{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:54:08Z","timestamp":1777128848612,"version":"3.51.4"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,4]],"date-time":"2023-06-04T00:00:00Z","timestamp":1685836800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6,4]]},"DOI":"10.1109\/icassp49357.2023.10094903","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T17:28:30Z","timestamp":1683307710000},"page":"1-5","source":"Crossref","is-referenced-by-count":16,"title":["From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-Lingual Speech Recognition"],"prefix":"10.1109","author":[{"given":"Chao-Han Huck","family":"Yang","sequence":"first","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bo","family":"Li","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nanxin","family":"Chen","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rohit","family":"Prabhavalkar","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tara N.","family":"Sainath","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Trevor","family":"Strohman","sequence":"additional","affiliation":[{"name":"Google,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1006"},{"key":"ref35","article-title":"Unsupervised cross-lingual representation learning for speech recognition","author":"conneau","year":"2020","journal-title":"Proc INTERSPEECH"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1242"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414502"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.541"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3200910"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.1"},{"key":"ref31","article-title":"Lingvo: a modular and scalable framework for sequence-to-sequence modeling","author":"shen","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688101"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1868"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746038"},{"key":"ref10","article-title":"Sequence transduction with recurrent neural networks","author":"graves","year":"2012","journal-title":"ICML Representation Workshop"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2826"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2014.08.005"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682336"},{"key":"ref17","first-page":"11 808","article-title":"Voice2series: Reprogramming acoustic models for time series classification","author":"yang","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref16","first-page":"2790","article-title":"Parameter-efficient transfer learning for nlp","author":"houlsby","year":"2019","journal-title":"International Conference on Machine Learning"},{"key":"ref19","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"kenton","year":"2019","journal-title":"Proceedings of NAACL-HLT"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10610"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1165"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2560534"},{"key":"ref26","article-title":"A study of low-resource speech commands recognition based on adversarial reprogramming","author":"yen","year":"2021"},{"key":"ref25","article-title":"Adversarial reprogramming of neural networks","author":"elsayed","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2858"},{"key":"ref21","article-title":"Learning multiple visual domains with residual adapters","volume":"30","author":"rebuffi","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref28","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"2018","journal-title":"International Conference on Learning Representations"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.381"},{"key":"ref29","first-page":"5659","article-title":"Sca-cnn: Spatial and channel-wise attention in convolutional networks for image captioning","author":"chen","year":"2017","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"ref7","first-page":"12 449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume":"33","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3182537"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687871"},{"key":"ref3","first-page":"4774","article-title":"State-of-the-art speech recognition with sequence-to-sequence models","author":"chiu","year":"2018","journal-title":"Proc ICASSP"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054715"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746594"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Rhodes Island, Greece","start":{"date-parts":[[2023,6,4]]},"end":{"date-parts":[[2023,6,10]]}},"container-title":["ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10094559\/10094560\/10094903.pdf?arnumber=10094903","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T18:59:49Z","timestamp":1700506789000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094903\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094903","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}