982)","journal-title":"Proc. IEEE"},{"key":"44_CR18","doi-asserted-by":"crossref","unstructured":"Vachhani, B., Bhat, C., Kopparapu, S.: Robust phonetic segmentation using multi-taper spectral estimation for noisy and clipped speech. In: 2016 24th European Signal Processing Conference (EUSIPCO), pp. 1343\u20131347, August 2016","DOI":"10.1109\/EUSIPCO.2016.7760467"},{"key":"44_CR19","doi-asserted-by":"crossref","unstructured":"Wesenick, M.B., Kipp, A.: Estimating the quality of phonetic transcriptions and segmentations of speech signals. In: Proceedings of the Fourth International Conference on Spoken Language 1996, ICSLP 1996, vol. 1, pp. 129\u2013132. IEEE (1996)","DOI":"10.21437\/ICSLP.1996-33"},{"key":"44_CR20","doi-asserted-by":"crossref","unstructured":"Yuan, J., Ryant, N., Liberman, M., Stolcke, A., Mitra, V., Wang, W.: Automatic phonetic segmentation using boundary models. In: Proceedings of the INTERSPEECH, pp. 2306\u20132310 (2013)","DOI":"10.21437\/Interspeech.2013-540"}],"container-title":["Lecture Notes in Computer Science","Text, Speech, and Dialogue"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-64206-2_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T12:42:32Z","timestamp":1710333752000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-64206-2_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319642055","9783319642062"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-64206-2_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2017]]},"assertion":[{"value":"29 July 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"TSD","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Text, Speech, and Dialogue","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2017","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 August 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 August 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"tsd2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.tsdconference.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}