{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T21:32:16Z","timestamp":1781127136324,"version":"3.54.1"},"reference-count":40,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,4,14]],"date-time":"2024-04-14T00:00:00Z","timestamp":1713052800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100002465","name":"Delta","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100002465","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,4,14]]},"DOI":"10.1109\/icassp48485.2024.10447215","type":"proceedings-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T18:56:31Z","timestamp":1710788191000},"page":"316-320","source":"Crossref","is-referenced-by-count":15,"title":["Improving Audio Captioning Models with Fine-Grained Audio Features, Text Embedding Supervision, and LLM Mix-Up Augmentation"],"prefix":"10.1109","author":[{"given":"Shih-Lun","family":"Wu","sequence":"first","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuankai","family":"Chang","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gordon","family":"Wichern","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jee-Weon","family":"Jung","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fran\u00e7ois","family":"Germain","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Labs (MERL),Cambridge,MA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shinji","family":"Watanabe","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University,Language Technologies Institute,Pittsburgh,PA,USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2017.8170058"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref3","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref4","article-title":"The DCASE 2021 challenge task 6 system: Automated audio captioning with weakly supervised pre-training and word selection methods","volume-title":"Tech. Rep., DCASE Challenge","author":"Yuan","year":"2021"},{"key":"ref5","article-title":"The SJTU system for DCASE2022 challenge task 6: Audio captioning with audiotext retrieval pre-training","volume-title":"Tech. Rep., DCASE Challenge","author":"Xu","year":"2022"},{"key":"ref6","article-title":"Automated audio captioning with multi-task learning","volume-title":"Tech. Rep., DCASE Challenge","author":"Ye","year":"2022"},{"key":"ref7","article-title":"HYU submission for the DCASE 2023 task 6a: Automated audio captioning model using AL-MixGen and synonyms substitution","volume-title":"Tech. Rep., DCASE Challenge","author":"Cho","year":"2023"},{"key":"ref8","article-title":"IRIT-UPS DCASE 2023 audio captioning and retrieval system","volume-title":"Tech. Rep., DCASE Challenge","author":"Labb\u00e9","year":"2023"},{"key":"ref9","article-title":"Leveraging state-of-the-art ASR techniques to audio captioning","volume-title":"Proc. DCASE","author":"Narisetty"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref12","article-title":"Masked autoencoders that listen","volume-title":"Proc. NeurIPS","author":"Huang"},{"key":"ref13","article-title":"BEATs: Audio pre-training with acoustic tokenizers","author":"Chen","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref15","article-title":"Training language models to follow instructions with human feedback","volume-title":"Proc. NeurIPS","author":"Ouyang"},{"key":"ref16","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.71"},{"key":"ref18","article-title":"Introducing ChatGPT","author":"Schulman","year":"2022","journal-title":"OpenAI Blog"},{"key":"ref19","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2020-3015"},{"key":"ref21","article-title":"Convolution-augmented transformer for semi-supervised sound event detection","volume-title":"Proc. DCASE","author":"Miyazaki"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. ICLR","author":"Zhang"},{"key":"ref24","article-title":"Efficient audio captioning transformer with patchout and text guidance","volume-title":"Tech. Rep., DCASE Challenge","author":"Kouzelis","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3419446"},{"key":"ref26","article-title":"The curious case of neural text degeneration","volume-title":"Proc. ICLR","author":"Holtzman"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref28","article-title":"BERT: Pre-training of deep bidirectional Transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref29","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref35","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref36","article-title":"An encoder-decoder based audio captioning system with transfer and reinforcement learning","volume-title":"Proc. DCASE","author":"Mei"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref38","article-title":"ImageBind: holistic AI learning across six modalities","author":"Schulman","year":"2023","journal-title":"Meta AI Blog"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.wnut-1.39"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"}],"event":{"name":"ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Seoul, Korea, Republic of","start":{"date-parts":[[2024,4,14]]},"end":{"date-parts":[[2024,4,19]]}},"container-title":["ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10445798\/10445803\/10447215.pdf?arnumber=10447215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,2]],"date-time":"2024-08-02T04:53:40Z","timestamp":1722574420000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10447215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,14]]},"references-count":40,"URL":"https:\/\/doi.org\/10.1109\/icassp48485.2024.10447215","relation":{},"subject":[],"published":{"date-parts":[[2024,4,14]]}}}