{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T19:45:18Z","timestamp":1730231118599,"version":"3.28.0"},"reference-count":28,"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\/icassp49357.2023.10095508","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":3,"title":["Understanding Shared Speech-Text Representations"],"prefix":"10.1109","author":[{"given":"Gary","family":"Wang","sequence":"first","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Kastner","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ankur","family":"Bapna","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhehuai","family":"Chen","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Rosenberg","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bhuvana","family":"Ramabhadran","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Google LLC,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10114"},{"journal-title":"SpeechStew Simply mix all available speech recognition data to train one large neural network","year":"2021","author":"chan","key":"ref12"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-239"},{"journal-title":"Speechbert An audio-and-text jointly learned language model for end-to-end spoken question answering","year":"2019","author":"chuang","key":"ref14"},{"key":"ref11","article-title":"Maestro-u: Leveraging joint speech-text representation learning for zero supervised speech asr","author":"chen","year":"2022","journal-title":"IEEE SLT"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"6645","DOI":"10.1109\/ICASSP.2013.6638947","article-title":"Speech recognition with deep recurrent neural networks","author":"graves","year":"2013","journal-title":"2013 IEEE International Conference on Acoustics Speech and Signal Processing"},{"journal-title":"mSLAM Massively multilingual joint pre-training for speech and text","year":"2022","author":"bapna","key":"ref2"},{"journal-title":"SLAM A unified encoder for speech and language modeling via speech-text joint pre-training","year":"2021","author":"bapna","key":"ref1"},{"key":"ref17","first-page":"8992","article-title":"Learning relationships between text, audio, and video via deep canonical correlation for multi-modal language analysis","author":"sun","year":"2020","journal-title":"The Thirty-Fourth AAAI Conference on Artificial Intelligence AAAI 2020 The Thirty-Second Innovative Applications of Artificial Intelligence Conference IAAI 2020 The Tenth AAAI Symposium on Educational Advances in Artificial Intelligence EAAI 2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472619"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2828"},{"journal-title":"Fleurs Few-shot learning evaluation of universal representations of speech","year":"2022","author":"conneau","key":"ref24"},{"key":"ref23","article-title":"Visualizing data using t-sne","volume":"9","author":"der maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref26","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"radford","year":"2021","journal-title":"International Conference on Machine Learning"},{"key":"ref25","first-page":"27826","article-title":"Unsupervised speech recognition","volume":"34","author":"baevski","year":"2021","journal-title":"Advances in neural information processing systems"},{"journal-title":"Fused acoustic and text encoding for multimodal bilingual pretraining and speech translation","year":"2021","author":"zheng","key":"ref20"},{"journal-title":"w2v-bert Combining contrastive learning and masked language modeling for self-supervised speech pre-training","year":"2021","author":"chung","key":"ref22"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052942"},{"journal-title":"Asif Coupled data turns unimodal models to multimodal without training","year":"2022","author":"norelli","key":"ref28"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1111\/j.1756-8765.2010.01109.x"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11123"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747862"},{"journal-title":"Sequence transduction with recurrent neural networks","year":"2012","author":"graves","key":"ref9"},{"key":"ref4","article-title":"Joist: A joint speech and text streaming model for asr","author":"sainath","year":"2022","journal-title":"IEEE SLT"},{"journal-title":"Maestro Matched speech text representations through modality matching","year":"2022","author":"chen","key":"ref3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-13"},{"key":"ref5","article-title":"Modular hybrid autoregressive transducer","author":"meng","year":"2022","journal-title":"to appear in SLT"}],"event":{"name":"ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","start":{"date-parts":[[2023,6,4]]},"location":"Rhodes Island, Greece","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\/10095508.pdf?arnumber=10095508","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T22:25:04Z","timestamp":1698099904000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095508\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":28,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095508","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}