{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,24]],"date-time":"2025-06-24T04:04:30Z","timestamp":1750737870181,"version":"3.41.0"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819665815","type":"print"},{"value":"9789819665822","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-6582-2_3","type":"book-chapter","created":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:40:42Z","timestamp":1750689642000},"page":"36-50","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Improving Multilingual Speech Recognition with\u00a0Tucker-Compressed Mixture of\u00a0LoRAs"],"prefix":"10.1007","author":[{"given":"Ye","family":"Hong","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guanghui","family":"Song","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xitong","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhui","family":"Meng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Juanjuan","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kejiang","family":"Ye","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,6,24]]},"reference":[{"issue":"3","key":"3_CR1","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1109\/MSP.2010.936030","volume":"27","author":"G Bergqvist","year":"2010","unstructured":"Bergqvist, G., Larsson, E.G.: The higher-order singular value decomposition: theory and an application [lecture notes]. IEEE Signal Process. Mag. 27(3), 151\u2013154 (2010). https:\/\/doi.org\/10.1109\/MSP.2010.936030","journal-title":"IEEE Signal Process. Mag."},{"key":"3_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019)"},{"key":"3_CR3","unstructured":"Gandhi, S., von Platen, P., Rush, A.M.: Esb: a benchmark for multi-domain end-to-end speech recognition (2022)"},{"issue":"5","key":"3_CR4","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1007\/BF02163027","volume":"14","author":"GH Golub","year":"1970","unstructured":"Golub, G.H., Reinsch, C.: Singular value decomposition and least squares solutions. Numer. Math. 14(5), 403\u2013420 (1970)","journal-title":"Numer. Math."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Graves, A., Mohamed, A.R., Hinton, G.: Speech recognition with deep recurrent neural networks. In: 2013 IEEE International Conference on Acoustics, Speech and Signal Processing. pp. 6645\u20136649. IEEE (2013)","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"3_CR6","unstructured":"Harshman, R.A.: Foundations of the parafac procedure: models and conditions for an \u201cexplanatory\u201d multi-modal factor analysis. UCLA Working Papers Phonetics 16(1), 84\u2013110 (1970)"},{"key":"3_CR7","unstructured":"Hu, E.J., et al.: Lora: low-rank adaptation of large language models (2021)"},{"key":"3_CR8","unstructured":"Huang, C., Liu, Q., Lin, B.Y., Pang, T., Du, C., Lin, M.: Lorahub: efficient cross-task generalization via dynamic lora composition (2024)"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Kannan, A., et al.: Large-scale multilingual speech recognition with a streaming end-to-end model (2019). https:\/\/arxiv.org\/abs\/1909.05330","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"3_CR10","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization (2017). https:\/\/arxiv.org\/abs\/1412.6980"},{"issue":"4","key":"3_CR11","doi-asserted-by":"publisher","first-page":"1253","DOI":"10.1137\/S0895479896305696","volume":"21","author":"LD Lathauwer","year":"2000","unstructured":"Lathauwer, L.D., Bie, T.D., Moor, B.D.: A multilinear singular value decomposition. SIAM J. Matrix Anal. Appl. 21(4), 1253\u20131278 (2000)","journal-title":"SIAM J. Matrix Anal. Appl."},{"key":"3_CR12","doi-asserted-by":"crossref","unstructured":"Liu, W., Hou, J., Yang, D., Cao, M., Lee, T.: A parameter-efficient language extension framework for multilingual asr (2024). https:\/\/arxiv.org\/abs\/2406.06329","DOI":"10.21437\/Interspeech.2024-1745"},{"key":"3_CR13","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization (2019). https:\/\/arxiv.org\/abs\/1711.05101"},{"key":"3_CR14","unstructured":"Radford, A., et al.: Robust speech recognition via large-scale weak supervision. In: International Conference on Machine Learning, pp. 28492\u201328518. PMLR (2023)"},{"issue":"8","key":"3_CR15","first-page":"9","volume":"1","author":"A Radford","year":"2019","unstructured":"Radford, A., Wu, J., Child, R., Luan, D., Amodei, D., Sutskever, I., et al.: Language models are unsupervised multitask learners. OpenAI blog 1(8), 9 (2019)","journal-title":"OpenAI blog"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Song, Z., Zhuo, J., Yang, Y., Ma, Z., Zhang, S., Chen, X.: Lora-whisper: Parameter-efficient and extensible multilingual asr (2024). https:\/\/arxiv.org\/abs\/2406.06619","DOI":"10.21437\/Interspeech.2024-892"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Yang, M., Tjandra, A., Liu, C., Zhang, D., Le, D., Kalinli, O.: Learning asr pathways: A sparse multilingual asr model (2023). https:\/\/arxiv.org\/abs\/2209.05735","DOI":"10.1109\/ICASSP49357.2023.10094300"},{"key":"3_CR18","doi-asserted-by":"publisher","unstructured":"Ye, Q., Lin, B.Y., Ren, X.: Crossfit: a few-shot learning challenge for cross-task generalization in nlp. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 7163\u20137189. Association for Computational Linguistics, https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.572, https:\/\/aclanthology.org\/2021.emnlp-main.572","DOI":"10.18653\/v1\/2021.emnlp-main.572"},{"key":"3_CR19","doi-asserted-by":"crossref","unstructured":"Zhu, Y., et al.: Multilingual speech recognition with self-attention structured parameterization. In: Interspeech 2020, 21st Annual Conference of the International Speech Communication Association (2020)","DOI":"10.21437\/Interspeech.2020-2847"}],"container-title":["Lecture Notes in Computer Science","Neural Information Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-6582-2_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,23]],"date-time":"2025-06-23T14:40:48Z","timestamp":1750689648000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-6582-2_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819665815","9789819665822"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-6582-2_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"24 June 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICONIP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Neural Information Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Auckland","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 December 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 December 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iconip2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/iconip2024.org","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}