{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T15:27:16Z","timestamp":1784215636956,"version":"3.55.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3611348","type":"journal-article","created":{"date-parts":[[2025,9,17]],"date-time":"2025-09-17T17:32:08Z","timestamp":1758130328000},"page":"163313-163330","source":"Crossref","is-referenced-by-count":8,"title":["M2D-CLAP: Exploring General-Purpose Audio-Language Representations Beyond CLAP"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5063-0508","authenticated-orcid":false,"given":"Daisuke","family":"Niizumi","sequence":"first","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daiki","family":"Takeuchi","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2776-9701","authenticated-orcid":false,"given":"Masahiro","family":"Yasuda","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3883-1315","authenticated-orcid":false,"given":"Binh","family":"Thien Nguyen","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7856-248X","authenticated-orcid":false,"given":"Yasunori","family":"Ohishi","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1759-4533","authenticated-orcid":false,"given":"Noboru","family":"Harada","sequence":"additional","affiliation":[{"name":"Communication Science Laboratories, NTT, Inc., Atsugi, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. ICML","author":"Radford"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747631"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747669"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448504"},{"key":"ref7","doi-asserted-by":"crossref","first-page":"3339","DOI":"10.1109\/TASLP.2024.3419446","article-title":"WavCaps: A ChatGPT-assisted weakly-labelled audio captioning dataset for audio-language multimodal research","volume":"32","author":"Mei","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang., Process."},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389692"},{"key":"ref9","first-page":"1","article-title":"CoLLAT: On adding fine-grained audio understanding to language models using token-level locked-language tuning","volume-title":"Proc. NeurIPS","author":"Silva"},{"key":"ref10","doi-asserted-by":"crossref","first-page":"4867","DOI":"10.1109\/TASLP.2024.3485170","article-title":"Cacophony: An improved contrastive audio-text model","volume":"32","author":"Zhu","year":"2024","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang., Process."},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-29"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446672"},{"key":"ref13","article-title":"Zero-shot audio captioning with audio-language model guidance and audio context keywords","author":"Salewski","year":"2023","journal-title":"arXiv:2311.08396"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref15","doi-asserted-by":"crossref","first-page":"137","DOI":"10.1109\/TASLP.2022.3221007","article-title":"BYOL for audio: Exploring pre-trained general-purpose audio representations","volume":"31","author":"Niizumi","year":"2023","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang., Process."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-950"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715076"},{"key":"ref20","article-title":"R&B\u2013rhythm and brain: Cross-subject decoding of musical tracks from human brain activity","volume-title":"Proc. KDD AIDSH","author":"Ferrante"},{"key":"ref21","article-title":"NV-embed: Improved techniques for training LLMs as generalist embedding models","author":"Lee","year":"2024","journal-title":"arXiv:2405.17428"},{"key":"ref22","article-title":"Mistral 7B","author":"Jiang","year":"2023","journal-title":"arXiv:2310.06825"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3389636"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2020.3030497"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746312"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413528"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref30","first-page":"1","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","volume-title":"Proc. NeurIPS Competitions Demonstrations Track","author":"Niizumi"},{"key":"ref31","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. NeurIPS","volume":"35","author":"Huang"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3352248"},{"key":"ref33","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10446348"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681145"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2488"},{"key":"ref39","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref40","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref41","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. NAACL-HLT","author":"Kim"},{"key":"ref42","article-title":"NV-retriever: Improving text embedding models with effective hard-negative mining","author":"Moreira","year":"2024","journal-title":"arXiv:2407.15831"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.eacl-main.148"},{"key":"ref44","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NAACL-HLT","author":"Devlin"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681472"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2024-420"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2021.3133208"},{"key":"ref51","article-title":"Speech commands: A dataset for limited-vocabulary speech recognition","author":"Warden","year":"2018","journal-title":"arXiv:1804.03209"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2014.2336244"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TSA.2002.800560"},{"key":"ref54","first-page":"1068","article-title":"Neural audio synthesis of musical notes with WaveNet autoencoders","volume-title":"Proc. ICML","author":"Engel"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.23919\/DAFx51585.2021.9768246"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10887666"},{"key":"ref57","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. NeurIPS","author":"Deshmukh"},{"key":"ref58","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","volume-title":"Proc. NeurIPS Competitions Demonstrations Track","author":"Turian"},{"key":"ref59","volume-title":"Voxforge","author":"MacLean","year":"2018"},{"key":"ref60","first-page":"39626","article-title":"MARBLE: Music audio representation benchmark for universal evaluation","volume-title":"Proc. NeurIPS","author":"Yuan"},{"key":"ref61","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv:2005.00341"},{"key":"ref62","first-page":"256","article-title":"Supervised and unsupervised learning of audio representations for music understanding","volume-title":"Proc. ISMIR","author":"McCallum"},{"key":"ref63","article-title":"MERT: Acoustic music understanding model with large-scale self-supervised training","volume-title":"Proc. ICLR","author":"Li"},{"key":"ref64","article-title":"Towards general text embeddings with multi-stage contrastive learning","author":"Li","year":"2023","journal-title":"arXiv:2308.03281"},{"key":"ref65","first-page":"387","article-title":"Evaluation of algorithms using games: The case of music tagging","volume-title":"Proc. ISMIR","author":"Law"},{"key":"ref66","article-title":"The MTG-jamendo dataset for automatic music tagging","volume-title":"Proc. ICML","author":"Bogdanov"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/2506364.2506365"},{"key":"ref68","first-page":"468","article-title":"VocalSet: A singing voice dataset","volume-title":"Proc. ISMIR","author":"Wilkins"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_79"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2022-227"},{"key":"ref72","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref73","article-title":"How to fine-tune vision models with SGD","author":"Kumar","year":"2022","journal-title":"arXiv:2211.09359"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29716"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/taslp.2024.3376984"},{"key":"ref76","article-title":"Listen, think, and understand","volume-title":"Proc. ICLR","author":"Gong"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref78","article-title":"GLAP: General contrastive audio-text pretraining across domains and languages","author":"Dinkel","year":"2025","journal-title":"arXiv:2506.11350"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447760"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-982"},{"key":"ref81","first-page":"116","article-title":"A sound description: Exploring prompt templates and class descriptions to enhance zero-shot audio classification","volume-title":"Proc. DCASE","author":"Olvera"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-11115"},{"key":"ref83","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2023","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1525\/9780520940420-020"},{"key":"ref85","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. WMT@ACL","author":"Banerjee"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.100"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746427"},{"key":"ref90","article-title":"Assessing the utility of audio foundation models for heart and respiratory sound analysis","volume-title":"Proc. EMBC","author":"Niizumi"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447265"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10715343"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11168481.pdf?arnumber=11168481","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:35:16Z","timestamp":1759235716000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11168481\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3611348","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}