{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T10:52:42Z","timestamp":1743072762255,"version":"3.40.3"},"publisher-location":"Cham","reference-count":28,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030878016"},{"type":"electronic","value":"9783030878023"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-87802-3_31","type":"book-chapter","created":{"date-parts":[[2021,9,21]],"date-time":"2021-09-21T23:36:52Z","timestamp":1632267412000},"page":"336-347","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Word-Level Style Control for Expressive, Non-attentive Speech Synthesis"],"prefix":"10.1007","author":[{"given":"Konstantinos","family":"Klapsas","sequence":"first","affiliation":[]},{"given":"Nikolaos","family":"Ellinas","sequence":"additional","affiliation":[]},{"given":"June Sig","family":"Sung","sequence":"additional","affiliation":[]},{"given":"Hyoungmin","family":"Park","sequence":"additional","affiliation":[]},{"given":"Spyros","family":"Raptis","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,9,22]]},"reference":[{"key":"31_CR1","doi-asserted-by":"crossref","unstructured":"Chu, W., Alwan, A.: Reducing F0 frame error of F0 tracking algorithms under noisy conditions with an unvoiced\/voiced classification frontend. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3969\u20133972. IEEE (2009)","DOI":"10.1109\/ICASSP.2009.4960497"},{"key":"31_CR2","doi-asserted-by":"publisher","unstructured":"Ellinas, N., et al.: High quality streaming speech synthesis with low, sentence-length-independent latency. In: Proceedings of the Interspeech (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2464","DOI":"10.21437\/Interspeech.2020-2464"},{"key":"31_CR3","doi-asserted-by":"crossref","unstructured":"Hayashi, T., Watanabe, S., Toda, T., Takeda, K., Toshniwal, S., Livescu, K.: Pre-trained text embeddings for enhanced text-to-speech synthesis. In: Proceedings of the Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-3177"},{"key":"31_CR4","doi-asserted-by":"crossref","unstructured":"Hono, Y., et al.: Hierarchical multi-grained generative model for expressive speech synthesis. In: Proceedings of the Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-2477"},{"key":"31_CR5","unstructured":"Hsu, W.N., et al.: Hierarchical generative modeling for controllable speech synthesis. In: Proceedings of the International Conference on Learning Representations (ICLR) (2019)"},{"key":"31_CR6","doi-asserted-by":"crossref","unstructured":"Karlapati, S., Moinet, A., Joly, A., Klimkov, V., Saez-Trigueros, D., Drugman, T.: CopyCat: many-to-many fine-grained prosody transfer for neural text-to-speech. In: Proceedings of the Interspeech (2020)","DOI":"10.21437\/Interspeech.2020-1251"},{"key":"31_CR7","unstructured":"Kenter, T., Wan, V., Chan, C.A., Clark, R., Vit, J.: CHiVE: varying prosody in speech synthesis with a linguistically driven dynamic hierarchical conditional variational network. In: Proceedings of the 36th International Conference on Machine Learning (2019)"},{"key":"31_CR8","doi-asserted-by":"crossref","unstructured":"King, S., Karaiskos, V.: The Blizzard challenge 2013. In: Blizzard Challenge Workshop (2013)","DOI":"10.21437\/Blizzard.2013-1"},{"key":"31_CR9","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of the International Conference on Learning Representations (ICLR). arXiv:1412.6980 (2015)"},{"key":"31_CR10","doi-asserted-by":"crossref","unstructured":"Klimkov, V., Ronanki, S., Rohnke, J., Drugman, T.: Fine-grained robust prosody transfer for single-speaker neural text-to-speech. In: Proceedings of the Interspeech (2019)","DOI":"10.21437\/Interspeech.2019-2571"},{"key":"31_CR11","doi-asserted-by":"crossref","unstructured":"Kubichek, R.: Mel-cepstral distance measure for objective speech quality assessment. In: Proceedings of IEEE Pacific Rim Conference on Communications Computers and Signal Processing, vol. 1, pp. 125\u2013128 (1993)","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"31_CR12","doi-asserted-by":"crossref","unstructured":"Lee, Y., Kim, T.: Robust and fine-grained prosody control of end-to-end speech synthesis. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5911\u20135915. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683501"},{"key":"31_CR13","doi-asserted-by":"crossref","unstructured":"Luong, T., Pham, H., Manning, C.D.: Effective approaches to attention-based neural machine translation. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 1412\u20131421. Association for Computational Linguistics, September 2015","DOI":"10.18653\/v1\/D15-1166"},{"key":"31_CR14","doi-asserted-by":"crossref","unstructured":"Raptis, S., Tsiakoulis, P., Chalamandaris, A., Karabetsos, S.: Expressive speech synthesis for story telling: the INNOETICS\u2019 entry to the blizzard challenge 2016. In: Proceedings of the Blizzard Challenge (2016)","DOI":"10.21437\/Blizzard.2016-13"},{"key":"31_CR15","unstructured":"Shen, J., et al.: Non-attentive Tacotron: robust and controllable neural TTS synthesis including unsupervised duration modeling. arXiv:2010.04301 (2020)"},{"key":"31_CR16","doi-asserted-by":"crossref","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4779\u20134783. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"31_CR17","unstructured":"Skerry-Ryan, R., et al.: Towards end-to-end prosody transfer for expressive speech synthesis with Tacotron. In: Proceedings of the 35th International Conference on Machine Learning, pp. 4693\u20134702 (2018)"},{"key":"31_CR18","doi-asserted-by":"crossref","unstructured":"Stanton, D., Wang, Y., Skerry-Ryan, R.: Predicting expressive speaking style from text in end-to-end speech synthesis. In: 2018 IEEE Spoken Language Technology Workshop (SLT), pp. 595\u20135602 (2018)","DOI":"10.1109\/SLT.2018.8639682"},{"key":"31_CR19","doi-asserted-by":"crossref","unstructured":"Sun, G., Zen, H., Weiss, R.J., Wu, Y., Zhang, Y., Cao, Y.: Fully-hierarchical fine-grained prosody modeling for interpretable speech synthesis. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053520"},{"key":"31_CR20","doi-asserted-by":"crossref","unstructured":"Sun, G., et al.: Generating diverse and natural text-to-speech samples using a quantized fine-grained VAE and autoregressive prosody prior. In: 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6699\u20136703 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053436"},{"key":"31_CR21","doi-asserted-by":"publisher","unstructured":"Valin, J., Skoglund, J.: LPCNet: improving neural speech synthesis through linear prediction. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5891\u20135895. IEEE (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682804","DOI":"10.1109\/ICASSP.2019.8682804"},{"key":"31_CR22","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. In: Proceedings of the Interspeech, pp. 4006\u20134010 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"31_CR23","unstructured":"Wang, Y., et al.: Uncovering latent style factors for expressive speech synthesis. In: ML4Audio Workshop, NIPS (2017)"},{"key":"31_CR24","unstructured":"Wang, Y., et al.: Style tokens: unsupervised style modeling, control and transfer in end-to-end speech synthesis. In: ICML (2018)"},{"key":"31_CR25","doi-asserted-by":"publisher","unstructured":"Xiao, Y., He, L., Ming, H., Soong, F.K.: Improving prosody with linguistic and BERT derived features in multi-speaker based mandarin Chinese neural TTS. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6704\u20136708. IEEE (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054337","DOI":"10.1109\/ICASSP40776.2020.9054337"},{"key":"31_CR26","unstructured":"Young, S., et al.: The HTK Book (version 3.5a) (2015)"},{"key":"31_CR27","doi-asserted-by":"crossref","unstructured":"Yu, C., et al.: DurIAN: duration informed attention network for multimodal synthesis. arXiv:1909.01700 (2019)","DOI":"10.21437\/Interspeech.2020-2968"},{"key":"31_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y.J., Pan, S., He, L., Ling, Z.: Learning latent representations for style control and transfer in end-to-end speech synthesis. In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6945\u20136949. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683623"}],"container-title":["Lecture Notes in Computer Science","Speech and Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87802-3_31","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,8]],"date-time":"2024-09-08T17:39:46Z","timestamp":1725817186000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87802-3_31"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030878016","9783030878023"],"references-count":28,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87802-3_31","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"22 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"SPECOM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Speech and Computer","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"St Petersburg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Russia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 September 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"specom2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/specom.nw.ru\/2021\/","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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"163","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":"74","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":"45% - 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":"3.5","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":"5.5","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)"}},{"value":"The conference was held online due to the COVID-19 pandemic.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}