{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,11]],"date-time":"2024-09-11T08:23:11Z","timestamp":1726042991368},"publisher-location":"Cham","reference-count":23,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030299323"},{"type":"electronic","value":"9783030299330"}],"license":[{"start":{"date-parts":[[2019,8,30]],"date-time":"2019-08-30T00:00:00Z","timestamp":1567123200000},"content-version":"tdm","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":[[2020]]},"DOI":"10.1007\/978-3-030-29933-0_23","type":"book-chapter","created":{"date-parts":[[2019,8,29]],"date-time":"2019-08-29T09:27:21Z","timestamp":1567070841000},"page":"271-282","update-policy":"http:\/\/dx.doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Phoneme Aware Speech Synthesis via Fine Tune Transfer Learning with a Tacotron Spectrogram Prediction Network"],"prefix":"10.1007","author":[{"given":"Jordan J.","family":"Bird","sequence":"first","affiliation":[]},{"given":"Anik\u00f3","family":"Ek\u00e1rt","sequence":"additional","affiliation":[]},{"given":"Diego R.","family":"Faria","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2019,8,30]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Turing, A.M.: Computing Machinery and Intelligence (1950)","key":"23_CR1","DOI":"10.1093\/mind\/LIX.236.433"},{"issue":"7","key":"23_CR2","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1111\/j.1467-9566.2009.01176.x","volume":"31","author":"L Locock","year":"2009","unstructured":"Locock, L., Ziebland, S., Dumelow, C.: Biographical disruption, abruption and repair in the context of motor neurone disease. Sociol. Health Illn. 31(7), 1043\u20131058 (2009)","journal-title":"Sociol. Health Illn."},{"issue":"1","key":"23_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1250\/ast.33.1","volume":"33","author":"J Yamagishi","year":"2012","unstructured":"Yamagishi, J., Veaux, C., King, S., Renals, S.: Speech synthesis technologies for individuals with vocal disabilities: voice banking and reconstruction. Acoust. Sci. Technol. 33(1), 1\u20135 (2012)","journal-title":"Acoust. Sci. Technol."},{"key":"23_CR4","doi-asserted-by":"publisher","DOI":"10.4324\/9780203994634","volume-title":"A History of the English Language","author":"AC Baugh","year":"1993","unstructured":"Baugh, A.C., Cable, T.: A History of the English Language. Routledge, Abingdon (1993)"},{"key":"23_CR5","doi-asserted-by":"publisher","DOI":"10.4324\/9781315845371","volume-title":"Anglo Saxon England and the Norman Conquest","author":"HR Loyn","year":"2014","unstructured":"Loyn, H.R.: Anglo Saxon England and the Norman Conquest. Routledge, London (2014)"},{"key":"23_CR6","volume-title":"An Introduction to Language","author":"V Fromkin","year":"2006","unstructured":"Fromkin, V., Rodman, R., Hyams, N.: An Introduction to Language. Cengage, Boston (2006)"},{"key":"23_CR7","volume-title":"Principles of Voice Production","author":"IR Titze","year":"1994","unstructured":"Titze, I.R., Martin, D.W.: Principles of Voice Production. Prentice-Hall, Englewood Cliffs (1994)"},{"unstructured":"Menzel, W., Atwell, E., Bonaventura, P., Herron, D., Howarth, P., Morton, R., Souter, C.: The ISLE corpus of non-native spoken English. In: Proceedings of LREC 2000: Language Resources and Evaluation Conference, vol. 2, pp.\u00a0957\u2013964. European Language Resources Association (2000)","key":"23_CR8"},{"doi-asserted-by":"crossref","unstructured":"Bird, J.J., Wanner, E., Ekart, A., Faria, D.R.: Phoneme aware speech recognition through evolutionary optimisation. In: The Genetic and Evolutionary Computation Conference, GECCO (2019)","key":"23_CR9","DOI":"10.1145\/3319619.3321951"},{"doi-asserted-by":"crossref","unstructured":"Wang, Y., Skerry-Ryan, R., Stanton, D., Wu, Y., Weiss, R.J., Jaitly, N., Yang, Z., Xiao, Y., Chen, Z., Bengio, S., et al.: Tacotron: Towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","key":"23_CR10","DOI":"10.21437\/Interspeech.2017-1452"},{"doi-asserted-by":"crossref","unstructured":"Tachibana, H., Uenoyama, K., Aihara, S.: Efficiently trainable text-to-speech system based on deep convolutional networks with guided attention. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a04784\u20134788. IEEE (2018)","key":"23_CR11","DOI":"10.1109\/ICASSP.2018.8461829"},{"doi-asserted-by":"crossref","unstructured":"Sak, H., Senior, A., Beaufays, F.: Long short-term memory recurrent neural network architectures for large scale acoustic modeling. In: Fifteenth Annual Conference of the International Speech Communication Association (2014)","key":"23_CR12","DOI":"10.21437\/Interspeech.2014-80"},{"doi-asserted-by":"crossref","unstructured":"Li, X., Wu, X.: Constructing long short-term memory based deep recurrent neural networks for large vocabulary speech recognition. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a04520\u20134524. IEEE (2015)","key":"23_CR13","DOI":"10.1109\/ICASSP.2015.7178826"},{"unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint arXiv:1409.0473 (2014)","key":"23_CR14"},{"issue":"2","key":"23_CR15","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1109\/TASSP.1984.1164317","volume":"32","author":"D Griffin","year":"1984","unstructured":"Griffin, D., Lim, J.: Signal estimation from modified short-time fourier transform. IEEE Trans. Acoust. Speech Signal Process. 32(2), 236\u2013243 (1984)","journal-title":"IEEE Trans. Acoust. Speech Signal Process."},{"issue":"1","key":"23_CR16","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1016\/j.dsp.2007.12.004","volume":"19","author":"E Sejdi\u0107","year":"2009","unstructured":"Sejdi\u0107, E., Djurovi\u0107, I., Jiang, J.: Time-frequency feature representation using energy concentration: an overview of recent advances. Digit. Signal Process. 19(1), 153\u2013183 (2009)","journal-title":"Digit. Signal Process."},{"unstructured":"Skerry-Ryan, R., Battenberg, E., Xiao, Y., Wang, Y., Stanton, D., Shor, J., Weiss, R.\u00a0J., Clark, R., Saurous, R.A.: Towards end-to-end prosody transfer for expressive speech synthesis with tacotron. In: International Conference on Machine Learning, pp.\u00a04693\u20134702 (2018)","key":"23_CR17"},{"doi-asserted-by":"crossref","unstructured":"Zhang, M., Wang, X., Fang, F., Li, H., Yamagishi, J.: Joint training framework for text-to-speech and voice conversion using multi-source tacotron and wavenet. arXiv preprint arXiv:1903.12389 (2019)","key":"23_CR18","DOI":"10.21437\/Interspeech.2019-1357"},{"issue":"2","key":"23_CR19","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1109\/MSP.2003.1184339","volume":"20","author":"J Bormans","year":"2003","unstructured":"Bormans, J., Gelissen, J., Perkis, A.: MPEG-21: the 21st century multimedia framework. IEEE Signal Process. Mag. 20(2), 53\u201362 (2003)","journal-title":"IEEE Signal Process. Mag."},{"unstructured":"Wang, A., et\u00a0al.: An industrial strength audio search algorithm. In: ISMIR, vol.\u00a02003, pp.\u00a07\u201313, Washington, DC (2003)","key":"23_CR20"},{"unstructured":"IEEE.: IEEE Transactions on Audio and Electroacoustics, vol.\u00a021. IEEE (1973)","key":"23_CR21"},{"doi-asserted-by":"crossref","unstructured":"Yochanang, K., Daengsi, T., Triyason, T., Wuttidittachotti, P.: A comparative study of VoIP quality measurement from G. 711 and G. 729 using PESQ and thai speech. In: International Conference on Advances in Information Technology, pp. 242\u2013255. Springer (2013)","key":"23_CR22","DOI":"10.1007\/978-3-319-03783-7_22"},{"doi-asserted-by":"crossref","unstructured":"Yankelovich, N., Kaplan, J., Provino, J., Wessler, M., DiMicco, J.M.: Improving audio conferencing: are two ears better than one? In: Proceedings of the 2006 20th Anniversary Conference on Computer Supported Cooperative Work, pp. 333\u2013342. ACM (2006)","key":"23_CR23","DOI":"10.1145\/1180875.1180926"}],"container-title":["Advances in Intelligent Systems and Computing","Advances in Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-29933-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T22:00:27Z","timestamp":1664229627000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-29933-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,8,30]]},"ISBN":["9783030299323","9783030299330"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-29933-0_23","relation":{},"ISSN":["2194-5357","2194-5365"],"issn-type":[{"type":"print","value":"2194-5357"},{"type":"electronic","value":"2194-5365"}],"subject":[],"published":{"date-parts":[[2019,8,30]]},"assertion":[{"value":"30 August 2019","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"UKCI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"UK Workshop on Computational Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Portsmouth","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2019","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ukci2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}