{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:27:10Z","timestamp":1776889630288,"version":"3.51.2"},"reference-count":35,"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\/icassp49357.2023.10094993","type":"proceedings-article","created":{"date-parts":[[2023,5,5]],"date-time":"2023-05-05T13:28:30Z","timestamp":1683293310000},"page":"1-5","source":"Crossref","is-referenced-by-count":8,"title":["Leveraging Large Text Corpora For End-To-End Speech Summarization"],"prefix":"10.1109","author":[{"given":"Kohei","family":"Matsuura","sequence":"first","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takanori","family":"Ashihara","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takafumi","family":"Moriya","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tomohiro","family":"Tanaka","sequence":"additional","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":"Ryo","family":"Masumura","sequence":"additional","affiliation":[{"name":"NTT Corporation,Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688218"},{"key":"ref35","article-title":"BERTScore: Evaluating text generation with BERT","author":"zhang","year":"2021","journal-title":"Proc of ICLR"},{"key":"ref12","article-title":"Leveraging sequence-to-sequence speech synthesis for enhancing acoustic-to-word speech recognition","author":"mimura","year":"2021","journal-title":"Proc of SLT"},{"key":"ref34","article-title":"Meteor universal: Language specific translation evaluation for any target language","author":"denkowski","year":"2021","journal-title":"Proc of EACL WMT"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1250\/ast.42.333"},{"key":"ref14","article-title":"Back-translation-style data augmentation for end-to-end ASR","author":"hayashi","year":"2021","journal-title":"Proc of SLT"},{"key":"ref31","article-title":"Conditional variational autoencoder with adversarial learning for end-to-end text-to-speech","author":"kim","year":"2021","journal-title":"Proc of ICML"},{"key":"ref30","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2021","journal-title":"Proc of ICLR"},{"key":"ref11","article-title":"End-to-end speech summarization using restricted self-attention","author":"sharma","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref33","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Text Summarization Branches Out"},{"key":"ref10","article-title":"A hierarchical neural summarization framework for spoken documents","author":"liu","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref32","article-title":"Speech database development: Design and analysis of the acoustic-phonetic corpus","author":"lamel","year":"2021","journal-title":"Proc of the DARPA CSR"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s00799-004-0101-0"},{"key":"ref1","article-title":"A comparative study on Trans-former vs RNN in speech applications","author":"karita","year":"2021","journal-title":"Proc of ASRU"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1930"},{"key":"ref16","article-title":"Multi-modal data augmentation for end-to-end ASR","author":"renduchintala","year":"2021","journal-title":"Proc of Interspeech"},{"key":"ref19","article-title":"English Giga-word","author":"graff","year":"2003","journal-title":"Linguistic Data Consortium Philadelphia"},{"key":"ref18","article-title":"Leveraging weakly supervised data to improve end-to-end speech-to-text translation","author":"jia","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref24","article-title":"Improving speech recognition using consistent predictions on synthesized speech","author":"wang","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref23","article-title":"End-to-end feedback loss in speech chain framework via straight-through estimator","author":"tjandra","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref26","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc of NIPS"},{"key":"ref25","article-title":"Conformer: Convolution-augmented Transformer for speech recognition","author":"gulati","year":"2021","journal-title":"Proc of Interspeech"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref22","article-title":"Natural TTS synthesis by conditioning wavenet on mel spectrogram predictions","author":"shen","year":"2021","journal-title":"Proc of ICASSP"},{"key":"ref21","article-title":"How2: A large-scale dataset for multimodal language understanding","author":"sanabria","year":"2021","journal-title":"Proc of NeurIPS Work-shop on ViGIL"},{"key":"ref28","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation,translation,and comprehension","author":"lewis","year":"2021","journal-title":"Proc of ACL"},{"key":"ref27","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2021","journal-title":"Proc of ICML"},{"key":"ref29","article-title":"Teaching machines to read and comprehend","author":"hermann","year":"2021","journal-title":"Proc of NIPS"},{"key":"ref8","article-title":"Assessing the semantic space bias caused by ASR error propagation and its effect on spoken document summarization","author":"t\u00fcndik","year":"2021","journal-title":"Proc of Inter-speech"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.472"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9687977"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1088\/1757-899X\/1131\/1\/012001"},{"key":"ref3","article-title":"Generating and validating abstracts of meeting conversations: a user study","author":"murray","year":"2021","journal-title":"Proc of INLG"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.377"},{"key":"ref5","article-title":"An automated medical scribe for documenting clinical encounters","author":"finley","year":"2021","journal-title":"Proc of NAACL"}],"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\/10094993.pdf?arnumber=10094993","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,20]],"date-time":"2023-11-20T14:05:25Z","timestamp":1700489125000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10094993\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,4]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49357.2023.10094993","relation":{},"subject":[],"published":{"date-parts":[[2023,6,4]]}}}