{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T14:40:39Z","timestamp":1725806439872},"reference-count":34,"publisher":"IEEE","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2018,11]]},"DOI":"10.1109\/iscslp.2018.8706608","type":"proceedings-article","created":{"date-parts":[[2019,5,20]],"date-time":"2019-05-20T22:58:35Z","timestamp":1558393115000},"page":"349-353","source":"Crossref","is-referenced-by-count":4,"title":["LSTM-Based Pitch Range Estimation from Spectral Information of Brief Speech Input"],"prefix":"10.1109","author":[{"given":"Wei","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Qi","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yanlu","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"journal-title":"Praat Doing phonetics by computer","year":"2011","author":"boersma","key":"ref33"},{"key":"ref32","article-title":"The Kaldi speech recognition toolkit","author":"povey","year":"0","journal-title":"IDIAP"},{"key":"ref31","first-page":"798","article-title":"Update progress of Sinohear: advanced Mandarin LVCSR system at NLPR","author":"gao","year":"2000","journal-title":"Proceedings of Interspeech"},{"key":"ref30","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proceedings of Advances in Neural Information Processing Systems"},{"journal-title":"Keras","year":"2013","author":"charles","key":"ref34"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1186\/1687-6180-2012-67"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2010.5734096"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2010.5734097"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1121\/1.3050322"},{"key":"ref14","article-title":"Influence of spectral cues on the perception of pitch height","author":"kuang","year":"2015","journal-title":"Proceeding of ICPhS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/SpeechProsody.2016-218"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-1483"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1121\/1.3488347"},{"journal-title":"A study of correlation between voice quality measures and tonal F0 parameters based on monosyllabic Chinese corpora","year":"2016","author":"li","key":"ref18"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ISCSLP.2016.7918472"},{"key":"ref28","article-title":"Show and tell: A neural image caption generator","author":"vinyals","year":"2015","journal-title":"Proceedings of IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref4","first-page":"650","article-title":"Modeling pitch range variation within and across speakers: Predicting F0 targets when ‘speaking up’","author":"shriberg","year":"1996","journal-title":"Proceedings of ICSLP"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/NNSP.2002.1030094"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.4714351"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1121\/1.1841751"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-74122-0_18"},{"key":"ref8","first-page":"135138","article-title":"Detecting changes in key and range for the automatic modelling and coding of intonation","author":"looze","year":"2008","journal-title":"Proceedings of Speech Prosody"},{"key":"ref7","first-page":"173","article-title":"Perceptual judgments of pitch range","author":"carlson","year":"2004","journal-title":"Proceedings of Speech Prosody"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1017\/CBO9781139166621"},{"key":"ref9","article-title":"Automatic estimation of pitch range through distribution fitting","author":"frid","year":"2010","journal-title":"Proceedings of the Meeting of Fonetik"},{"journal-title":"A Dictionary of Phonetics and Phonology","year":"1996","author":"trask","key":"ref1"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TNN.1994.8753425"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1037\/0096-1523.9.6.864"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"journal-title":"Intonational Phonology","year":"1996","author":"ladd","key":"ref24"},{"key":"ref23","first-page":"11691172","article-title":"Pitch range modelling: Linguistic dimensions of variation","author":"patterson","year":"1999","journal-title":"Proceedings of ICPhS"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-24797-2_2"},{"key":"ref25","article-title":"A guide to recurrent neural networks and backpropagation","author":"boden","year":"2002","journal-title":"The Dallas Project Sics Technical Report T2002 03 SICS"}],"event":{"name":"2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)","start":{"date-parts":[[2018,11,26]]},"location":"Taipei City, Taiwan","end":{"date-parts":[[2018,11,29]]}},"container-title":["2018 11th International Symposium on Chinese Spoken Language Processing (ISCSLP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8701133\/8706262\/08706608.pdf?arnumber=8706608","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,8,23]],"date-time":"2020-08-23T23:09:29Z","timestamp":1598224169000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8706608\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11]]},"references-count":34,"URL":"https:\/\/doi.org\/10.1109\/iscslp.2018.8706608","relation":{},"subject":[],"published":{"date-parts":[[2018,11]]}}}