{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/multiscale-audio-spectrogram-transformer-for","title":"Multiscale Audio Spectrogram Transformer for Efficient Audio Classification","arxiv_id":"2303.10757","date":"2023-03-19","proceeding":null,"authors":["Wentao Zhu","Mohamed Omar"],"abstract":"Audio event has a hierarchical architecture in both time and frequency and can be grouped together to construct more abstract semantic audio classes. In this work, we develop a multiscale audio spectrogram Transformer (MAST) that employs hierarchical representation learning for efficient audio classification. Specifically, MAST employs one-dimensional (and two-dimensional) pooling operators along the time (and frequency domains) in different stages, and progressively reduces the number of tokens and increases the feature dimensions. MAST significantly outperforms AST~\\cite{gong2021ast} by 22.2\\%, 4.4\\% and 4.7\\% on Kinetics-Sounds, Epic-Kitchens-100 and VGGSound in terms of the top-1 accuracy without external training data. On the downloaded AudioSet dataset, which has over 20\\% missing audios, MAST also achieves slightly better accuracy than AST. In addition, MAST is 5x more efficient in terms of multiply-accumulates (MACs) with 42\\% reduction in the number of parameters compared to AST. Through clustering metrics and visualizations, we demonstrate that the proposed MAST can learn semantically more separable feature representations from audio signals.","url_abs":"https://arxiv.org/abs/2303.10757v1","url_pdf":"https://arxiv.org/pdf/2303.10757v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"}],"methods":[{"method_slug":"absolute-position-encodings","method_name":"Absolute Position Encodings"},{"method_slug":"adam","method_name":"Adam"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"bpe","method_name":"BPE"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"method_slug":"label-smoothing","method_name":"Label Smoothing"},{"method_slug":"layer-normalization","method_name":"Layer Normalization"},{"method_slug":"linear-layer","method_name":"Linear Layer"},{"method_slug":"multi-head-attention","method_name":"Multi-Head Attention"},{"method_slug":"position-wise-feed-forward-layer","method_name":"Position-Wise Feed-Forward Layer"},{"method_slug":"residual-connection","method_name":"Residual Connection"},{"method_slug":"softmax","method_name":"Softmax"},{"method_slug":"transformer","method_name":"Transformer"}],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/audio-classification-on-vggsound","task":"Audio Classification","dataset":"VGGSound","model":"MAST (Audio Only)","rank_in_archive_order":15,"of":23,"metrics":{"Top 1 Accuracy":"57.0","Top 5 Accuracy":"81.3"},"uses_additional_data":false}],"syntology":{"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}