{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T02:54:32Z","timestamp":1743044072983,"version":"3.40.3"},"publisher-location":"Cham","reference-count":24,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030410049"},{"type":"electronic","value":"9783030410056"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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\/978-3-030-41005-6_25","type":"book-chapter","created":{"date-parts":[[2020,2,12]],"date-time":"2020-02-12T21:03:52Z","timestamp":1581541432000},"page":"369-382","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Measuring the Effect of Reverberation on Statistical Parametric Speech Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6833-9938","authenticated-orcid":false,"given":"Marvin","family":"Coto-Jim\u00e9nez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,2,12]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Black, A.W.: Unit selection and emotional speech. In: Eighth European Conference on Speech Communication and Technology (2003)","DOI":"10.21437\/Eurospeech.2003-473"},{"issue":"2","key":"25_CR2","doi-asserted-by":"publisher","first-page":"39","DOI":"10.3390\/biomimetics4020039","volume":"4","author":"M Coto-Jim\u00e9nez","year":"2019","unstructured":"Coto-Jim\u00e9nez, M.: Improving post-filtering of artificial speech using pre-trained LSTM neural networks. Biomimetics 4(2), 39 (2019)","journal-title":"Biomimetics"},{"issue":"01","key":"25_CR3","doi-asserted-by":"publisher","first-page":"1860008","DOI":"10.1142\/S021800141860008X","volume":"32","author":"M Coto-Jim\u00e9nez","year":"2018","unstructured":"Coto-Jim\u00e9nez, M., Goddard-Close, J.: LSTM deep neural networks postfiltering for enhancing synthetic voices. Int. J. Pattern Recognit Artif Intell. 32(01), 1860008 (2018)","journal-title":"Int. J. Pattern Recognit Artif Intell."},{"key":"25_CR4","volume-title":"Speech Synthesis and Recognition","author":"W Holmes","year":"2001","unstructured":"Holmes, W.: Speech Synthesis and Recognition. CRC Press, Boca Raton (2001)"},{"key":"25_CR5","unstructured":"ITU-T, R.P.: 862.1: Mapping function for transforming P. 862 raw result scores to MOS-LQO. International Telecommunication Union, Geneva, Switzerland, November 2003 (2003)"},{"issue":"2","key":"25_CR6","doi-asserted-by":"publisher","first-page":"285","DOI":"10.1109\/JSTSP.2013.2278492","volume":"8","author":"R Karhila","year":"2013","unstructured":"Karhila, R., Remes, U., Kurimo, M.: Noise in HMM-based speech synthesis adaptation: analysis, evaluation methods and experiments. IEEE J. Sel. Top. Signal Process. 8(2), 285\u2013295 (2013)","journal-title":"IEEE J. Sel. Top. Signal Process."},{"issue":"1","key":"25_CR7","doi-asserted-by":"publisher","first-page":"e006","DOI":"10.3989\/loquens.2014.006","volume":"1","author":"S King","year":"2014","unstructured":"King, S.: Measuring a decade of progress in text-to-speech. Loquens 1(1), e006 (2014)","journal-title":"Loquens"},{"key":"25_CR8","unstructured":"Kominek, J., Black, A.W.: The CMU arctic speech databases. In: Fifth ISCA Workshop on Speech Synthesis (2004)"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Lee, J., Song, K., Noh, K., Park, T.J., Chang, J.H.: DNN based multi-speaker speech synthesis with temporal auxiliary speaker id embedding. In: 2019 International Conference on Electronics, Information, and Communication (ICEIC), pp. 1\u20134. IEEE (2019)","DOI":"10.23919\/ELINFOCOM.2019.8706390"},{"key":"25_CR10","unstructured":"Moreno Pimentel, J., et al.: Effects of noise on a speaker-adaptive statistical speech synthesis system (2014)"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"\u00d6zt\u00fcrk, M.G., Ulusoy, O., Demiroglu, C.: DNN-based speaker-adaptive postfiltering with limited adaptation data for statistical speech synthesis systems. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7030\u20137034. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683714"},{"key":"25_CR12","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3617\u20133621. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683143"},{"issue":"10","key":"25_CR13","first-page":"755","volume":"50","author":"AW Rix","year":"2002","unstructured":"Rix, A.W., Hollier, M.P., Hekstra, A.P., Beerends, J.G.: Perceptual evaluation of speech quality (PESQ) the new itu standard for end-to-end speech quality assessment Part I-time-delay compensation. J. Audio Eng. Soc. 50(10), 755\u2013764 (2002)","journal-title":"J. Audio Eng. Soc."},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Stewart, R., Sandler, M.: Database of omnidirectional and B-format room impulse responses. In: 2010 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 165\u2013168. IEEE (2010)","DOI":"10.1109\/ICASSP.2010.5496083"},{"issue":"5","key":"25_CR15","doi-asserted-by":"publisher","first-page":"1234","DOI":"10.1109\/JPROC.2013.2251852","volume":"101","author":"K Tokuda","year":"2013","unstructured":"Tokuda, K., Nankaku, Y., Toda, T., Zen, H., Yamagishi, J., Oura, K.: Speech synthesis based on hidden Markov models. Proc. IEEE 101(5), 1234\u20131252 (2013)","journal-title":"Proc. IEEE"},{"key":"25_CR16","unstructured":"Tokuda, K., Zen, H., Black, A.W.: An HMM-based speech synthesis system applied to English. In: IEEE Speech Synthesis Workshop, pp. 227\u2013230 (2002)"},{"key":"25_CR17","doi-asserted-by":"crossref","unstructured":"Valentini-Botinhao, C., Wang, X., Takaki, S., Yamagishi, J.: Speech enhancement for a noise-robust text-to-speech synthesis system using deep recurrent neural networks. In: Interspeech, pp. 352\u2013356 (2016)","DOI":"10.21437\/Interspeech.2016-159"},{"issue":"8","key":"25_CR18","doi-asserted-by":"publisher","first-page":"1420","DOI":"10.1109\/TASLP.2018.2828980","volume":"26","author":"C Valentini-Botinhao","year":"2018","unstructured":"Valentini-Botinhao, C., Yamagishi, J.: Speech enhancement of noisy and reverberant speech for text-to-speech. IEEE\/ACM Trans. Audio Speech Lang. Process. 26(8), 1420\u20131433 (2018)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"25_CR19","doi-asserted-by":"crossref","unstructured":"Valin, J.M., Skoglund, J.: LPCNet: improving neural speech synthesis through linear prediction. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5891\u20135895. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"25_CR20","doi-asserted-by":"crossref","unstructured":"Wang, X., Lorenzo-Trueba, J., Takaki, S., Juvela, L., Yamagishi, J.: A comparison of recent waveform generation and acoustic modeling methods for neural-network-based speech synthesis. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4804\u20134808. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461452"},{"key":"25_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.specom.2017.11.002","volume":"96","author":"X Wang","year":"2018","unstructured":"Wang, X., Takaki, S., Yamagishi, J.: Investigating very deep highway networks for parametric speech synthesis. Speech Commun. 96, 1\u20139 (2018)","journal-title":"Speech Commun."},{"key":"25_CR22","unstructured":"Wen, J.Y., Gaubitch, N.D., Habets, E.A., Myatt, T., Naylor, P.A.: Evaluation of speech dereverberation algorithms using the MARDY database. In: Proceedings of the International Workshop Acoustic Echo Noise Control (IWAENC). Citeseer (2006)"},{"key":"25_CR23","unstructured":"Zen, H., et al.: The HMM-based speech synthesis system (HTS) version 2.0. In: SSW, pp. 294\u2013299. Citeseer (2007)"},{"key":"25_CR24","unstructured":"Zen, H., et al.: Recent development of the HMM-based speech synthesis system (HTS) (2009)"}],"container-title":["Communications in Computer and Information Science","High Performance Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-41005-6_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,15]],"date-time":"2022-10-15T11:11:34Z","timestamp":1665832294000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-41005-6_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030410049","9783030410056"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-41005-6_25","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"12 February 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CARLA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Latin American High Performance Computing Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Turrialba","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Costa Rica","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":"25 September 2019","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2019","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"carla2019","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/carla2019.ccarla.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"OCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"62","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"52% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}