{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:15:41Z","timestamp":1787012141789,"version":"3.56.0"},"reference-count":17,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9053193","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"7474-7478","source":"Crossref","is-referenced-by-count":35,"title":["Training Keyword Spotters with Limited and Synthesized Speech Data"],"prefix":"10.1109","author":[{"given":"James","family":"Lin","sequence":"first","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kevin","family":"Kilgour","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dominik","family":"Roblek","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthew","family":"Sharifi","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00610"},{"key":"ref11","article-title":"Data Augmentation for Robust Keyword Spotting under Playback Interference","author":"raju","year":"2018"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU46091.2019.9003990"},{"key":"ref13","article-title":"Using Synthesized Speech to Improve Speech Recognition for Low–Resource Languages","author":"rygaard","year":"2015"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461368"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2204"},{"key":"ref16","article-title":"Compressed Time Delay Neural Network for Small-Footprint Keyword Spotting","author":"et al","year":"2017","journal-title":"TERSPEECH"},{"key":"ref17","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"warden","year":"2018"},{"key":"ref4","article-title":"Google Cloud Text-to-Speech API","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1363"},{"key":"ref6","article-title":"Deep Residual Learning for Image Recognition","author":"he","year":"2015"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683474"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"477","DOI":"10.1109\/SLT.2018.8639589","article-title":"Leveraging Sequence-to-Sequence Speech Synthesis for Enhancing Acoustic-to-Word Speech Recognition","author":"mimura","year":"2018","journal-title":"Spoken Language Technology Workshop (SLT) IEEE"},{"key":"ref7","article-title":"Training Neural Speech Recognition Systems with Synthetic Speech Augmentation","author":"li","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854370"},{"key":"ref1","article-title":"TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems","author":"abadi","year":"2016"},{"key":"ref9","article-title":"WaveNet: A Generative Model for Raw Audio","author":"van den oord","year":"2016"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09053193.pdf?arnumber=9053193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,25]],"date-time":"2025-08-25T20:40:08Z","timestamp":1756154408000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9053193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":17,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9053193","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}