{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T16:14:11Z","timestamp":1771949651123,"version":"3.50.1"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,5,1]],"date-time":"2019-05-01T00:00:00Z","timestamp":1556668800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2019,5]]},"DOI":"10.1109\/icassp.2019.8683846","type":"proceedings-article","created":{"date-parts":[[2019,4,17]],"date-time":"2019-04-17T16:01:56Z","timestamp":1555516916000},"page":"6925-6929","source":"Crossref","is-referenced-by-count":14,"title":["Casting to Corpus: Segmenting and Selecting Spontaneous Dialogue for Tts with a Cnn-lstm Speaker-dependent Breath Detector"],"prefix":"10.1109","author":[{"given":"Eva","family":"Szekely","sequence":"first","affiliation":[]},{"given":"Gustav Eje","family":"Henter","sequence":"additional","affiliation":[]},{"given":"Joakim","family":"Gustafson","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-018-0270-6"},{"key":"ref11","first-page":"1","article-title":"Automatic detection of inhalation breath pauses for improved pause modelling in HMM-TTS","volume":"8","author":"braunschweiler","year":"2013","journal-title":"Proc of SSW6"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-66429-3_9"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2018.01.008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2014.04.002"},{"key":"ref15","first-page":"6","article-title":"Classification and clustering of clicks, breathing and silences within speech pauses","volume":"5","author":"canal","year":"2018","journal-title":"Proc Laughter Workshop"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2009.04.004"},{"key":"ref17","first-page":"1","article-title":"Respiratory constraints in verbal and non-verbal communication","volume":"8","author":"w?odarczak","year":"2017","journal-title":"Front Psychol"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3115\/1075434.1075437"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1098\/rstb.2013.0399"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1507"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2017.01.002"},{"key":"ref6","first-page":"581","article-title":"Robustness of HMM-based speech synthesis","author":"yamagishi","year":"2008","journal-title":"Proc INTERSPEECH"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461870"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472655"},{"key":"ref7","first-page":"1821","article-title":"Automatic sentence selection from speech corpora including diverse speech for improved HMM-TTS synthesis quality","author":"braunschweiler","year":"2011","journal-title":"Proc INTERSPEECH"},{"key":"ref2","article-title":"Statistical parametric speech synthesis using conversational data and phenomena","author":"dall","year":"2017","journal-title":"Ph D Dissertation"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2018-34"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2011.08.001"},{"key":"ref20","first-page":"1522","article-title":"Deep convolutional recurrent neural network for rare acoustic event detection","author":"amiriparian","year":"2018","journal-title":"Proc DAGA"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-434"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123371"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846324"},{"key":"ref23","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc NIPS"},{"key":"ref26","first-page":"941","article-title":"Improved overlapped speech handling for speaker diarization","author":"boakye","year":"2011","journal-title":"Proc In-terspeech"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2006.889750"}],"event":{"name":"ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Brighton, United Kingdom","start":{"date-parts":[[2019,5,12]]},"end":{"date-parts":[[2019,5,17]]}},"container-title":["ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/8671773\/8682151\/08683846.pdf?arnumber=8683846","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,7,14]],"date-time":"2022-07-14T23:18:50Z","timestamp":1657840730000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8683846\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,5]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp.2019.8683846","relation":{},"subject":[],"published":{"date-parts":[[2019,5]]}}}