{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T00:58:24Z","timestamp":1779929904052,"version":"3.53.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,5,23]],"date-time":"2022-05-23T00:00:00Z","timestamp":1653264000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,5,23]]},"DOI":"10.1109\/icassp43922.2022.9747742","type":"proceedings-article","created":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T19:50:34Z","timestamp":1651089034000},"page":"3713-3717","source":"Crossref","is-referenced-by-count":5,"title":["Study of Positional Encoding Approaches for Audio Spectrogram Transformers"],"prefix":"10.1109","author":[{"given":"Leonardo","family":"Pepino","sequence":"first","affiliation":[{"name":"CONICET-UBA,Instituto de Investigación en Ciencias de la Computación (ICC),Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Riera","sequence":"additional","affiliation":[{"name":"CONICET-UBA,Instituto de Investigación en Ciencias de la Computación (ICC),Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luciana","family":"Ferrer","sequence":"additional","affiliation":[{"name":"CONICET-UBA,Instituto de Investigación en Ciencias de la Computación (ICC),Argentina"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2018.8489641"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref11","article-title":"Audio transformers: Transformer architectures for large scale audio understanding. adieu convolutions","author":"verma","year":"2021"},{"key":"ref12","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021"},{"key":"ref13","article-title":"Roformer: Enhanced transformer with rotary position embedding","author":"su","year":"2021"},{"key":"ref14","article-title":"Selfattention with relative position representations","author":"shaw","year":"2018","journal-title":"NAACL"},{"key":"ref15","article-title":"Music transformer","author":"huang","year":"2019","journal-title":"ICLRE"},{"key":"ref16","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","author":"press","year":"2021"},{"key":"ref17","article-title":"Convit: Improving vision transformers with soft convolutional inductive biases","author":"d\u2019ascoli","year":"2021"},{"key":"ref18","author":"mitchell","year":"1980","journal-title":"The need for biases in learning generalizations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1613\/jair.731"},{"key":"ref28","article-title":"Urban sound tagging using multi-channel audio feature with convolutional neural networks","author":"kim","year":"2020","journal-title":"Proceedings of the Detection and Classification of Acoustic Scenes and Events"},{"key":"ref4","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"Proceedings of the 38th International Conference on Machine Learning"},{"key":"ref27","article-title":"A sequential self teaching approach for improving generalization in sound event recognition","author":"kumar","year":"2020","journal-title":"ICML"},{"key":"ref3","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021"},{"key":"ref6","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"baevski","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref29","article-title":"Learning from between-class examples for deep sound recognition","author":"tokozume","year":"2018","journal-title":"ICLRE"},{"key":"ref5","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3015"},{"key":"ref7","article-title":"A framework for generative and contrastive learning of audio representations","author":"verma","year":"2020"},{"key":"ref2","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054476"},{"key":"ref1","article-title":"BERT: pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2019","journal-title":"NAACL-HLT"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref22","article-title":"Speech Commands: A Dataset for Limited-Vocabulary Speech Recognition","author":"warden","year":"0"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0275-4"},{"key":"ref26","article-title":"Averaging weights leads to wider optima and better generalization","author":"izmailov","year":"2018","journal-title":"Conference on Uncertainty in Artificial Intelligence"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3120633"}],"event":{"name":"ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Singapore, Singapore","start":{"date-parts":[[2022,5,23]]},"end":{"date-parts":[[2022,5,27]]}},"container-title":["ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9745891\/9746004\/09747742.pdf?arnumber=9747742","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,8,22]],"date-time":"2022-08-22T20:10:39Z","timestamp":1661199039000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9747742\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,23]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icassp43922.2022.9747742","relation":{},"subject":[],"published":{"date-parts":[[2022,5,23]]}}}