{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T21:41:18Z","timestamp":1760132478913,"version":"3.41.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783319698991"},{"type":"electronic","value":"9783319699004"}],"license":[{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2017,1,1]],"date-time":"2017-01-01T00:00:00Z","timestamp":1483228800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2017]]},"DOI":"10.1007\/978-3-319-69900-4_38","type":"book-chapter","created":{"date-parts":[[2017,10,31]],"date-time":"2017-10-31T01:42:58Z","timestamp":1509414178000},"page":"299-307","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":4,"title":["Analysis of Features and Metrics for Alignment in Text-Dependent Voice Conversion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7294-6757","authenticated-orcid":false,"given":"Nirmesh J.","family":"Shah","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4068-2005","authenticated-orcid":false,"given":"Hemant A.","family":"Patil","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2017,11,1]]},"reference":[{"key":"38_CR1","doi-asserted-by":"crossref","unstructured":"Aradilla, G., Bourlard, H., Magimai-Doss, M.: Posterior features applied to speech recognition tasks with user-defined vocabulary. In: Proceeding ICASSP, Taipei, pp. 3809\u20133812 (2009)","DOI":"10.1109\/ICASSP.2009.4960457"},{"key":"38_CR2","doi-asserted-by":"crossref","unstructured":"Aradilla, G., Vepa, J., Bourlard, H.: Using posterior-based features in template matching for speech recognition. In: INTERSPEECH, Pittsburgh, pp. 1\u20135 (2006)","DOI":"10.21437\/Interspeech.2006-644"},{"issue":"4","key":"38_CR3","doi-asserted-by":"publisher","first-page":"357","DOI":"10.1109\/TASSP.1980.1163420","volume":"28","author":"S Davis","year":"1980","unstructured":"Davis, S., Mermelstein, P.: Comparison of parametric representations for monosyllabic word recognition in continuously spoken sentences. IEEE Trans. Acoust. Speech Signal Process. 28(4), 357\u2013366 (1980)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"5","key":"38_CR4","doi-asserted-by":"publisher","first-page":"944","DOI":"10.1109\/TASL.2009.2038669","volume":"18","author":"D Erro","year":"2010","unstructured":"Erro, D., Moreno, A., Bonafonte, A.: INCA algorithm for training voice conversion systems from nonparallel corpora. IEEE Trans. Audio Speech Lang. Process. 18(5), 944\u2013953 (2010)","journal-title":"IEEE Trans. Audio Speech Lang. Process."},{"key":"38_CR5","doi-asserted-by":"crossref","unstructured":"Fukada, T., Tokuda, K., Kobayashi, T., Imai, S.: An adaptive algorithm for mel-cepstral analysis of speech. In: ICASSP, San Francisco, California, USA, pp. 137\u2013140 (1992)","DOI":"10.1109\/ICASSP.1992.225953"},{"key":"38_CR6","doi-asserted-by":"crossref","unstructured":"Helander, E., Schwarz, J., Nurminen, J., Silen, H., Gabbouj, M.: On the impact of alignment on voice conversion performance. In: INTERSPEECH, Brisbane, Australia, pp. 1\u20135 (2008)","DOI":"10.21437\/Interspeech.2008-419"},{"key":"38_CR7","doi-asserted-by":"crossref","unstructured":"Kain, A., Macon, M.W.: Spectral voice conversion for text-to-speech synthesis. In: Proceeding ICASSP, Seattle, WA, pp. 285\u2013288 (1998)","DOI":"10.1109\/ICASSP.1998.674423"},{"issue":"4","key":"38_CR8","doi-asserted-by":"publisher","first-page":"287","DOI":"10.1561\/2200000019","volume":"5","author":"B Kulis","year":"2013","unstructured":"Kulis, B., et al.: Metric learning: a survey. Found. Trends\u00ae Mach. Learn. 5(4), 287\u2013364 (2013)","journal-title":"Found. Trends\u00ae Mach. Learn."},{"key":"38_CR9","doi-asserted-by":"crossref","unstructured":"Madhavi, M.C., Patil, H.A.: Modification in sequential dynamic time warping for fast computation of query-by-example spoken term detection task. In: SPCOM, Bangalore, India, pp. 1\u20135 (2016)","DOI":"10.1109\/SPCOM.2016.7746657"},{"key":"38_CR10","doi-asserted-by":"crossref","unstructured":"Patil, H.A., Patel, T., Talesara, S., Shah, N., Sailor, H., Vachhani, B., Akhani, J., Kanakiya, B., Gaur, Y., Prajapati, V.: Algorithms for speech segmentation at syllable-level for text-to-speech synthesis system in Gujarati. In: Oriental COCOSDA, New Delhi, India, pp. 1\u20137 (2013)","DOI":"10.1109\/ICSDA.2013.6709852"},{"key":"38_CR11","doi-asserted-by":"crossref","unstructured":"Rajpal, A., Shah, N.J., Zaki, M., Patil, H.A.: Quality assessment of voice converted speech using articulatory features. In: Proceeding ICASSP, New Orleans, pp. 5515\u20135519 (2017)","DOI":"10.1109\/ICASSP.2017.7953211"},{"key":"38_CR12","doi-asserted-by":"crossref","unstructured":"Rao, S.V., Shah, N.J., Patil, H.A.: Novel pre-processing using outlier removal in voice conversion. In: 9th ISCA Speech Synthesis Workshop, Sunnyvale, CA, USA, pp. 147\u2013152 (2016)","DOI":"10.21437\/SSW.2016-22"},{"key":"38_CR13","doi-asserted-by":"crossref","unstructured":"Reddy, P.R., Rout, K., Murty, K.S.R.: Query word retrieval from continuous speech using GMM posteriorgrams. In: SPCOM, Banglore, India, pp. 1\u20136 (2014)","DOI":"10.1109\/SPCOM.2014.6984011"},{"issue":"1\u20133","key":"38_CR14","doi-asserted-by":"publisher","first-page":"19","DOI":"10.1006\/dspr.1999.0361","volume":"10","author":"DA Reynolds","year":"2000","unstructured":"Reynolds, D.A., Quatieri, T.F., Dunn, R.B.: Speaker verification using adapted Gaussian mixture models. Digit. Signal Process. 10(1\u20133), 19\u201341 (2000)","journal-title":"Digit. Signal Process."},{"issue":"1","key":"38_CR15","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/TASSP.1978.1163055","volume":"26","author":"H Sakoe","year":"1978","unstructured":"Sakoe, H., Chiba, S.: Dynamic programming algorithm optimization for spoken word recognition. IEEE Trans. Acoust. Speech Signal Process. 26(1), 43\u201349 (1978)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"key":"38_CR16","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: Proceeding ICASSP, Florence, Italy, pp. 270\u2013274 (2014)","DOI":"10.1109\/ICASSP.2014.6853600"},{"key":"38_CR17","doi-asserted-by":"crossref","unstructured":"Shah, N.J., Patil, H.A.: Novel amplitude scaling method for bilinear frequency warping based voice conversion. In: Proceeding ICASSP, New Orleans, USA, pp. 5520\u20135524 (2017)","DOI":"10.1109\/ICASSP.2017.7953212"},{"key":"38_CR18","unstructured":"S\u00fcndermann, D., Bonafonte, A., Ney, H., H\u00f6ge, H.: A first step towards text-independent voice conversion. In: International Conference on Spoken Language Processing (ICSLP), South Korea, pp. 1\u20134 (2004)"},{"key":"38_CR19","doi-asserted-by":"crossref","unstructured":"Talesara, S., Patil, H.A., Patel, T., Sailor, H., Shah, N.: A novel Gaussian filter-based automatic labeling of speech data for TTS system in Gujarati language. In: Proceeding IALP, Urumqi, China, pp. 139\u2013142 (2013)","DOI":"10.1109\/IALP.2013.46"},{"key":"38_CR20","doi-asserted-by":"crossref","unstructured":"Zaki, M., Shah, N.J., Patil, H.A.: Effectiveness of multiscale fractal dimension-based phonetic segmentation in speech synthesis for low resource language. In: Proceeding IALP, Kuching, Borneo, Malaysia, pp. 103\u2013106 (2014)","DOI":"10.1109\/IALP.2014.6973508"},{"key":"38_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Glass, J.R.: Unsupervised spoken keyword spotting via segmental DTW on Gaussian posteriorgrams. In: IEEE Workshop on Automatic Speech Recognition & Understanding (ASRU), Merano, Italy, pp. 398\u2013403 (2009)","DOI":"10.1109\/ASRU.2009.5372931"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Machine Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-319-69900-4_38","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,26]],"date-time":"2025-06-26T20:11:38Z","timestamp":1750968698000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-319-69900-4_38"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017]]},"ISBN":["9783319698991","9783319699004"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-319-69900-4_38","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":"1 November 2017","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PReMI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Machine Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kolkata","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"India","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":"5 December 2017","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 December 2017","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"7","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"premi2017","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.isical.ac.in\/~premi17","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}