{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T14:51:07Z","timestamp":1784299867110,"version":"3.55.0"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030876258","type":"print"},{"value":"9783030876265","type":"electronic"}],"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\/978-3-030-87626-5_15","type":"book-chapter","created":{"date-parts":[[2021,9,29]],"date-time":"2021-09-29T06:14:35Z","timestamp":1632896075000},"page":"204-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":17,"title":["HUI-Audio-Corpus-German: A High Quality TTS Dataset"],"prefix":"10.1007","author":[{"given":"Pascal","family":"Puchtler","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johannes","family":"Wirth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ren\u00e9","family":"Peinl","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,9,30]]},"reference":[{"key":"15_CR1","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. In: Proceedings of Interspeech 2017, pp. 4006\u20134010 (2017)","DOI":"10.21437\/Interspeech.2017-1452"},{"key":"15_CR2","doi-asserted-by":"crossref","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. arXiv preprint arXiv:2005.05106 (2020)","DOI":"10.1109\/SLT48900.2021.9383551"},{"key":"15_CR3","unstructured":"voicebot.ai: Hearables Consumer Adoption Report 2020. https:\/\/research.voicebot.ai\/report-list\/hearables-consumer-adoption-report-2020\/. Accessed 12 May 2021"},{"key":"15_CR4","doi-asserted-by":"crossref","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. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"15_CR5","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. arXiv preprint arXiv:1609.03499 (2016)"},{"key":"15_CR6","unstructured":"The LJ Speech Dataset. https:\/\/keithito.com\/LJ-Speech-Dataset. Accessed 03 May 2021"},{"key":"15_CR7","doi-asserted-by":"crossref","unstructured":"Zen, H., et al.: LibriTTS: a corpus derived from LibriSpeech for text-to-speech. arXiv:1904.02882 [cs, eess] (2019)","DOI":"10.21437\/Interspeech.2019-2441"},{"key":"15_CR8","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: Generative adversarial networks for efficient and high fidelity speech synthesis. In: Advances in Neural Information Processing Systems, vol. 33 (2020)"},{"key":"15_CR9","unstructured":"Chen, N., Zhang, Y., Zen, H., Weiss, R.J., Norouzi, M., Chan, W.: WaveGrad: estimating gradients for waveform generation. arXiv preprint arXiv:2009.00713 (2020)"},{"key":"15_CR10","unstructured":"The M-AILABS Speech Dataset \u2013 caito. https:\/\/www.caito.de\/2019\/01\/the-m-ailabs-speech-dataset\/. Accessed 03 May 2021"},{"key":"15_CR11","doi-asserted-by":"crossref","unstructured":"Govalkar, P., Fischer, J., Zalkow, F., Dittmar, C.: A comparison of recent neural vocoders for speech signal reconstruction. In: Proceedings of 10th ISCA Speech Synthesis Workshop, pp. 7\u201312 (2019)","DOI":"10.21437\/SSW.2019-2"},{"key":"15_CR12","unstructured":"Kumar, K., et al.: MelGAN: generative adversarial networks for conditional waveform synthesis. In: Wallach, H., Larochelle, H., Beygelzimer, A., Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol. 32, pp. 14910\u201314921. Curran Associates, Inc. (2019)"},{"key":"15_CR13","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"},{"key":"15_CR14","unstructured":"M\u00fcller, T.: Thorsten Open German Voice Dataset. https:\/\/github.com\/thorstenMueller\/deep-learning-german-tts. Accessed 26 March 2021"},{"key":"15_CR15","doi-asserted-by":"crossref","unstructured":"Park, K., Mulc, T.: CSS10: a collection of single speaker speech datasets for 10 languages. arXiv preprint arXiv:1903.11269 (2019)","DOI":"10.21437\/Interspeech.2019-1500"},{"key":"15_CR16","doi-asserted-by":"crossref","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. arXiv preprint arXiv:2012.03411 (2020)","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"15_CR17","doi-asserted-by":"crossref","unstructured":"Panayotov, V., Chen, G., Povey, D., Khudanpur, S.: Librispeech: an ASR corpus based on public domain audio books. In: 2015 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 5206\u20135210. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"15_CR18","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep learning. Das umfassende Handbuch: Grundlagen, aktuelle Verfahren und Algorithmen, neue Forschungsans\u00e4tze. mitp, Frechen (2018)"},{"key":"15_CR19","unstructured":"Agarwal, A., Zesch, T.: German end-to-end speech recognition based on DeepSpeech. In: Proceedings of the 15th Conference on Natural Language Processing (2019)"},{"key":"15_CR20","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1016\/j.trc.2020.01.005","volume":"111","author":"KNS Behara","year":"2020","unstructured":"Behara, K.N.S., Bhaskar, A., Chung, E.: A novel approach for the structural comparison of origin-destination matrices: levenshtein distance. Transp. Res. Part C: Emerg. Technol. 111, 513\u2013530 (2020). https:\/\/doi.org\/10.1016\/j.trc.2020.01.005","journal-title":"Transp. Res. Part C: Emerg. Technol."},{"key":"15_CR21","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Tacotron: towards end-to-end speech synthesis. arXiv preprint arXiv:1703.10135 (2017)","DOI":"10.21437\/Interspeech.2017-1452"}],"container-title":["Lecture Notes in Computer Science","KI 2021: Advances in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-87626-5_15","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T07:05:00Z","timestamp":1639724700000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-87626-5_15"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030876258","9783030876265"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-87626-5_15","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"30 September 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"KI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"German Conference on Artificial Intelligence (K\u00fcnstliche Intelligenz)","order":2,"name":"conference_name","label":"Conference Name","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":"1 October 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"44","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ki2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ki2021.uni-luebeck.de\/","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":"59","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":"16","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":"4","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":"27% - 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":"4","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)"}}]}}