{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T15:00:02Z","timestamp":1743087602341,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":17,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819743988"},{"type":"electronic","value":"9789819743995"}],"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\/978-981-97-4399-5_12","type":"book-chapter","created":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:01:52Z","timestamp":1720281712000},"page":"123-132","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["PhonHuBERT: A Phoneme Transcription Tool for\u00a0Song Datasets"],"prefix":"10.1007","author":[{"given":"Amaury","family":"Prat","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Runxuan","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Hu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,7,7]]},"reference":[{"key":"12_CR1","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)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR2","doi-asserted-by":"crossref","unstructured":"Li, J., et\u00a0al.: Recent advances in end-to-end automatic speech recognition. APSIPA Trans. Signal Inf. Process. 11(1) (2022)","DOI":"10.1561\/116.00000050"},{"key":"12_CR3","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1109\/TASLP.2023.3328283","volume":"32","author":"R Prabhavalkar","year":"2024","unstructured":"Prabhavalkar, R., Hori, T., Sainath, T.N., Schl\u00fcter, R., Watanabe, S.: End-to-end speech recognition: a survey. IEEE\/ACM Trans. Audio Speech Lang. Process. 32, 325\u2013351 (2024)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"12_CR4","doi-asserted-by":"crossref","unstructured":"Zeyer, A., Bahar, P., Irie, K., Schl\u00fcter, R., Ney, H.: A comparison of transformer and LSTM encoder decoder models for ASR. In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU), pp. 8\u201315 (2019)","DOI":"10.1109\/ASRU46091.2019.9004025"},{"key":"12_CR5","doi-asserted-by":"crossref","unstructured":"Li, J., Wu, Y., Gaur, Y., Wang, C., Zhao, R., Liu, S.: On the comparison of popular end-to-end models for large scale speech recognition. In: Interspeech 2020 (2020)","DOI":"10.21437\/Interspeech.2020-2846"},{"key":"12_CR6","doi-asserted-by":"crossref","unstructured":"Gulati, A., et al.: Conformer: convolution-augmented transformer for speech recognition. In: Interspeech 2020, pp. 5036\u20135040 (2020)","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"12_CR7","doi-asserted-by":"crossref","unstructured":"Stoller, D., Durand, S., Ewert, S.: End-to-end lyrics alignment for polyphonic music using an audio-to-character recognition model. In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 181\u2013185 (2019)","DOI":"10.1109\/ICASSP.2019.8683470"},{"key":"12_CR8","doi-asserted-by":"crossref","unstructured":"Teytaut, Y., Roebel, A.: Phoneme-to-audio alignment with recurrent neural networks for speaking and singing voice. In: Interspeech 2021, pp. 61\u201365 (2021)","DOI":"10.21437\/Interspeech.2021-1676"},{"key":"12_CR9","doi-asserted-by":"crossref","unstructured":"McAuliffe, M., Socolof, M., Mihuc, S., Wagner, M., Sonderegger, M.: Montreal forced aligner: trainable text-speech alignment using Kaldi. In: Interspeech 2017, pp. 498\u2013502 (2017)","DOI":"10.21437\/Interspeech.2017-1386"},{"key":"12_CR10","doi-asserted-by":"crossref","unstructured":"Schulze-Forster, K., Doire, C.S., Richard, G., Badeau, R.: Joint phoneme alignment and text-informed speech separation on highly corrupted speech. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7274\u20137278 (2020)","DOI":"10.1109\/ICASSP40776.2020.9053182"},{"key":"12_CR11","doi-asserted-by":"crossref","unstructured":"Boulianne, G.: Phoneme transcription of endangered languages: an evaluation of recent ASR architectures in the single speaker scenario. In: Findings of the Association for Computational Linguistics: ACL 2022, pp. 2301\u20132308 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.180"},{"key":"12_CR12","unstructured":"Adams, O., Cohn, T., Neubig, G., Cruz, H., Bird, S., Michaud, A.: Evaluating phonemic transcription of low-resource tonal languages for language documentation. In: 11th International Conference on Language Resources and Evaluation, LREC 2018, pp. 3356\u20133365 (2019)"},{"key":"12_CR13","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: Opencpop: a high-quality open source Chinese popular song corpus for singing voice synthesis. In: Interspeech 2022, pp. 4242\u20134246 (2022)","DOI":"10.21437\/Interspeech.2022-48"},{"key":"12_CR14","doi-asserted-by":"crossref","unstructured":"van Niekerk, B., Carbonneau, M.A., Za\u00efdi, J., Baas, M., Seut\u00e9, H., Kamper, H.: A comparison of discrete and soft speech units for improved voice conversion. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6562\u20136566 (2022)","DOI":"10.1109\/ICASSP43922.2022.9746484"},{"key":"12_CR15","unstructured":"Kingma, D., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations (2014)"},{"key":"12_CR16","doi-asserted-by":"crossref","unstructured":"McFee, B., et al.: librosa: audio and music signal analysis in python. In: SciPy, pp. 18\u201324 (2015)","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"12_CR17","doi-asserted-by":"crossref","unstructured":"Lin, T.Y., Goyal, P., Girshick, R., He, K., Doll\u00e1r, P.: Focal loss for dense object detection. In: IEEE International Conference on Computer Vision, pp. 2980\u20132988 (2017)","DOI":"10.1109\/ICCV.2017.324"}],"container-title":["Lecture Notes in Computer Science","Advances in Neural Networks \u2013 ISNN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-4399-5_12","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,6]],"date-time":"2024-07-06T16:03:36Z","timestamp":1720281816000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-4399-5_12"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819743988","9789819743995"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-4399-5_12","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":"7 July 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISNN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Weihai","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 July 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 July 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isnn2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/conference.cs.cityu.edu.hk\/isnn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}