{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T12:17:25Z","timestamp":1773317845346,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3611380.3628555","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T12:03:31Z","timestamp":1703937811000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["PhasePerturbation: Speech Data Augmentation via Phase Perturbation for Automatic Speech Recognition"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-5799-5977","authenticated-orcid":false,"given":"Chengxi","family":"Lei","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Dalian Maritime University, China and School of Mathematical and Computational Sciences, Massey university, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9032-6781","authenticated-orcid":false,"given":"Satwinder","family":"Singh","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5776-9177","authenticated-orcid":false,"given":"Feng","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, New Zealand"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5525-9349","authenticated-orcid":false,"given":"Xiaoyun","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Governance & School of Political Science and Public Administration, Shandong University, CN"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2899-9816","authenticated-orcid":false,"given":"Ruili","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Mathematical and Computational Sciences, Massey University, NZ and School of Artificial Intelligence, Dalian Maritime University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","unstructured":"Alexei Baevski Henry Zhou Abdelrahman Mohamed and Michael Auli. 2020. wav2vec 2.0: A Framework for Self-Supervised Learning of Speech Representations. In NeurIPS. 12449\u201312460. https:\/\/doi.org\/10.48550\/arXiv.2006.11477","DOI":"10.48550\/arXiv.2006.11477"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1904.08779"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095036"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2011.2134090"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1412.5567"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2012.2205597"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053112"},{"key":"e_1_3_2_1_10_1","volume-title":"Proceedings of the 30 th Int. Conf. Mach. Learn. 90","author":"Jaitly Navdeep","year":"2013","unstructured":"Navdeep Jaitly and Geoffrey Hinton. 2013. Vocal Tract Length Perturbation (VTLP) improves speech recognition. In Proceedings of the 30 th Int. Conf. Mach. Learn. 90 (2013). 42\u201351. https:\/\/doi.org\/"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"key":"e_1_3_2_1_12_1","unstructured":"Tero Karras Samuli Laine Miika Aittala Janne Hellsten Jaakko Lehtinen and Timo Aila. 2020. Training Generative Adversarial Networks with Limited Data. In NeurIPS. 12104\u201312114."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383605"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-1510"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-103"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2015-711"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096374"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414483"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","unstructured":"Max Morrison Rithesh Kumar Kundan Kumar Prem Seetharaman Aaron Courville and Yoshua Bengio. 2022. Chunked Autoregressive GAN for Conditional Waveform Synthesis. In ICLR. https:\/\/doi.org\/10.48550\/arXiv.2110.10139","DOI":"10.48550\/arXiv.2110.10139"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178964"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472644"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","unstructured":"Satwinder Singh Feng Hou and Ruili Wang. 2023. A Novel Self-training Approach for Low-resource Speech Recognition. https:\/\/doi.org\/doi.org\/10.48550\/arXiv.2308.05269","DOI":"10.48550\/arXiv.2308.05269"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746899"},{"key":"e_1_3_2_1_24_1","unstructured":"Satwinder Singh Ruili Wang Feng Hou and Zhizhong Ma. 2023. Enhancing End-to-End Automatic Speech Recognition for Low-resource Punjabi Language using Synthesized Datasets. https:\/\/doi.org\/SSRN 4181844"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2275"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2103.16858"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-526"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-711"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.09412"}],"event":{"name":"MMAsia '23: ACM Multimedia Asia","location":"Tainan Taiwan","acronym":"MMAsia '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["ACM Multimedia Asia Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628555","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611380.3628555","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:09:34Z","timestamp":1756235374000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628555"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":30,"alternative-id":["10.1145\/3611380.3628555","10.1145\/3611380"],"URL":"https:\/\/doi.org\/10.1145\/3611380.3628555","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}