{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:33:20Z","timestamp":1776890000552,"version":"3.51.2"},"reference-count":154,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T00:00:00Z","timestamp":1743465600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001659","name":"Deutsche Forschungsgemeinschaft (DFG) Reinhart Koselleck Project","doi-asserted-by":"publisher","award":["442218748 (AUDI0NOMOUS)"],"award-info":[{"award-number":["442218748 (AUDI0NOMOUS)"]}],"id":[{"id":"10.13039\/501100001659","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2025,4]]},"DOI":"10.1109\/jproc.2025.3593952","type":"journal-article","created":{"date-parts":[[2025,8,13]],"date-time":"2025-08-13T17:34:56Z","timestamp":1755106496000},"page":"317-343","source":"Crossref","is-referenced-by-count":5,"title":["Computer Audition: From Task-Specific Machine Learning to Foundation Models"],"prefix":"10.1109","volume":"113","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8338-617X","authenticated-orcid":false,"given":"Andreas","family":"Triantafyllopoulos","sequence":"first","affiliation":[{"name":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9614-5894","authenticated-orcid":false,"given":"Iosif","family":"Tsangko","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4169-5403","authenticated-orcid":false,"given":"Alexander","family":"Gebhard","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6640-9752","authenticated-orcid":false,"given":"Annamaria","family":"Mesaros","sequence":"additional","affiliation":[{"name":"Audio Research Group, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4604-9729","authenticated-orcid":false,"given":"Tuomas","family":"Virtanen","sequence":"additional","affiliation":[{"name":"Audio Research Group, Tampere University, Tampere, Finland"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"Chair of Health Informatics (CHI), TUM University Hospital, Munich, Germany"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1006\/csla.1994.1016"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/EUSIPCO.2016.7760424"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.33682\/m76f-d618"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10447868"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.33682\/kfmf-zv94"},{"key":"ref6","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref7","article-title":"Sparks of large audio models: A survey and outlook","author":"Latif","year":"2023","journal-title":"arXiv:2308.12792"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/NNICE64954.2025.11063722"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.807"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1093\/nsr\/nwae403"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100616"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3506283"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/9780470043387"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2326181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2021.3090678"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1017\/9781139051699"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414579"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.33682\/006b-jx26"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683158"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref23","first-page":"9","article-title":"A multi-device dataset for urban acoustic scene classification","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop (DCASE)","author":"Mesaros"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9415085"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.23919\/APSIPAASC55919.2022.9979822"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/IWAENC.2018.8521242"},{"key":"ref27","article-title":"Hierarchical learning for DNN-based acoustic scene classification","author":"Xu","year":"2016","journal-title":"arXiv:1607.03682"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682341"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/23312165211046135"},{"key":"ref30","first-page":"186","article-title":"Description and discussion on DCASE 2021 challenge task 2: Unsupervised anomalous sound detection for machine condition monitoring under domain shifted conditions","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop (DCASE)","author":"Kawaguchi"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806254"},{"key":"ref32","article-title":"On the influence of cultural differences on the perception of audio coding artifacts in music","author":"Dick","year":"2018","journal-title":"J. Audio Eng. Soc."},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-63450-0_3"},{"key":"ref34","first-page":"965","article-title":"Acoustical sound database in real environments for sound scene understanding and hands-free speech recognition","volume-title":"Proc. Int. Conf.Lang. Resource Eval.","author":"Nakamura"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096198"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052990"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3010650"},{"key":"ref38","article-title":"Language-based audio retrieval task in DCASE 2022 challenge","author":"Xie","year":"2022","journal-title":"arXiv:2206.06108"},{"key":"ref39","first-page":"119","article-title":"AudioCaps: Generating captions for audios in the wild","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","author":"Kim"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3419446"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909680"},{"key":"ref42","article-title":"Listen, think, and understand","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Gong"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1121\/10.0011809"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.2990485"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2018.2885636"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA52581.2021.9632778"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3382504"},{"key":"ref48","article-title":"STARSS23: An audio-visual dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Shimada"},{"key":"ref49","first-page":"165","article-title":"A dataset of reverberant spatial sound scenes with moving sources for sound event localization and detection","volume-title":"Proc. Detection Classification Acoustic Scenes Events Workshop (DCASE)","author":"Politis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746544"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461310"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09905-3"},{"key":"ref53","first-page":"37524","article-title":"A closer look at weakly-supervised audio-visual source localization","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mo"},{"key":"ref54","first-page":"4733","article-title":"Learning representations from audio-visual spatial alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Morgado"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.23919\/FUSION45008.2020.9190480"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-698"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2928625"},{"key":"ref60","article-title":"LEAF: A learnable frontend for audio classification","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Zeghidour"},{"key":"ref61","first-page":"13873","article-title":"Learning the spectrogram temporal resolution for audio classification","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Liu"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref63","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Simonyan"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref65","first-page":"512","article-title":"What is being transferred in transfer learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Neyshabur"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414896"},{"key":"ref67","first-page":"5178","article-title":"BEATs: Audio pre-training with acoustic tokenizers","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Chen"},{"key":"ref68","first-page":"145","article-title":"Few-shot bioacoustic event detection: A new task at the DCASE 2021 challenge","volume-title":"Proc. DCASE","author":"Morfi"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.7717\/peerj.13152"},{"key":"ref70","article-title":"Prototypical networks for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Snell"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1142\/9789812797926_0003"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO63174.2024.10714948"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3065234"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909701"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095889"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10445807"},{"key":"ref77","first-page":"12449","article-title":"Wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst. (NIPS)","author":"Baevski"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3263585"},{"key":"ref79","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-2193"},{"key":"ref81","article-title":"High fidelity neural audio compression","author":"D\u00e9fossez","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2024.3506286"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref85","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-main.64"},{"key":"ref87","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"issue":"8","key":"ref88","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3221007"},{"key":"ref90","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Vaswani"},{"key":"ref91","first-page":"28708","article-title":"Masked autoencoders that listen","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Huang"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/83.480761"},{"key":"ref94","article-title":"RULER: What\u2019s the real context size of your long-context language models?","volume-title":"Proc. 1st Conf. Lang. Model.","author":"Hsieh"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref96","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"},{"key":"ref97","article-title":"The evolution of multimodal model architectures","author":"Wadekar","year":"2024","journal-title":"arXiv:2405.17927"},{"key":"ref98","article-title":"BAT: Learning to reason about spatial sounds with large language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Zheng"},{"issue":"70","key":"ref99","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.754"},{"key":"ref101","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Hu"},{"key":"ref102","first-page":"10088","article-title":"QLoRA: Efficient finetuning of quantized LLMs","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dettmers"},{"key":"ref103","first-page":"9459","article-title":"Retrieval-augmented generation for knowledge-intensive NLP tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Lewis"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448030"},{"key":"ref105","first-page":"133","article-title":"Weight averaging for neural networks and local resampling schemes","volume-title":"Proc. Workshop Integrating Multiple Learned Models","author":"Utans"},{"key":"ref106","article-title":"The role of permutation invariance in linear mode connectivity of neural networks","author":"Entezari","year":"2021","journal-title":"arXiv:2110.06296"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.emnlp-industry.36"},{"key":"ref108","first-page":"23965","article-title":"Model soups: Averaging weights of multiple fine-tuned models improves accuracy without increasing inference time","volume-title":"Proc. 39th Int. Conf. Mach. Learn.","author":"Wortsman"},{"key":"ref109","first-page":"15300","article-title":"Optimizing mode connectivity via neuron alignment","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tatro"},{"key":"ref110","article-title":"LLM augmented LLMs: Expanding capabilities through composition","author":"Bansal","year":"2024","journal-title":"arXiv:2401.02412"},{"key":"ref111","first-page":"18090","article-title":"Pengi: An audio language model for audio tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Deshmukh"},{"key":"ref112","article-title":"Acoustic prompt tuning: Empowering large language models with audition capabilities","author":"Liang","year":"2023","journal-title":"arXiv:2312.00249"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU57964.2023.10389742"},{"key":"ref114","article-title":"Qwen-audio: Advancing universal audio understanding via unified large-scale audio-language models","author":"Chu","year":"2023","journal-title":"arXiv:2311.07919"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.855"},{"key":"ref116","article-title":"Audio flamingo: A novel audio language model with few-shot learning and dialogue abilities","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Kong"},{"key":"ref117","article-title":"UniAudio: An audio foundation model toward universal audio generation","author":"Yang","year":"2023","journal-title":"arXiv:2310.00704"},{"key":"ref118","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv:2403.05530"},{"key":"ref119","article-title":"LauraGPT: Listen, attend, understand, and regenerate audio with GPT","author":"Du","year":"2023","journal-title":"arXiv:2310.04673"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3006378"},{"key":"ref121","first-page":"486","article-title":"Freesound datasets: A platform for the creation of open audio datasets","volume-title":"Proc. Int. Soc. Music Inf. Retr. Conf. (ISMIR)","author":"Fonseca"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-1136"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149712"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO54536.2021.9616087"},{"key":"ref125","first-page":"8896","article-title":"SoundSpaces 2.0: A simulation platform for visual-acoustic learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Chen"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1049\/sil2.12233"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1109\/WASPAA.2015.7336899"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.33682\/j5zw-2t88"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3287560.3287596"},{"key":"ref131","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref132","article-title":"Efficient streaming language models with attention sinks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Xiao"},{"key":"ref133","first-page":"125","article-title":"HEAR: Holistic evaluation of audio representations","volume-title":"Proc. NeurIPS Competitions Demonstrations Track","author":"Turian"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2021-1775"},{"key":"ref135","article-title":"Audiobox: Unified audio generation with natural language prompts","author":"Vyas","year":"2023","journal-title":"arXiv:2312.15821"},{"key":"ref136","first-page":"462","article-title":"Generating training data with language models: Towards zero-shot language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yu"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-024-07566-y"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1145\/3462244.3479879"},{"key":"ref139","article-title":"Listenable maps for zero-shot audio classifiers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Paissan"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00026"},{"key":"ref141","first-page":"17703","article-title":"Merging models with Fisher-weighted averaging","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Matena"},{"key":"ref142","article-title":"Merging vision transformers from different tasks and domains","author":"Ye","year":"2023","journal-title":"arXiv:2312.16240"},{"key":"ref143","article-title":"EMR-merging: Tuning-free high-performance model merging","author":"Huang","year":"2024","journal-title":"arXiv:2405.17461"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1002\/9781119230724"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2023.e23142"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4614-7397-8_23"},{"key":"ref147","article-title":"Expressivity and speech synthesis","author":"Triantafyllopoulos","year":"2024","journal-title":"arXiv:2404.19363"},{"key":"ref148","article-title":"The Llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref149","article-title":"Data-efficient low-complexity acoustic scene classification in the DCASE 2024 challenge","author":"Schmid","year":"2024","journal-title":"arXiv:2405.10018"},{"key":"ref150","first-page":"795","article-title":"Sustainable AI: Environmental implications, challenges and opportunities","volume-title":"Proc. Mach. Learn. Syst.","author":"Wu"},{"key":"ref151","first-page":"129","article-title":"What is the state of neural network pruning","volume-title":"Proc. Mach. Learn. Syst.","volume":"2","author":"Blalock"},{"key":"ref152","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1145\/3698767"},{"key":"ref154","article-title":"DDSP: Differentiable digital signal processing","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Engel"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5\/11156163\/11124350.pdf?arnumber=11124350","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,16]],"date-time":"2025-09-16T17:34:29Z","timestamp":1758044069000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11124350\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4]]},"references-count":154,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2025.3593952","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4]]}}}