{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:07:55Z","timestamp":1742911675765,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819981250"},{"type":"electronic","value":"9789819981267"}],"license":[{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T00:00:00Z","timestamp":1699833600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8126-7_20","type":"book-chapter","created":{"date-parts":[[2023,11,24]],"date-time":"2023-11-24T08:05:19Z","timestamp":1700813119000},"page":"252-264","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Cross-Lingual Knowledge Distillation via\u00a0Flow-Based Voice Conversion for\u00a0Robust Polyglot Text-to-Speech"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7974-9887","authenticated-orcid":false,"given":"Dariusz","family":"Piotrowski","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-8759-803X","authenticated-orcid":false,"given":"Renard","family":"Korzeniowski","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6574-5607","authenticated-orcid":false,"given":"Alessio","family":"Falai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4763-8381","authenticated-orcid":false,"given":"Sebastian","family":"Cygert","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-0756-4118","authenticated-orcid":false,"given":"Kamil","family":"Pokora","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9910-6598","authenticated-orcid":false,"given":"Georgi","family":"Tinchev","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0617-1340","authenticated-orcid":false,"given":"Ziyao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3444-7287","authenticated-orcid":false,"given":"Kayoko","family":"Yanagisawa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,11,13]]},"reference":[{"key":"20_CR1","doi-asserted-by":"publisher","unstructured":"Bilinski, P., et al.: Creating new voices using normalizing flows. In: Proceedings of Interspeech 2022, pp. 2958\u20132962 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10195","DOI":"10.21437\/Interspeech.2022-10195"},{"key":"20_CR2","doi-asserted-by":"publisher","unstructured":"Comini, G., Huybrechts, G., Ribeiro, M.S., Gabry\u015b, A., Lorenzo-Trueba, J.: Low-data? No problem: low-resource, language-agnostic conversational text-to-speech via F0-conditioned data augmentation. In: Proceedings of Interspeech 2022, pp. 1946\u20131950 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10338","DOI":"10.21437\/Interspeech.2022-10338"},{"key":"20_CR3","doi-asserted-by":"publisher","unstructured":"Ellinas, N., et al.: Cross-lingual text-to-speech with flow-based voice conversion for improved pronunciation (2022). https:\/\/doi.org\/10.48550\/ARXIV.2210.17264. https:\/\/arxiv.org\/abs\/2210.17264","DOI":"10.48550\/ARXIV.2210.17264"},{"key":"20_CR4","doi-asserted-by":"publisher","unstructured":"Finkelstein, L., et al.: Training text-to-speech systems from synthetic data: a practical approach for accent transfer tasks. In: Proceedings of Interspeech 2022, pp. 4571\u20134575 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-10115","DOI":"10.21437\/Interspeech.2022-10115"},{"key":"20_CR5","doi-asserted-by":"publisher","unstructured":"Hwang, M.J., Yamamoto, R., Song, E., Kim, J.M.: TTS-by-TTS: TTS-driven data augmentation for fast and high-quality speech synthesis. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6598\u20136602 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414408","DOI":"10.1109\/ICASSP39728.2021.9414408"},{"key":"20_CR6","unstructured":"ITUR Recommendation: BS.1534-1. method for the subjective assessment of intermediate sound quality (MUSHRA). International Telecommunications Union, Geneva (2001)"},{"key":"20_CR7","doi-asserted-by":"publisher","unstructured":"Jiao, Y., Gabry\u015b, A., Tinchev, G., Putrycz, B., Korzekwa, D., Klimkov, V.: Universal neural vocoding with parallel wavenet. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6044\u20136048 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9414444","DOI":"10.1109\/ICASSP39728.2021.9414444"},{"key":"20_CR8","doi-asserted-by":"publisher","unstructured":"Karlapati, S., et al.: CopyCat2: a single model for multi-speaker TTS and many-to-many fine-grained prosody transfer. In: Proceedings of Interspeech 2022, pp. 3363\u20133367 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-67","DOI":"10.21437\/Interspeech.2022-67"},{"key":"20_CR9","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: generative adversarial networks for efficient and high fidelity speech synthesis. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 17022\u201317033. Curran Associates, Inc. (2020)"},{"key":"20_CR10","doi-asserted-by":"publisher","unstructured":"Latorre, J., Bailleul, C., Morrill, T., Conkie, A., Stylianou, Y.: Combining speakers of multiple languages to improve quality of neural voices. In: Proceedings of 11th ISCA Speech Synthesis Workshop (SSW 2011), pp. 37\u201342 (2021). https:\/\/doi.org\/10.21437\/SSW.2021-7","DOI":"10.21437\/SSW.2021-7"},{"key":"20_CR11","doi-asserted-by":"crossref","unstructured":"Luo, R., et al.: Lightspeech: lightweight and fast text to speech with neural architecture search. In: ICASSP 2021, pp. 5699\u20135703 (2021)","DOI":"10.1109\/ICASSP39728.2021.9414403"},{"key":"20_CR12","doi-asserted-by":"publisher","unstructured":"Merritt, T., et al.: Text-free non-parallel many-to-many voice conversion using normalising flow. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6782\u20136786 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746368","DOI":"10.1109\/ICASSP43922.2022.9746368"},{"key":"20_CR13","doi-asserted-by":"publisher","unstructured":"Miao, C., Liang, S., Chen, M., Ma, J., Wang, S., Xiao, J.: Flow-TTS: a non-autoregressive network for text to speech based on flow. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7209\u20137213 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9054484","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"20_CR14","doi-asserted-by":"publisher","unstructured":"Nachmani, E., Wolf, L.: Unsupervised polyglot text-to-speech. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7055\u20137059 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8683519","DOI":"10.1109\/ICASSP.2019.8683519"},{"key":"20_CR15","unstructured":"Popov, V., Vovk, I., Gogoryan, V., Sadekova, T., Kudinov, M.S., Wei, J.: Diffusion-based voice conversion with fast maximum likelihood sampling scheme. In: International Conference on Learning Representations (2022)"},{"key":"20_CR16","unstructured":"Qian, K., Zhang, Y., Chang, S., Yang, X., Hasegawa-Johnson, M.: AutoVC: zero-shot voice style transfer with only autoencoder loss. In: Proceedings of Machine Learning Research, Long Beach, California, USA, vol. 97, pp. 5210\u20135219. PMLR (2019)"},{"key":"20_CR17","doi-asserted-by":"publisher","unstructured":"Ramani, B., Actlin Jeeva, M.P., Vijayalakshmi, P., Nagarajan, T.: Voice conversion-based multilingual to polyglot speech synthesizer for Indian languages. In: 2013 IEEE International Conference of IEEE Region 10 (TENCON 2013), pp. 1\u20134 (2013). https:\/\/doi.org\/10.1109\/TENCON.2013.6719019","DOI":"10.1109\/TENCON.2013.6719019"},{"key":"20_CR18","unstructured":"Ren, Y., et al.: Fastspeech 2: fast and high-quality end-to-end text to speech. In: International Conference on Learning Representations (2021)"},{"key":"20_CR19","doi-asserted-by":"publisher","unstructured":"Sanchez, A., Falai, A., Zhang, Z., Angelini, O., Yanagisawa, K.: Unify and conquer: how phonetic feature representation affects polyglot text-to-speech (TTS). In: Proceedings of Interspeech 2022, pp. 2963\u20132967 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-233","DOI":"10.21437\/Interspeech.2022-233"},{"key":"20_CR20","doi-asserted-by":"publisher","unstructured":"Shah, R., et al.: Non-autoregressive TTS with explicit duration modelling for low-resource highly expressive speech. In: Proceedings of 11th ISCA Speech Synthesis Workshop (SSW 2011), pp. 96\u2013101 (2021). https:\/\/doi.org\/10.21437\/SSW.2021-17","DOI":"10.21437\/SSW.2021-17"},{"key":"20_CR21","doi-asserted-by":"publisher","unstructured":"Sharma, M., Kenter, T., Clark, R.: StrawNet: self-training WaveNet for TTS in low-data regimes. In: Proceedings of Interspeech 2020, pp. 3550\u20133554 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-1437","DOI":"10.21437\/Interspeech.2020-1437"},{"key":"20_CR22","doi-asserted-by":"publisher","unstructured":"Shen, J., et al.: Natural TTS synthesis by conditioning WaveNet on Mel spectrogram predictions. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4779\u20134783 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8461368","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"20_CR23","doi-asserted-by":"publisher","unstructured":"Sun, L., Wang, H., Kang, S., Li, K., Meng, H.: Personalized, cross-lingual TTS using phonetic posteriorgrams. In: Interspeech 2016, pp. 322\u2013326 (2016). https:\/\/doi.org\/10.21437\/Interspeech.2016-1043","DOI":"10.21437\/Interspeech.2016-1043"},{"key":"20_CR24","doi-asserted-by":"publisher","unstructured":"Wan, L., Wang, Q., Papir, A., Moreno, I.L.: Generalized end-to-end loss for speaker verification. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4879\u20134883 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8462665","DOI":"10.1109\/ICASSP.2018.8462665"},{"key":"20_CR25","doi-asserted-by":"publisher","unstructured":"Wang, Z., et al.: Accent and speaker disentanglement in many-to-many voice conversion. In: 2021 12th International Symposium on Chinese Spoken Language Processing (ISCSLP), pp. 1\u20135 (2021). https:\/\/doi.org\/10.1109\/ISCSLP49672.2021.9362120","DOI":"10.1109\/ISCSLP49672.2021.9362120"},{"key":"20_CR26","doi-asserted-by":"publisher","unstructured":"Wu, J., Polyak, A., Taigman, Y., Fong, J., Agrawal, P., He, Q.: Multilingual text-to-speech training using cross language voice conversion and self-supervised learning of speech representations. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8017\u20138021 (2022). https:\/\/doi.org\/10.1109\/ICASSP43922.2022.9746282","DOI":"10.1109\/ICASSP43922.2022.9746282"},{"key":"20_CR27","doi-asserted-by":"publisher","unstructured":"Yang, G., Yang, S., Liu, K., Fang, P., Chen, W., Xie, L.: Multi-band MelGAN: faster waveform generation for high-quality text-to-speech. In: 2021 IEEE Spoken Language Technology Workshop (SLT), pp. 492\u2013498 (2021). https:\/\/doi.org\/10.1109\/SLT48900.2021.9383551","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"20_CR28","doi-asserted-by":"publisher","unstructured":"Zhang, Y., et al.: Learning to speak fluently in a foreign language: multilingual speech synthesis and cross-language voice cloning. In: Proceedings of Interspeech 2019, pp. 2080\u20132084 (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2668","DOI":"10.21437\/Interspeech.2019-2668"},{"key":"20_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, Z., Falai, A., Sanchez, A., Angelini, O., Yanagisawa, K.: Mix and match: an empirical study on training corpus composition for polyglot text-to-speech (TTS). In: Proceedings of Interspeech 2022, pp. 2353\u20132357 (2022). https:\/\/doi.org\/10.21437\/Interspeech.2022-242","DOI":"10.21437\/Interspeech.2022-242"},{"key":"20_CR30","doi-asserted-by":"publisher","unstructured":"Zhao, G., Sonsaat, S., Levis, J., Chukharev-Hudilainen, E., Gutierrez-Osuna, R.: Accent conversion using phonetic posteriorgrams. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5314\u20135318 (2018). https:\/\/doi.org\/10.1109\/ICASSP.2018.8462258","DOI":"10.1109\/ICASSP.2018.8462258"},{"key":"20_CR31","doi-asserted-by":"publisher","unstructured":"Zhao, S., Nguyen, T.H., Wang, H., Ma, B.: Towards natural bilingual and code-switched speech synthesis based on mix of monolingual recordings and cross-lingual voice conversion. In: Proceedings of Interspeech 2020, pp. 2927\u20132931 (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-1163","DOI":"10.21437\/Interspeech.2020-1163"}],"container-title":["Communications in Computer and Information Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8126-7_20","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,7]],"date-time":"2024-03-07T11:34:41Z","timestamp":1709811281000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8126-7_20"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,13]]},"ISBN":["9789819981250","9789819981267"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8126-7_20","relation":{},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"type":"print","value":"1865-0929"},{"type":"electronic","value":"1865-0937"}],"subject":[],"published":{"date-parts":[[2023,11,13]]},"assertion":[{"value":"13 November 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Changsha","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 November 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 November 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2023.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":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1274","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":"650","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":"51% - 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":"4.14","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":"2.46","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)"}}]}}