{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T19:13:50Z","timestamp":1776885230271,"version":"3.51.2"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T00:00:00Z","timestamp":1693785600000},"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":[[2023,9,4]]},"DOI":"10.23919\/eusipco58844.2023.10289815","type":"proceedings-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T17:55:44Z","timestamp":1698861344000},"page":"451-455","source":"Crossref","is-referenced-by-count":5,"title":["Low-Complexity Audio Embedding Extractors"],"prefix":"10.23919","author":[{"given":"Florian","family":"Schmid","sequence":"first","affiliation":[{"name":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Khaled","family":"Koutini","sequence":"additional","affiliation":[{"name":"Johannes Kepler University,LIT Artificial Intelligence Lab,Linz,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gerhard","family":"Widmer","sequence":"additional","affiliation":[{"name":"Institute of Computational Perception, Johannes Kepler University,Linz,Austria"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref35","article-title":"CMKD: cnn\/transformer-based cross-model knowledge distillation for audio classification","author":"gong","year":"2022","journal-title":"CoRR"},{"key":"ref12","article-title":"An image is worth 16&#x00D7;16 words: Trans-formers for image recognition at scale","author":"dosovitskiy","year":"0","journal-title":"9th International Conference on Learning Representations ICLR"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-227"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO55093.2022.9909674"},{"key":"ref14","article-title":"AST: audio spectrogram trans-former","author":"gong","year":"0","journal-title":"Interspeech 22nd Annual Conference of the International Speech Communication Association"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref31","article-title":"Mo-bilenetv2: Inverted residuals and linear bottlenecks","author":"sandler","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition CVPR"},{"key":"ref30","article-title":"Mobilenets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref11","article-title":"Samplernn: An unconditional end-to-end neural audio generation model","author":"mehri","year":"0","journal-title":"5th International Conference on Learning Representations ICLR"},{"key":"ref33","article-title":"Efficientnetv2: Smaller models and faster training","author":"tan","year":"0","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref10","article-title":"Wavenet: A generative model for raw audio","author":"van den oord","year":"0","journal-title":"The 9th ISCA Speech Synthesis Workshop"},{"key":"ref32","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"0","journal-title":"Proceedings of the ICML International Conference on Machine Learning"},{"key":"ref2","article-title":"Audio feature extraction and analysis for scene segmentation and classification","author":"liu","year":"1998","journal-title":"J VLSI Signal Process"},{"key":"ref1","article-title":"HEAR: holistic evaluation of audio representations","author":"turian","year":"0","journal-title":"NeurIPS 2021 Competitions and Demonstrations Track"},{"key":"ref17","article-title":"Masked spectrogram prediction for self-supervised audio pre-training","author":"chong","year":"2022","journal-title":"CoRR"},{"key":"ref39","article-title":"BYOL-S: learning self-supervised speech representations by bootstrapping","author":"elbanna","year":"0","journal-title":"Heart"},{"key":"ref16","article-title":"Masked spectrogram modeling using masked autoencoders for learning general-purpose audio representation","author":"niizumi","year":"2022","journal-title":"CoRR"},{"key":"ref38","article-title":"Learning general audio representations with large-scale training of patchout audio transformers","author":"koutini","year":"0","journal-title":"Heart"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-10961"},{"key":"ref24","article-title":"Contrastive learning of general-purpose audio representations","author":"saeed","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref26","article-title":"Self-supervised audio representation learning for mobile devices","author":"tagliasacchi","year":"2019","journal-title":"CoRR"},{"key":"ref25","article-title":"Towards learning universal audio representations","author":"wang","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref20","article-title":"Audio set: An ontology and human-labeled dataset for audio events","author":"gemmeke","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref22","article-title":"Masked autoencoders that listen","author":"huang","year":"0","journal-title":"Annual Conference on Neural Information Processing Systems NeurIPS"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref27","article-title":"Efficient end-to-end audio embeddings generation for audio classification on target applications","author":"lopez-meyer","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref29","article-title":"Efficient large-scale audio tagging via transformer-to-cnn knowledge distillation","author":"schmid","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN52387.2021.9534474"},{"key":"ref7","article-title":"Representation learning with contrastive predictive coding","author":"van den oord","year":"2018","journal-title":"CoRR"},{"key":"ref9","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"0","journal-title":"Annual Conference on Neural Information Processing Systems NeurIPS"},{"key":"ref4","article-title":"Mel frequency cepstral coefficients for music modeling","author":"logan","year":"0","journal-title":"ISMIR 1st International Symposium on Music Information Retrieval"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref6","article-title":"Look, listen, and learn more: Design choices for deep audio embeddings","author":"cramer","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"},{"key":"ref5","article-title":"CNN architectures for large-scale audio classification","author":"hershey","year":"0","journal-title":"IEEE International Conference on Acoustics Speech and Signal Processing ICASSP"}],"event":{"name":"2023 31st European Signal Processing Conference (EUSIPCO)","location":"Helsinki, Finland","start":{"date-parts":[[2023,9,4]]},"end":{"date-parts":[[2023,9,8]]}},"container-title":["2023 31st European Signal Processing Conference (EUSIPCO)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10289698\/10289713\/10289815.pdf?arnumber=10289815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,27]],"date-time":"2023-11-27T19:20:47Z","timestamp":1701112847000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10289815\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,4]]},"references-count":39,"URL":"https:\/\/doi.org\/10.23919\/eusipco58844.2023.10289815","relation":{},"subject":[],"published":{"date-parts":[[2023,9,4]]}}}