{"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/audio-mamba-selective-state-spaces-for-self","title":"Audio Mamba: Selective State Spaces for Self-Supervised Audio Representations","arxiv_id":"2406.02178","date":"2024-06-04","proceeding":null,"authors":["Sarthak Yadav","Zheng-Hua Tan"],"abstract":"Despite its widespread adoption as the prominent neural architecture, the Transformer has spurred several independent lines of work to address its limitations. One such approach is selective state space models, which have demonstrated promising results for language modelling. However, their feasibility for learning self-supervised, general-purpose audio representations is yet to be investigated. This work proposes Audio Mamba, a selective state space model for learning general-purpose audio representations from randomly masked spectrogram patches through self-supervision. Empirical results on ten diverse audio recognition downstream tasks show that the proposed models, pretrained on the AudioSet dataset, consistently outperform comparable self-supervised audio spectrogram transformer (SSAST) baselines by a considerable margin and demonstrate better performance in dataset size, sequence length and model size comparisons.","url_abs":"https://arxiv.org/abs/2406.02178v2","url_pdf":"https://arxiv.org/pdf/2406.02178v2.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":[{"paper_slug":"audio-mamba-selective-state-spaces-for-self","repo_url":"https://github.com/SarthakYadav/audio-mamba-official","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"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":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2406.02178","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.02178"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/SarthakYadav/audio-mamba-official","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran_honours":1,"ran":5,"unverified":1},"by_repo_kind":{"official":{"samples":7,"ran":6,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"bd3578806ecf5ac2","entry":"adjust_learning_rate","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"src/lr_sched.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/src/lr_sched.py","link_basis":"harvester_set","language":"python","status":"ran_honours","verification_level":1,"contract_check":"HONOURS","metamorphic_tier":"well_formed","behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"bd3578806ecf5ac2"}},{"code_sha256_prefix":"3dc19396537db789","entry":"all_reduce_mean","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"src/misc.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/src/misc.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"3dc19396537db789"}},{"code_sha256_prefix":"59d7db08da442a55","entry":"get_info","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"stats_aggregation.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/stats_aggregation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"59d7db08da442a55"}},{"code_sha256_prefix":"baa71eb9105f2237","entry":"get_stats","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"stats_aggregation.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/stats_aggregation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"baa71eb9105f2237"}},{"code_sha256_prefix":"939965089bf8ebbc","entry":"mae_loss","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"src/loss.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/src/loss.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"939965089bf8ebbc"}},{"code_sha256_prefix":"4eddf0f5b7f45b95","entry":"parse","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"stats_aggregation.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/stats_aggregation.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"4eddf0f5b7f45b95"}},{"code_sha256_prefix":"ba1356e8ceb654d2","entry":"get_grad_norm_","repo":"SarthakYadav/audio-mamba-official","repo_kind":"official","path":"src/misc.py","file_url":"https://github.com/SarthakYadav/audio-mamba-official/blob/HEAD/src/misc.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"ba1356e8ceb654d2"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}