{"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-bidirectional-state-space-model","title":"Audio Mamba: Bidirectional State Space Model for Audio Representation Learning","arxiv_id":"2406.03344","date":"2024-06-05","proceeding":null,"authors":["Mehmet Hamza Erol","Arda Senocak","Jiu Feng","Joon Son Chung"],"abstract":"Transformers have rapidly become the preferred choice for audio classification, surpassing methods based on CNNs. However, Audio Spectrogram Transformers (ASTs) exhibit quadratic scaling due to self-attention. The removal of this quadratic self-attention cost presents an appealing direction. Recently, state space models (SSMs), such as Mamba, have demonstrated potential in language and vision tasks in this regard. In this study, we explore whether reliance on self-attention is necessary for audio classification tasks. By introducing Audio Mamba (AuM), the first self-attention-free, purely SSM-based model for audio classification, we aim to address this question. We evaluate AuM on various audio datasets - comprising six different benchmarks - where it achieves comparable or better performance compared to well-established AST model.","url_abs":"https://arxiv.org/abs/2406.03344v1","url_pdf":"https://arxiv.org/pdf/2406.03344v1.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-bidirectional-state-space-model","repo_url":"https://github.com/mhamzaerol/audio-mamba-aum","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"tasks":[{"task_slug":"audio-classification","task_name":"Audio Classification"},{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"mamba","task_name":"Mamba"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"state-space-models","task_name":"State Space Models"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2406.03344","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2406.03344"}},"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/mhamzaerol/audio-mamba-aum","reach":{"status":"ok","spdx":"BSD-3-Clause"}}],"summary":{"ran":7,"ran_draft_wrong":1,"unverified":9},"by_repo_kind":{"official":{"samples":17,"ran":8,"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":"0e272bec13ad46b9","entry":"get_start_end_idx","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/epic_sounds/epic_data/audio_loader_epicsounds.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/epic_sounds/epic_data/audio_loader_epicsounds.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0e272bec13ad46b9"}},{"code_sha256_prefix":"c15efdd12442aeb4","entry":"lookup_list","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"c15efdd12442aeb4"}},{"code_sha256_prefix":"a8fb3f62e2a901d7","entry":"make_index_dict","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8fb3f62e2a901d7"}},{"code_sha256_prefix":"cbf115a314bcd23e","entry":"make_name_dict","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/dataloader.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/dataloader.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"cbf115a314bcd23e"}},{"code_sha256_prefix":"0e11bb8b11afc5b8","entry":"sample","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/utils/generation.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/utils/generation.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"0e11bb8b11afc5b8"}},{"code_sha256_prefix":"ba7b868fec181b57","entry":"selective_scan_ref","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/ops/selective_scan_interface.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/ops/selective_scan_interface.py","link_basis":"harvester_set","language":"python","status":"ran_draft_wrong","verification_level":1,"contract_check":"MISDECLARED","metamorphic_tier":"invariant","behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ba7b868fec181b57"}},{"code_sha256_prefix":"75d36c81e5267e3f","entry":"temporal_sampling","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/epic_sounds/epic_data/audio_loader_epicsounds.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/epic_sounds/epic_data/audio_loader_epicsounds.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"75d36c81e5267e3f"}},{"code_sha256_prefix":"ecb5ae1f3a358b96","entry":"validate_ensemble","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/traintest.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ecb5ae1f3a358b96"}},{"code_sha256_prefix":"feab015e66e37666","entry":"decode","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/utils/generation.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/utils/generation.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"feab015e66e37666"}},{"code_sha256_prefix":"2ce8fcf5bedd19ec","entry":"layer_norm_ref","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/ops/triton/layernorm.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/ops/triton/layernorm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"2ce8fcf5bedd19ec"}},{"code_sha256_prefix":"7a8ab4bf37f8fa41","entry":"load_config_hf","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/utils/hf.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/utils/hf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"7a8ab4bf37f8fa41"}},{"code_sha256_prefix":"70607b36f7d19351","entry":"load_state_dict_hf","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/utils/hf.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/utils/hf.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"70607b36f7d19351"}},{"code_sha256_prefix":"da95e9a7906f3d52","entry":"modify_logit_for_repetition_penalty","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/utils/generation.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/utils/generation.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"da95e9a7906f3d52"}},{"code_sha256_prefix":"a8482f7a57988c22","entry":"pack_audio","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/epic_sounds/epic_data/audio_loader_epicsounds.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/epic_sounds/epic_data/audio_loader_epicsounds.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"a8482f7a57988c22"}},{"code_sha256_prefix":"ab802ae3195c6316","entry":"rms_norm_ref","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"vim-mamba_ssm/mamba_ssm/ops/triton/layernorm.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/vim-mamba_ssm/mamba_ssm/ops/triton/layernorm.py","link_basis":"harvester_set","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ab802ae3195c6316"}},{"code_sha256_prefix":"ff5d747f7c356f30","entry":"train","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/traintest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"ff5d747f7c356f30"}},{"code_sha256_prefix":"aa052f9fd3245715","entry":"validate_acc","repo":"mhamzaerol/audio-mamba-aum","repo_kind":"official","path":"src/traintest.py","file_url":"https://github.com/mhamzaerol/audio-mamba-aum/blob/HEAD/src/traintest.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"BSD-3-Clause","inline_ok":true,"mcp_get_code":{"code_sha256":"aa052f9fd3245715"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}