{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:34:37Z","timestamp":1762770877529,"version":"build-2065373602"},"publisher-location":"Singapore","reference-count":18,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819543946","type":"print"},{"value":"9789819543953","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,11]],"date-time":"2025-11-11T00:00:00Z","timestamp":1762819200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-4395-3_7","type":"book-chapter","created":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:29:55Z","timestamp":1762770595000},"page":"86-99","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Do End-to-End TTS Systems Exploit Patterns in\u00a0Speech?"],"prefix":"10.1007","author":[{"given":"Parth","family":"Khadse","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sunil Kumar","family":"Kopparapu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,11]]},"reference":[{"key":"7_CR1","doi-asserted-by":"crossref","unstructured":"Bain, M., Huh, J., Han, T., Zisserman, A.: WhisperX: time-accurate speech transcription of long-form audio (2023). https:\/\/arxiv.org\/abs\/2303.00747","DOI":"10.21437\/Interspeech.2023-78"},{"key":"7_CR2","unstructured":"Bell, A.M.: Visible Speech: The Science of Universal Alphabetics. Internet Archive (1867). https:\/\/archive.org\/details\/b21782520. Accessed 29 May 2025"},{"key":"7_CR3","doi-asserted-by":"crossref","unstructured":"Chen, Y., et al.: F5-TTS: a fairytaler that fakes fluent and faithful speech with flow matching (2025). https:\/\/arxiv.org\/abs\/2410.06885","DOI":"10.18653\/v1\/2025.acl-long.313"},{"key":"7_CR4","unstructured":"NVIDIA Corporation: WaveGlow: a flow-based generative network for speech synthesis. https:\/\/github.com\/NVIDIA\/waveglow. Accessed 21 Mar 2023"},{"key":"7_CR5","unstructured":"IISc: LIMMITS25 multi-speaker, multi-lingual INDIC TTS with voice cloning grand challenge. https:\/\/sites.google.com\/view\/limmits25. Accessed 22 Mar 2023"},{"key":"7_CR6","unstructured":"Kim, J., Kim, S., Kong, J., Yoon, S.: Glow-TTS: a generative flow for text-to-speech via monotonic alignment search. In: Proceedings of the 34th International Conference on Neural Information Processing Systems, NIPS 2020. Curran Associates Inc., Red Hook, NY, USA (2020)"},{"key":"7_CR7","unstructured":"Kim, J., Kong, J., Son, J.: Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech. In: International Conference on Machine Learning, pp. 5530\u20135540. PMLR (2021)"},{"key":"7_CR8","unstructured":"Klatt, D.H.: Software for a casette-based speech synthesis system. Technical report. HLR-80-06, Haskins Laboratories, New Haven, CT, August 1980. http:\/\/www.haskins.yale.edu\/pubs\/pubs.html"},{"key":"7_CR9","doi-asserted-by":"publisher","unstructured":"Kudo, T., Richardson, J.: SentencePiece: a simple and language independent subword tokenizer and detokenizer for neural text processing, November 2018. https:\/\/doi.org\/10.18653\/v1\/D18-2012, https:\/\/aclanthology.org\/D18-2012","DOI":"10.18653\/v1\/D18-2012"},{"key":"7_CR10","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":"7_CR11","doi-asserted-by":"crossref","unstructured":"Prenger, R., Valle, R., Catanzaro, B.: WaveGlow: a flow-based generative network for speech synthesis. In: ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3617\u20133621. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8683143"},{"key":"7_CR12","unstructured":"Radford, A., et\u00a0al.: Whisper: automatic Speech Recognition with Open AI. https:\/\/openai.com\/index\/whisper\/. Accessed 22 Mar 2023"},{"key":"7_CR13","unstructured":"Radford, A., Kim, J.W., Xu, T., Brockman, G., McLeavey, C., Sutskever, I.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"key":"7_CR14","unstructured":"Ren, Y., et al.: FastSpeech: fast, robust and controllable text to speech. In: Wallach, H., Larochelle, H., Beygelzimer, A., d\u2019Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in Neural Information Processing Systems, vol.\u00a032. Curran Associates, Inc. (2019)"},{"key":"7_CR15","doi-asserted-by":"publisher","unstructured":"Sennrich, R., Haddow, B., Birch, A.: Neural machine translation of rare words with subword units. In: Erk, K., Smith, N.A. (eds.) Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), August 2016, pp. 1715\u20131725. Association for Computational Linguistics, Berlin, Germany (2016). https:\/\/doi.org\/10.18653\/v1\/P16-1162. https:\/\/aclanthology.org\/P16-1162","DOI":"10.18653\/v1\/P16-1162"},{"key":"7_CR16","doi-asserted-by":"crossref","unstructured":"Shah, N., Khadse, P., Karande, S., Kopparapu, S.K.: Hamaraawaz: advancing low-latency streaming tts for multilingual speech in Indian languages. In: 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), ICASSP 2025, pp.\u00a01\u20132. IEEE (2025)","DOI":"10.1109\/ICASSP49660.2025.10887580"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Shen, J., et\u00a0al.: 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":"7_CR18","doi-asserted-by":"publisher","unstructured":"Tripathi, A., Bhosale, S., Kopparapu, S.K.: Automatic speaker independent dysarthric speech intelligibility assessment system. Comput. Speech Lang. 69, 101213 (2021). https:\/\/doi.org\/10.1016\/j.csl.2021.101213. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0885230821000206","DOI":"10.1016\/j.csl.2021.101213"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-4395-3_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,10]],"date-time":"2025-11-10T10:30:00Z","timestamp":1762770600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-4395-3_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,11]]},"ISBN":["9789819543946","9789819543953"],"references-count":18,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-4395-3_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,11]]},"assertion":[{"value":"11 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ACPR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Asian Conference on Pattern Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Gold Coast, QLD","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Australia","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"acpr2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.acpr2025.com\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}