{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:50:39Z","timestamp":1742914239750,"version":"3.40.3"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031569913"},{"type":"electronic","value":"9783031569920"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-3-031-56992-0_5","type":"book-chapter","created":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T00:02:01Z","timestamp":1711670521000},"page":"67-83","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Deep Learning Approaches for\u00a0Sung Vowel Classification"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1856-5088","authenticated-orcid":false,"given":"Parker","family":"Carlson","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1033-5931","authenticated-orcid":false,"given":"Patrick J.","family":"Donnelly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,3,29]]},"reference":[{"key":"5_CR1","doi-asserted-by":"publisher","unstructured":"Avramidis, K., Kratimenos, A., Garoufis, C., Zlatintsi, A., Maragos, P.: Deep convolutional and recurrent networks for polyphonic instrument classification from monophonic raw audio waveforms. In: ICASSP 2021\u20132021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3010\u20133014 (2021). https:\/\/doi.org\/10.1109\/ICASSP39728.2021.9413479","DOI":"10.1109\/ICASSP39728.2021.9413479"},{"key":"5_CR2","doi-asserted-by":"publisher","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems, vol. 33, pp. 12449\u201312460 (2020). https:\/\/doi.org\/10.48550\/arXiv.2006.11477","DOI":"10.48550\/arXiv.2006.11477"},{"key":"5_CR3","doi-asserted-by":"publisher","unstructured":"Burrows, D.: Singing and saying. J. Musicology 7(3), 390\u2013402 (1989). https:\/\/doi.org\/10.2307\/763607, http:\/\/www.jstor.org\/stable\/763607","DOI":"10.2307\/763607"},{"key":"5_CR4","doi-asserted-by":"publisher","unstructured":"Dabike, G.R., Barker, J.: Automatic lyric transcription from karaoke vocal tracks: resources and a baseline system. In: Proceedings of Interspeech, pp. 579\u2013583. International Speech Communication Association (ISCA) (2019). https:\/\/doi.org\/10.21437\/Interspeech.2019-2378","DOI":"10.21437\/Interspeech.2019-2378"},{"issue":"3","key":"5_CR5","doi-asserted-by":"publisher","first-page":"1781","DOI":"10.1121\/1.1781620","volume":"116","author":"F De Wet","year":"2004","unstructured":"De Wet, F., Weber, K., Boves, L., Cranen, B., Bengio, S., Bourlard, H.: Evaluation of formant-like features on an automatic vowel classification task. J. Acoust. Soc. Am. 116(3), 1781\u20131792 (2004). https:\/\/doi.org\/10.1121\/1.1781620","journal-title":"J. Acoust. Soc. Am."},{"key":"5_CR6","doi-asserted-by":"publisher","unstructured":"Demirel, E., Ahlb\u00e4ck, S., Dixon, S.: Automatic lyrics transcription using dilated convolutional neural networks with self-attention. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2020). https:\/\/doi.org\/10.1109\/IJCNN48605.2020.9207052","DOI":"10.1109\/IJCNN48605.2020.9207052"},{"key":"5_CR7","doi-asserted-by":"publisher","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Burstein, J., Doran, C., Solorio, T. (eds.) Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). pp. 4171\u20134186. Association for Computational Linguistics, Minneapolis, Minnesota (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1423, https:\/\/aclanthology.org\/N19-1423","DOI":"10.18653\/v1\/N19-1423"},{"issue":"3","key":"5_CR8","doi-asserted-by":"publisher","first-page":"195","DOI":"10.1561\/2000000004","volume":"1","author":"M Gales","year":"2008","unstructured":"Gales, M., Young, S.: Application of hidden Markov models in speech recognition. Found. Trends Sig. Process. 1(3), 195\u2013304 (2008). https:\/\/doi.org\/10.1561\/2000000004","journal-title":"Found. Trends Sig. Process."},{"key":"5_CR9","doi-asserted-by":"publisher","unstructured":"Garofolo, J.S., et al.: Timit acoustic-phonetic continous speech corpus (1993). https:\/\/doi.org\/10.35111\/17gk-bn40","DOI":"10.35111\/17gk-bn40"},{"key":"5_CR10","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"799","DOI":"10.1007\/11550907_126","volume-title":"Artificial Neural Networks (ICANN)","author":"A Graves","year":"2005","unstructured":"Graves, A., Fern\u00e1ndez, S., Schmidhuber, J.: Bidirectional LSTM networks for improved phoneme classification and recognition. In: Duch, W., Kacprzyk, J., Oja, E., Zadro\u017cny, S. (eds.) ICANN 2005. LNCS, vol. 3697, pp. 799\u2013804. Springer, Heidelberg (2005). https:\/\/doi.org\/10.1007\/11550907_126"},{"key":"5_CR11","doi-asserted-by":"publisher","unstructured":"Gupta, C., Y\u0131lmaz, E., Li, H.: Automatic lyrics alignment and transcription in polyphonic music: does background music help? In: Proceedings of the International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 496\u2013500. IEEE (2020). https:\/\/doi.org\/10.1109\/TASLP.2022.3190742","DOI":"10.1109\/TASLP.2022.3190742"},{"key":"5_CR12","doi-asserted-by":"publisher","unstructured":"He, Y., et al.: Streaming end-to-end speech recognition for mobile devices. In: IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6381\u20136385 (2019). https:\/\/doi.org\/10.1109\/ICASSP.2019.8682336","DOI":"10.1109\/ICASSP.2019.8682336"},{"issue":"4","key":"5_CR13","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1044\/jshr.3604.694","volume":"36","author":"J Hillenbrand","year":"1993","unstructured":"Hillenbrand, J., Gayvert, R.T.: Vowel classification based on fundamental frequency and formant frequencies. J. Speech Lang. Hear. Res. 36(4), 694\u2013700 (1993). https:\/\/doi.org\/10.1044\/jshr.3604.694","journal-title":"J. Speech Lang. Hear. Res."},{"key":"5_CR14","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 3451\u20133460 (2021). https:\/\/doi.org\/10.1109\/TASLP.2021.3122291","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"5_CR15","doi-asserted-by":"publisher","unstructured":"Jha, M.V., Rao, P.: Assessing vowel quality for singing evaluation. In: National Conference on Communications (NCC 2012), pp. 1\u20135. IEEE (2012). https:\/\/doi.org\/10.1109\/NCC.2012.6176860","DOI":"10.1109\/NCC.2012.6176860"},{"key":"5_CR16","doi-asserted-by":"publisher","unstructured":"Karpagavalli, S., Chandra, E.: A review on automatic speech recognition architecture and approaches. J. Sig. Process. Image Process. Pattern Recogn. 9(4), 393\u2013404 (2016). https:\/\/doi.org\/10.14257\/ijsip.2016.9.4.34","DOI":"10.14257\/ijsip.2016.9.4.34"},{"key":"5_CR17","doi-asserted-by":"publisher","unstructured":"Kermanshahi, M.A., Akbari, A., Nasersharif, B.: Transfer learning for end-to-end ASR to deal with low-resource problem in Persian language. In: 26th International Computer Conference, Computer Society of Iran (CSICC), pp. 1\u20135 (2021). https:\/\/doi.org\/10.1109\/CSICC52343.2021.9420540","DOI":"10.1109\/CSICC52343.2021.9420540"},{"key":"5_CR18","doi-asserted-by":"publisher","unstructured":"Khunarsal, P., Lursinsap, C., Raicharoen, T.: Singing voice recognition based on matching of spectrogram pattern. In: Proceedings of the International Joint Conference on Neural Networks (IJCNN), pp. 1595\u20131599 (2009). https:\/\/doi.org\/10.1109\/IJCNN.2009.5179014","DOI":"10.1109\/IJCNN.2009.5179014"},{"key":"5_CR19","doi-asserted-by":"publisher","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: 3rd International Conference on Learning Representations (ICLR) (2015). https:\/\/doi.org\/10.48550\/arXiv.1412.6980","DOI":"10.48550\/arXiv.1412.6980"},{"key":"5_CR20","doi-asserted-by":"publisher","first-page":"28","DOI":"10.1016\/j.apacoust.2019.04.027","volume":"154","author":"Y Korkmaz","year":"2019","unstructured":"Korkmaz, Y., Boyac\u0131, A., Tuncer, T.: Turkish vowel classification based on acoustical and decompositional features optimized by genetic algorithm. Appl. Acoust. 154, 28\u201335 (2019). https:\/\/doi.org\/10.1016\/j.apacoust.2019.04.027","journal-title":"Appl. Acoust."},{"key":"5_CR21","doi-asserted-by":"publisher","unstructured":"Korkmaz, Y., Boyaci, A.: Classification of Turkish vowels based on formant frequencies. In: Proceedings of the International Conference on Artificial Intelligence and Data Processing (IDAP), pp. 1\u20134 (2018). https:\/\/doi.org\/10.1109\/IDAP.2018.8620877","DOI":"10.1109\/IDAP.2018.8620877"},{"key":"5_CR22","unstructured":"Kruspe, A.M.: Training phoneme models for singing with \u201csongified\u201d speech data. In: Proceedings of the 16th International Conference on Music Information Retrieval (ISMIR), pp. 336\u2013342 (2015). https:\/\/archives.ismir.net\/ismir2015\/paper\/000034.pdf"},{"key":"5_CR23","unstructured":"Kruspe, A.M.: Application of automatic speech recognition technologies to singing. Ph.D. thesis, TU Technische Universit\u00e4t, Ilmenau, Germany (2018). https:\/\/www.db-thueringen.de\/receive\/dbt_mods_00035065"},{"key":"5_CR24","doi-asserted-by":"publisher","unstructured":"Li, Y., et al.: MERT: acoustic music understanding model with large-scale self-supervised training (2023). https:\/\/doi.org\/10.48550\/arXiv.2306.00107","DOI":"10.48550\/arXiv.2306.00107"},{"key":"5_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2010\/546047","volume":"2010","author":"A Mesaros","year":"2010","unstructured":"Mesaros, A., Virtanen, T.: Automatic recognition of lyrics in singing. EURASIP J. Audio, Speech, Music Process. 2010, 1\u201311 (2010). https:\/\/doi.org\/10.1155\/2010\/546047","journal-title":"EURASIP J. Audio, Speech, Music Process."},{"key":"5_CR26","doi-asserted-by":"publisher","unstructured":"van den Oord, A., et al.: Wavenet: a generative model for raw audio (2016). https:\/\/doi.org\/10.48550\/arXiv.1609.03499","DOI":"10.48550\/arXiv.1609.03499"},{"key":"5_CR27","unstructured":"Ou, L., Gu, X., Wang, Y.: Transfer learning of wav2vec 2.0 for automatic lyric transcription. In: Proceedings of the 23rd International Conference on Music Information Retrieval (ISMIR), pp. 891\u2013899 (2022). https:\/\/archives.ismir.net\/ismir2022\/paper\/000107.pdf"},{"key":"5_CR28","doi-asserted-by":"publisher","unstructured":"Palaz, D., Collobert, R., Doss, M.M.: Estimating phoneme class conditional probabilities from raw speech signal using convolutional neural networks. In: Proceedings of Interspeech (2013). https:\/\/doi.org\/10.21437\/Interspeech.2013-438","DOI":"10.21437\/Interspeech.2013-438"},{"key":"5_CR29","doi-asserted-by":"publisher","unstructured":"Santana, I.A.P., et al.: Music4all: a new music database and its applications. In: International Conference on Systems, Signals and Image Processing (IWSSIP), pp. 399\u2013404. IEEE (2020). https:\/\/doi.org\/10.1109\/IWSSIP48289.2020.9145170","DOI":"10.1109\/IWSSIP48289.2020.9145170"},{"key":"5_CR30","doi-asserted-by":"publisher","unstructured":"Smule, I.: DAMP-MVP: Digital Archive of Mobile Performances - Smule Multilingual Vocal Performance 300x30x2 (2018). https:\/\/doi.org\/10.5281\/zenodo.2747436","DOI":"10.5281\/zenodo.2747436"},{"issue":"4","key":"5_CR31","first-page":"629","volume":"90","author":"BH Story","year":"2004","unstructured":"Story, B.H.: Vowel acoustics for speaking and singing. Acta Acust. Acust. 90(4), 629\u2013640 (2004)","journal-title":"Acta Acust. Acust."},{"issue":"1969","key":"5_CR32","first-page":"33","volume":"1","author":"J Sundberg","year":"1969","unstructured":"Sundberg, J.: Articulatory differences between spoken and sung vowels in singers. STL-QPSR, KTH 1(1969), 33\u201346 (1969)","journal-title":"STL-QPSR, KTH"},{"key":"5_CR33","doi-asserted-by":"publisher","unstructured":"Sundberg, J.: Articulatory interpretation of the \u201csinging formant\u201d. J. Acoust. Soc. Am. 55(4), 838\u2013844 (1974). https:\/\/doi.org\/10.1121\/1.1914609","DOI":"10.1121\/1.1914609"},{"key":"5_CR34","doi-asserted-by":"publisher","unstructured":"Teytaut, Y., Roebel, A.: Phoneme-to-audio alignment with recurrent neural networks for speaking and singing voice. In: Proceedings of Interspeech. pp. 61\u201365. International Speech Communication Association (ISCA) (2021). https:\/\/doi.org\/10.21437\/interspeech.2021-1676","DOI":"10.21437\/interspeech.2021-1676"},{"key":"5_CR35","unstructured":"Tieleman, T., Hinton, G.: Lecture 6e rmsprop: divide the gradient by a running average of its recent magnitude. In: COURSERA: Neural Networks for Machine Learning, vol. 4, pp. 26\u201331 (2012). https:\/\/www.cs.toronto.edu\/~tijmen\/csc321\/slides\/lecture_slides_lec6.pdf"},{"key":"5_CR36","doi-asserted-by":"publisher","unstructured":"Verma, P., Berger, J.: Audio transformers: transformer architectures for large scale audio understanding. adieu convolutions (2021). https:\/\/doi.org\/10.48550\/arXiv.2105.00335","DOI":"10.48550\/arXiv.2105.00335"},{"issue":"4","key":"5_CR37","doi-asserted-by":"publisher","first-page":"457","DOI":"10.1016\/s0892-1997(01)00046-7","volume":"15","author":"R Weiss","year":"2001","unstructured":"Weiss, R., Brown, W., Jr., Moris, J.: Singer\u2019s formant in sopranos: fact or fiction? J. Voice 15(4), 457\u2013468 (2001). https:\/\/doi.org\/10.1016\/s0892-1997(01)00046-7","journal-title":"J. Voice"},{"key":"5_CR38","doi-asserted-by":"publisher","unstructured":"Wilkins, J., Seetharaman, P., Wahl, A., Pardo, B.: Vocalset: a singing voice dataset. In: Proceedings of the 19th International Conference on Music Information Retrieval (ISMIR), pp. 468\u2013474 (2018). https:\/\/doi.org\/10.5281\/zenodo.1193957","DOI":"10.5281\/zenodo.1193957"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence in Music, Sound, Art and Design"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-56992-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,29]],"date-time":"2024-03-29T00:02:54Z","timestamp":1711670574000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-56992-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031569913","9783031569920"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-56992-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"29 March 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"EvoMUSART","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computational Intelligence in Music, Sound, Art and Design (Part of EvoStar)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Aberystwyth","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 April 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 April 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"evomusart2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.evostar.org\/2024\/evomusart\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-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":"55","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":"17","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":"8","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":"31% - 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":"3","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":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}