{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T20:06:52Z","timestamp":1743106012569,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031160776"},{"type":"electronic","value":"9783031160783"}],"license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-16078-3_51","type":"book-chapter","created":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:16:25Z","timestamp":1661991385000},"page":"739-751","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Quality Assurance for Speech Synthesis with ASR"],"prefix":"10.1007","author":[{"given":"Ren\u00e9","family":"Peinl","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Johannes","family":"Wirth","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,9,1]]},"reference":[{"key":"51_CR1","doi-asserted-by":"crossref","unstructured":"Murthy, S., Sitaram, D., Sitaram, S.: Effect of TTS generated audio on OOV Detection and word error rate in ASR for low-resource languages. In: Interspeech, pp. 1026\u20131030 (2018)","DOI":"10.21437\/Interspeech.2018-1555"},{"key":"51_CR2","doi-asserted-by":"crossref","unstructured":"Gokay, R., Yalcin, H.: Improving low resource Turkish speech recognition with data augmentation and TTS. In: 2019 16th International Multi-Conference on Systems, Signals & Devices (SSD), pp. 357\u2013360 (2019)","DOI":"10.1109\/SSD.2019.8893184"},{"key":"51_CR3","doi-asserted-by":"crossref","unstructured":"Baskar, M.K., Burget, L., Watanabe, S., Astudillo, R.F.: Eat: enhanced ASR-TTS for self-supervised speech recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6753\u20136757 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413375"},{"key":"51_CR4","doi-asserted-by":"crossref","unstructured":"Karita, S., Watanabe, S., Iwata, T., Delcroix, M., Ogawa, A., Nakatani, T.: Semi-supervised end-to-end speech recognition using text-to-speech and autoencoders. In: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6166\u20136170 (2019)","DOI":"10.1109\/ICASSP.2019.8682890"},{"key":"51_CR5","doi-asserted-by":"crossref","unstructured":"Chen, Z.: Semi-supervision in ASR: Sequential mixmatch and factorized TTS-based augmentation (2021)","DOI":"10.21437\/Interspeech.2021-677"},{"key":"51_CR6","unstructured":"Baby, A.: An ASR Guided Speech Intelligibility Measure for TTS Model Selection. arXiv preprint arXiv:2006.01463 (2020)"},{"key":"51_CR7","doi-asserted-by":"crossref","unstructured":"Taylor, J., Richmond, K.: Confidence Intervals for ASR-based TTS Evaluation (2021)","DOI":"10.21437\/Interspeech.2021-2203"},{"key":"51_CR8","doi-asserted-by":"crossref","unstructured":"Protasio Ribeiro, F., Florencio, D., Zhang, C., Seltzer, M.: CROWDMOS: an approach for crowdsourcing mean opinion score studies. Mai 2011, ICASSP. Verf\u00fcgbar unter: https:\/\/www.microsoft.com\/en-us\/research\/publication\/crowdmos-an-approach-for-crowdsourcing-mean-opinion-score-studies\/","DOI":"10.1109\/ICASSP.2011.5946971"},{"key":"51_CR9","doi-asserted-by":"crossref","unstructured":"Shen, J.: Natural TTS synthesis by conditioning waveNet on MEL spectrogram predictions. In: 2018 IEEE Int. Conf. on Acoustics, Speech and Signal Processing (ICASSP), pp. 4779\u20134783 (2018)","DOI":"10.1109\/ICASSP.2018.8461368"},{"issue":"1","key":"51_CR10","doi-asserted-by":"publisher","first-page":"55","DOI":"10.1016\/j.csl.2003.12.001","volume":"19","author":"M Viswanathan","year":"2005","unstructured":"Viswanathan, M., Viswanathan, M.: Measuring speech quality for text-to-speech systems: development and assessment of a modified mean opinion score (MOS) scale. Comput. Speech Lang. 19(1), 55\u201383 (2005). https:\/\/doi.org\/10.1016\/j.csl.2003.12.001","journal-title":"Comput. Speech Lang."},{"key":"51_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, pp. 125\u2013128 (1993)","DOI":"10.1109\/PACRIM.1993.407206"},{"key":"51_CR12","doi-asserted-by":"crossref","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\u20132020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7209\u20137213 (2020)","DOI":"10.1109\/ICASSP40776.2020.9054484"},{"key":"51_CR13","doi-asserted-by":"crossref","unstructured":"Badlani, R., \\Lancucki, A., Shih, K.J., Valle, R., Ping, W., Catanzaro, B.: One TTS alignment to rule them all. arXiv preprint arXiv:2108.10447 (2021)","DOI":"10.1109\/ICASSP43922.2022.9747707"},{"key":"51_CR14","doi-asserted-by":"crossref","unstructured":"Rix, A.W., Beerends, J.G., Hollier, M.P., Hekstra, A.P.: Perceptual evaluation of speech quality (PESQ)-a new method for speech quality assessment of telephone networks and codecs. In: 2001 IEEE international conference on acoustics, speech, and signal processing. Proceedings (Cat. No. 01CH37221), pp. 749\u2013752 (2001)","DOI":"10.1109\/ICASSP.2001.941023"},{"key":"51_CR15","unstructured":"Beerends, J.G.: Perceptual objective listening quality assessment (POLQA), the third generation ITU-T standard for end-to-end speech quality measurement part I\u2014temporal alignment. J. Audio Eng. Soc. 61(6), 366\u2013384 (2013)"},{"key":"51_CR16","doi-asserted-by":"crossref","unstructured":"Chinen, M., Lim, F.S., Skoglund, J., Gureev, N., O\u2019Gorman, F., Hines, A.: VISQOL v3: an open source production ready objective speech and audio metric. In: 2020 Twelfth International Conference on Quality of Multimedia Experience (QoMEX), pp. 1\u20136 (2020)","DOI":"10.1109\/QoMEX48832.2020.9123150"},{"key":"51_CR17","doi-asserted-by":"crossref","unstructured":"Wang, W., Zhou, Z., Lu, Y, Wang, H., Du, C., Qian, Y.: Towards data selection on TTS data for children\u2019s speech recognition. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6888\u20136892 (2021)","DOI":"10.1109\/ICASSP39728.2021.9413930"},{"key":"51_CR18","doi-asserted-by":"crossref","unstructured":"Wu, Z., Xie, Z., King, S.: The blizzard challenge 2019. In: Proceedings of Blizzard Challenge Workshop 2019 (2019)","DOI":"10.21437\/Blizzard.2019-1"},{"key":"51_CR19","doi-asserted-by":"publisher","unstructured":"Morris, A., Maier, V., Green, P.: From WER and RIL to MER and WIL: improved evaluation measures for connected speech recognition Okt. (2004). https:\/\/doi.org\/10.21437\/Interspeech.2004-668","DOI":"10.21437\/Interspeech.2004-668"},{"key":"51_CR20","doi-asserted-by":"publisher","unstructured":"Hayashi, T.: Espnet-TTS: unified, reproducible, and integratable open source end-to-end text-to-speech toolkit. In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Barcelona, Spain, Mai 2020, pp. 7654\u20137658 (2020). https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053512","DOI":"10.1109\/ICASSP40776.2020.9053512"},{"key":"51_CR21","unstructured":"Wirth, J., Puchtler, P., Peinl, R.: Neural Speech Synthesis in German. Okt. pp. 26\u201334. Zugegriffen: 12. Januar 2022 (2021). Verf\u00fcgbar unter: https:\/\/www.thinkmind.org\/index.php?view=article&articleid=centric_2021_2_30_30009"},{"key":"51_CR22","unstructured":"Majumdar, S., Balam, J., Hrinchuk, O., Lavrukhin, V., Noroozi, V., Ginsburg, B.: Citrinet: Closing the Gap between Non-Autoregressive and Autoregressive End-to-End Models for Automatic Speech Recognition. arXiv preprint arXiv:2104.01721 (2021)"},{"key":"51_CR23","doi-asserted-by":"publisher","unstructured":"Pratap, V., Xu, Q., Sriram, A., Synnaeve, G., Collobert, R.: MLS: a large-scale multilingual dataset for speech research. In: Interspeech 2020, pp. 2757\u20132761. Okt (2020). https:\/\/doi.org\/10.21437\/Interspeech.2020-2826","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"51_CR24","doi-asserted-by":"crossref","unstructured":"Wang, C.: VoxPopuli: a large-scale multilingual speech corpus for representation learning, semi-supervised learning and interpretation. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), August 2021, pp. 993\u20131003 (2021). https:\/\/aclanthology.org\/2021.acl-long.80","DOI":"10.18653\/v1\/2021.acl-long.80"},{"key":"51_CR25","unstructured":"Baevski, A., Zhou, H., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. [cs, eess]. Okt, Zugegriffen: 14. Januar 2022 (2020). http:\/\/arxiv.org\/abs\/2006.11477"},{"key":"51_CR26","doi-asserted-by":"crossref","unstructured":"Jeong, M., Kim, H., Cheon, S.J., Choi, B.J., Kim, N.S.: Diff-TTS: a denoising diffusion model for text-to-speech. arXiv preprint arXiv:2104.01409 (2021)","DOI":"10.21437\/Interspeech.2021-469"},{"key":"51_CR27","unstructured":"Kong, J., Kim, J., Bae, J.: HiFi-GAN: Generative Adversarial Networks for Efficient and High Fidelity Speech Synthesis. Advances in Neural Information Processing Systems. 33 (2020)"},{"key":"51_CR28","unstructured":"Kim, J., Kong, J., Son, J.: Conditional Variational Autoencoder with Adversarial Learning for End-to-End Text-to-Speech. arXiv preprint arXiv:2106.06103 (2021)"},{"key":"51_CR29","doi-asserted-by":"crossref","unstructured":"Han, W.: ContextNet: Improving convolutional neural networks for automatic speech recognition with global context. arXiv preprint arXiv:2005.03191 (2020)","DOI":"10.21437\/Interspeech.2020-2059"},{"key":"51_CR30","doi-asserted-by":"crossref","unstructured":"Gulati, A.: Conformer: Convolution-augmented transformer for speech recognition\u201c, arXiv preprint arXiv:2005.08100 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"51_CR31","doi-asserted-by":"crossref","unstructured":"Burchi, M., Vielzeuf, V.: Efficient Conformer: Progressive Downsampling and Grouped Attention for Automatic Speech Recognition. arXiv preprint arXiv:2109.01163 (2021)","DOI":"10.1109\/ASRU51503.2021.9687874"},{"key":"51_CR32","unstructured":"Hinterleitner, F., Norrenbrock, C., M\u00f6ller, S.: Is intelligibility still the main problem? A review of perceptual quality dimensions of synthetic speech (2013)"}],"container-title":["Lecture Notes in Networks and Systems","Intelligent Systems and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-16078-3_51","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,3]],"date-time":"2024-10-03T01:34:11Z","timestamp":1727919251000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-16078-3_51"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9,1]]},"ISBN":["9783031160776","9783031160783"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-16078-3_51","relation":{},"ISSN":["2367-3370","2367-3389"],"issn-type":[{"type":"print","value":"2367-3370"},{"type":"electronic","value":"2367-3389"}],"subject":[],"published":{"date-parts":[[2022,9,1]]},"assertion":[{"value":"1 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"IntelliSys","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Proceedings of SAI Intelligent Systems Conference","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Amsterdam","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"The Netherlands","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"intellisys2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/saiconference.com\/IntelliSys","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}