{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:24:05Z","timestamp":1773325445916,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":20,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819570713","type":"print"},{"value":"9789819570720","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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\/978-981-95-7072-0_48","type":"book-chapter","created":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:11:57Z","timestamp":1773274317000},"page":"676-683","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Empowering M\u0101ori Automatic Speech Recognition through EMD-Based Augmentation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5799-5977","authenticated-orcid":false,"given":"Chengxi","family":"Lei","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7636-3797","authenticated-orcid":false,"given":"Sheng","family":"Li","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9032-6781","authenticated-orcid":false,"given":"Satwinder","family":"Singh","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5776-9177","authenticated-orcid":false,"given":"Feng","family":"Hou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1375-4066","authenticated-orcid":false,"given":"Huia","family":"Jahnke","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-9816","authenticated-orcid":false,"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,4,1]]},"reference":[{"key":"48_CR1","doi-asserted-by":"crossref","unstructured":"Babu, A., et\u00a0al.: XLS-R: Self-supervised cross-lingual speech representation learning at scale. Interspeech 2022 (2022)","DOI":"10.21437\/Interspeech.2022-143"},{"key":"48_CR2","unstructured":"Coto-Solano, R., et al.: Development of automatic speech recognition for the documentation of cook islands m\u0101ori (2022)"},{"key":"48_CR3","unstructured":"Hannun, A., et\u00a0al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"key":"48_CR4","doi-asserted-by":"crossref","unstructured":"Rudd, H.D., Huo, H., Xu, G.: An extended variational mode decomposition algorithm developed speech emotion recognition performance. In: Pacific-Asia Conference on Knowledge Discovery and Data Mining, pp. 219\u2013231. Springer (2023)","DOI":"10.1007\/978-3-031-33380-4_17"},{"key":"48_CR5","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., et al.: 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":"48_CR6","doi-asserted-by":"crossref","unstructured":"Huang, N.E., et al.: The empirical mode decomposition and the Hilbert spectrum for nonlinear and non-stationary time series analysis. Proc. Roy. Soc. London Ser. A Math. Phys. Eng. Sci. 454(1971), 903\u2013995 (1998)","DOI":"10.1098\/rspa.1998.0193"},{"key":"48_CR7","unstructured":"Jaitly, N., Hinton, G.E.: Vocal Tract Length Perturbation (VTLP) improves speech recognition. In: Proceedings of the ICML workshop on deep learning for audio, speech and language. vol.\u00a0117, p.\u00a021 (2013)"},{"key":"48_CR8","doi-asserted-by":"crossref","unstructured":"James, J., et al.: Development of community-oriented text-to-speech models for m\u0101ori \u2018avaiki nui (cook islands m\u0101ori). In: Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 4820\u20134831 (2024)","DOI":"10.63317\/2k4rcop9hfd8"},{"key":"48_CR9","doi-asserted-by":"crossref","unstructured":"Kheddar, H., Hemis, M., Himeur, Y.: Automatic speech recognition using advanced deep learning approaches: a survey. Inf. Fusion, 102422 (2024)","DOI":"10.1016\/j.inffus.2024.102422"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Lee, J., Han, S., Cho, H., Jung, W.: PhaseAug: a differentiable augmentation for speech synthesis to simulate one-to-many mapping. In: ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096374"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Lei, C., Singh, S., Hou, F., Jia, X., Wang, R.: Phaseperturbation: speech data augmentation via phase perturbation for automatic speech recognition. In: Proceedings of the 5th ACM International Conference on Multimedia in Asia Workshops, pp.\u00a01\u20136 (2023)","DOI":"10.1145\/3611380.3628555"},{"issue":"1","key":"48_CR12","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1186\/s13636-024-00349-3","volume":"2024","author":"Y Liu","year":"2024","unstructured":"Liu, Y., Yang, X., Qu, D.: Exploration of whisper fine-tuning strategies for low-resource ASR. EURASIP J. Audio Speech Music Process. 2024(1), 29 (2024)","journal-title":"EURASIP J. Audio Speech Music Process."},{"key":"48_CR13","first-page":"2613","volume":"2019","author":"DS Park","year":"2019","unstructured":"Park, D.S.: Specaugment: a simple data augmentation method for automatic speech recognition. Interspeech 2019, 2613 (2019)","journal-title":"Interspeech"},{"key":"48_CR14","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1109\/TASLP.2023.3328283","volume":"32","author":"R Prabhavalkar","year":"2023","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 (2023)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"48_CR15","doi-asserted-by":"crossref","unstructured":"Singh, S., Hou, F., Wang, R.: A novel self-training approach for low-resource speech recognition. In: Proceedings of the Interspeech 2023, pp. 1588\u20131592 (2023)","DOI":"10.21437\/Interspeech.2023-540"},{"key":"48_CR16","doi-asserted-by":"publisher","DOI":"10.1016\/j.dib.2023.109865","volume":"52","author":"S Singh","year":"2024","unstructured":"Singh, S., Hou, F., Wang, R.: Real and synthetic Punjabi speech datasets for automatic speech recognition. Data Brief 52, 109865 (2024)","journal-title":"Data Brief"},{"key":"48_CR17","first-page":"551","volume":"2021","author":"H Wang","year":"2021","unstructured":"Wang, H., Zou, Y., Wang, W.: Specaugment++: a hidden space data augmentation method for acoustic scene classification. Interspeech 2021, 551\u2013555 (2021)","journal-title":"Interspeech"},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Wang, Z., et\u00a0al.: Cyclicaugment: speech data random augmentation with cosine annealing scheduler for auotmatic speech recognition. In: Interspeech, pp. 3859\u20133863 (2022)","DOI":"10.21437\/Interspeech.2022-526"},{"key":"48_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Hou, F., Wang, R.: Clrl-tuning: a novel continual learning approach for automatic speech recognition. In: Proceedings of the Interspeech 2023, pp. 1279\u20131283 (2023)","DOI":"10.21437\/Interspeech.2023-503"},{"issue":"5","key":"48_CR20","doi-asserted-by":"publisher","first-page":"6112","DOI":"10.1016\/j.eswa.2010.11.013","volume":"38","author":"JD Wu","year":"2011","unstructured":"Wu, J.D., Tsai, Y.J.: Speaker identification system using empirical mode decomposition and an artificial neural network. Expert Syst. Appl. 38(5), 6112\u20136117 (2011)","journal-title":"Expert Syst. Appl."}],"container-title":["Lecture Notes in Computer Science","PRICAI 2025: Trends in Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-7072-0_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T00:12:00Z","timestamp":1773274320000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-7072-0_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819570713","9789819570720"],"references-count":20,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-7072-0_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"1 April 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Pacific Rim International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Wellington","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"New Zealand","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":"17 November 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"pricai2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.pricai.org\/2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}