{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:26Z","timestamp":1776885206898,"version":"3.51.2"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10887613","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":3,"title":["Text-guided Device-realistic Sound Generation for Fiber-based Sound Event Classification"],"prefix":"10.1109","author":[{"given":"Wataru","family":"Kohno","sequence":"first","affiliation":[{"name":"NEC Laboratories America, Inc,The United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Noriyuki","family":"Tonami","sequence":"additional","affiliation":[{"name":"NEC Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jian","family":"Fang","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Inc,The United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shaobo","family":"Han","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Inc,The United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingchen","family":"Sun","sequence":"additional","affiliation":[{"name":"The State University of New York at Buffalo,NEC Laboratories America, Inc,The United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ting","family":"Wang","sequence":"additional","affiliation":[{"name":"NEC Laboratories America, Inc,The United States of America"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2022.3199742"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2022.3208451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1364\/OE.414598"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref5","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. International Conference on Machine Learning","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref8","first-page":"31","article-title":"Description and discussion on dcase 2022 challenge task 2: Unsupervised anomalous sound detection for machine condition monitoring applying domain generalization techniques","volume-title":"Proc. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Dohi"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.5555\/3294996.3295163"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413584"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1082"},{"key":"ref12","first-page":"230","article-title":"Two-stage domain adaptation for sound event detection","volume-title":"Proc. Workshop on Detection and Classification of Acoustic Scenes and Events (DCASE)","author":"Yang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3044153"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref15","first-page":"48382","article-title":"Stablerep: synthetic images from text-to-image models make strong visual representation learners","volume-title":"Proc. International Conference on Neural Information Processing Systems (NuerIPS)","author":"Tian"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00705"},{"key":"ref17","first-page":"1","article-title":"SynthCLIP: Are we ready for a fully synthetic CLIP training?","volume-title":"Proc. Synthetic Data for Computer Vision Workshop @ CVPR 2024","author":"Hammoud"},{"key":"ref18","first-page":"1","article-title":"AudioGen: Textually guided audio generation","volume-title":"Proc. International Conference on Learning Representations (ICLR)","author":"Kreuk"},{"key":"ref19","first-page":"21450","article-title":"AudioLDM: Text-to-audio generation with latent diffusion models","volume-title":"Proc. International Conference on Machine Learning","author":"Liu"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-1350"},{"key":"ref22","article-title":"Synthe-sizing soundscapes: Leveraging text-to-audio models for environmental sound classification","author":"Ronchini","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/JLT.2019.2919713"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2017.2657381"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10468"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO58844.2023.10289983"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1364\/OFS.2023.Tu3.33"},{"key":"ref32","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. International conference on machine learning (ICML)","author":"Radford"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10887613.pdf?arnumber=10887613","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:24:54Z","timestamp":1774416294000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887613\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887613","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}