{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T18:35:05Z","timestamp":1776882905397,"version":"3.51.2"},"reference-count":29,"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\/icassp49357.2023.10095019","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":8,"title":["Speech Summarization of Long Spoken Document: Improving Memory Efficiency of Speech\/Text Encoders"],"prefix":"10.1109","author":[{"given":"Takatomo","family":"Kano","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsunori","family":"Ogawa","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Marc","family":"Delcroix","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Roshan","family":"Sharma","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kohei","family":"Matsuura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Pittsburgh,USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"ACL"},{"key":"ref12","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020","journal-title":"ArXiv"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.naacl-main.319"},{"key":"ref14","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"sanabria","year":"2018","journal-title":"ArXiv"},{"key":"ref11","first-page":"17283","article-title":"Big bird: Transformers for longer sequences","author":"zaheer","year":"2020","journal-title":"NIPS"},{"key":"ref10","first-page":"449","article-title":"A comparative study on transformer vs RNN in speech applications","author":"karita","year":"2019","journal-title":"ASRU"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746699"},{"key":"ref1","first-page":"316","article-title":"An effective contextual language modeling framework for speech summarization with augmented features","author":"weng","year":"2020","journal-title":"EUSIPCO"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17325"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2018.07.029"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref24","first-page":"1106","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref26","first-page":"4171","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref25","article-title":"Deep learning using rectified linear units (relu)","author":"agarap","year":"2018","journal-title":"ArXiv"},{"key":"ref20","article-title":"A cross-modal fusion network based on self-attention and residual structure for multimodal emotion recognition","author":"fu","year":"2021","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414858"},{"key":"ref21","article-title":"A survey of transformers","author":"lin","year":"2021","journal-title":"ArXiv"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1456"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383462"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref8","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"NIPS"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747320"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1210"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-537"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687977"},{"key":"ref5","article-title":"Abstractive summarization of spoken and written instructions with BERT","author":"savelieva","year":"2020","journal-title":"ArXiv"}],"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\/10095019.pdf?arnumber=10095019","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T19:04:23Z","timestamp":1700507063000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10095019\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":29,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10095019","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}