{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T00:17:11Z","timestamp":1742948231969,"version":"3.40.3"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031723490"},{"type":"electronic","value":"9783031723506"}],"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\/978-3-031-72350-6_1","type":"book-chapter","created":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:14:50Z","timestamp":1726661690000},"page":"3-15","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Breaking the\u00a0Corpus Bottleneck for\u00a0Multi-dialect Speech Recognition with\u00a0Flexible Adapters"],"prefix":"10.1007","author":[{"given":"Tengyue","family":"Deng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianguo","family":"Wei","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Minghao","family":"Guo","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenjun","family":"Ke","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wenhuan","family":"Lu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,9,17]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bapna, A., Arivazhagan, N., Firat, O.: Simple, scalable adaptation for neural machine translation. arXiv preprint arXiv:1909.08478 (2019)","DOI":"10.18653\/v1\/N19-1191"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Baziotis, C., Artetxe, M., Cross, J., Bhosale, S.: Multilingual machine translation with hyper-adapters. arXiv preprint arXiv:2205.10835 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.77"},{"key":"1_CR3","unstructured":"Chan, W., Park, D., Lee, C., Zhang, Y., Le, Q., Norouzi, M.: Speechstew: simply mix all available speech recognition data to train one large neural network. arXiv preprint arXiv:2104.02133 (2021)"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Das, A., Kumar, K., Wu, J.: Multi-dialect speech recognition in English using attention on ensemble of experts. In: ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6244\u20136248. IEEE (2021)","DOI":"10.1109\/ICASSP39728.2021.9413952"},{"key":"1_CR5","unstructured":"Engelhart, E., Elyasi, M., Bharaj, G.: Grapheme-to-phoneme transformer model for transfer learning dialects. arXiv preprint arXiv:2104.04091 (2021)"},{"key":"1_CR6","first-page":"317","volume":"30","author":"W Hou","year":"2021","unstructured":"Hou, W., et al.: Exploiting adapters for cross-lingual low-resource speech recognition. IEEE-ACM Trans. Audio SPE 30, 317\u2013329 (2021)","journal-title":"IEEE-ACM Trans. Audio SPE"},{"key":"1_CR7","unstructured":"Houlsby, N., et al.: Parameter-efficient transfer learning for NLP. In: International Conference on Machine Learning, pp. 2790\u20132799. PMLR (2019)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Kannan, A., et al.: Large-scale multilingual speech recognition with a streaming end-to-end model. arXiv preprint arXiv:1909.05330 (2019)","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Kunze, J., Kirsch, L., Kurenkov, I., Krug, A., Johannsmeier, J., Stober, S.: Transfer learning for speech recognition on a budget. arXiv preprint arXiv:1706.00290 (2017)","DOI":"10.18653\/v1\/W17-2620"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Li, B., et al.: Multi-dialect speech recognition with a single sequence-to-sequence model. In: 2018 IEEE international conference on acoustics, speech and signal processing (ICASSP), pp. 4749\u20134753. IEEE (2018)","DOI":"10.1109\/ICASSP.2018.8461886"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Liu, Y., Zhao, Y., Xu, X., Xu, L., Zhang, X.: Multi-task pre-training for Lhasa-Tibetan speech recognition. In: International Conference on Artificial Neural Networks, pp. 78\u201390. Springer (2023). https:\/\/doi.org\/10.1007\/978-3-031-44201-8_7","DOI":"10.1007\/978-3-031-44201-8_7"},{"key":"1_CR12","doi-asserted-by":"crossref","unstructured":"Luo, J., Wang, J., Cheng, N., Zheng, Z., Xiao, J.: Adaptive activation network for low resource multilingual speech recognition. In: 2022 International Joint Conference on Neural Networks (IJCNN), pp.\u00a01\u20137. IEEE (2022)","DOI":"10.1109\/IJCNN55064.2022.9892396"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Pan, L., Li, S., Wang, L., Dang, J.: Effective training end-to-end ASR systems for low-resource Lhasa dialect of Tibetan language. In: 2019 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 1152\u20131156. IEEE (2019)","DOI":"10.1109\/APSIPAASC47483.2019.9023100"},{"key":"1_CR14","unstructured":"Pham, M.Q., Crego, J.M., Yvon, F., Senellart, J.: A study of residual adapters for multi-domain neural machine translation. In: Conference on Machine Translation (2020)"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Philip, J., Berard, A., Gall\u00e9, M., Besacier, L.: Monolingual adapters for zero-shot neural machine translation. In: Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), pp. 4465\u20134470 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.361"},{"issue":"1","key":"1_CR16","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13636-021-00231-6","volume":"2022","author":"S Qin","year":"2022","unstructured":"Qin, S., Wang, L., Li, S., Dang, J., Pan, L.: Improving low-resource Tibetan end-to-end ASR by multilingual and multilevel unit modeling. Eurasip J. Audio Spee. 2022(1), 1\u201310 (2022)","journal-title":"Eurasip J. Audio Spee."},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Qin, S., Wang, L., Li, S., Lin, Y., Dang, J.: Finer-grained modeling units-based meta-learning for low-resource Tibetan speech recognition. In: Proceedings Interspeech (2022)","DOI":"10.21437\/Interspeech.2022-10015"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Shetty, V.M., NJ, M.S.M.: Improving the performance of transformer based low resource speech recognition for Indian languages. In: ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 8279\u20138283. IEEE (2020)","DOI":"10.1109\/ICASSP40776.2020.9053808"},{"key":"1_CR19","unstructured":"Sun, H., Xiong, D.: Language branch gated multilingual neural machine translation. In: Proceedings of the 29th International Conference on Computational Linguistics, pp. 5046\u20135053 (2022)"},{"key":"1_CR20","doi-asserted-by":"crossref","unstructured":"Thomas, B., Kessler, S., Karout, S.: Efficient adapter transfer of self-supervised speech models for automatic speech recognition. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7102\u20137106. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9746223"},{"key":"1_CR21","doi-asserted-by":"crossref","unstructured":"Vander\u00a0Eeckt, S., Van\u00a0Hamme, H.: Using adapters to overcome catastrophic forgetting in end-to-end automatic speech recognition. In: ICASSP 2023\u20132023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10095837"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Wang, C., Pino, J., Gu, J.: Improving cross-lingual transfer learning for end-to-end speech recognition with speech translation. arXiv preprint arXiv:2006.05474 (2020)","DOI":"10.21437\/Interspeech.2020-2955"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Yan, J., Lv, Z., Huang, S., Yu, H.: Low-resource Tibetan dialect acoustic modeling based on transfer learning. In: SLTU, pp. 6\u201310 (2018)","DOI":"10.21437\/SLTU.2018-2"},{"key":"1_CR24","doi-asserted-by":"crossref","unstructured":"Yang, J., et al.: Effective fine-tuning method for Tibetan low-resource dialect speech recognition. In: 2023 Asia Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA ASC), pp. 960\u2013965. IEEE (2023)","DOI":"10.1109\/APSIPAASC58517.2023.10317230"},{"key":"1_CR25","doi-asserted-by":"crossref","unstructured":"Yang, X., Wang, W., Yang, H., Jiang, J.: Simple data augmented transformer end-to-end tibetan speech recognition. In: 2020 IEEE 3rd International Conference on Information Communication and Signal Processing (ICICSP), pp. 148\u2013152. IEEE (2020)","DOI":"10.1109\/ICICSP50920.2020.9232114"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Zalmout, N., Habash, N.: Adversarial multitask learning for joint multi-feature and multi-dialect morphological modeling. arXiv preprint arXiv:1910.12702 (2019)","DOI":"10.18653\/v1\/P19-1173"},{"key":"1_CR27","unstructured":"Zhang, Y.: Research on Tibetan Lhasa dialect speech recognition based on deep learning, (ph. d. thesis) (2016)"},{"issue":"1","key":"1_CR28","doi-asserted-by":"publisher","first-page":"17","DOI":"10.32604\/jiot.2019.05866","volume":"1","author":"Y Zhao","year":"2019","unstructured":"Zhao, Y., et al.: Tibetan multi-dialect speech recognition using latent regression Bayesian network and end-to-end mode. J. Int. Things 1(1), 17 (2019)","journal-title":"J. Int. Things"},{"issue":"1","key":"1_CR29","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1109\/JPROC.2020.3004555","volume":"109","author":"F Zhuang","year":"2020","unstructured":"Zhuang, F., et al.: A comprehensive survey on transfer learning. Proc. IEEE 109(1), 43\u201376 (2020)","journal-title":"Proc. IEEE"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-72350-6_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,18]],"date-time":"2024-09-18T12:15:09Z","timestamp":1726661709000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72350-6_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9783031723490","9783031723506"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72350-6_1","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":"17 September 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lugano","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Switzerland","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":"17 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20 September 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"33","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}