{"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/eh-mam-easy-to-hard-masked-acoustic-modeling","title":"EH-MAM: Easy-to-Hard Masked Acoustic Modeling for Self-Supervised Speech Representation Learning","arxiv_id":"2410.13179","date":"2024-10-17","proceeding":null,"authors":["Ashish Seth","Ramaneswaran Selvakumar","S Sakshi","Sonal Kumar","Sreyan Ghosh","Dinesh Manocha"],"abstract":"In this paper, we present EH-MAM (Easy-to-Hard adaptive Masked Acoustic Modeling), a novel self-supervised learning approach for speech representation learning. In contrast to the prior methods that use random masking schemes for Masked Acoustic Modeling (MAM), we introduce a novel selective and adaptive masking strategy. Specifically, during SSL training, we progressively introduce harder regions to the model for reconstruction. Our approach automatically selects hard regions and is built on the observation that the reconstruction loss of individual frames in MAM can provide natural signals to judge the difficulty of solving the MAM pre-text task for that frame. To identify these hard regions, we employ a teacher model that first predicts the frame-wise losses and then decides which frames to mask. By learning to create challenging problems, such as identifying harder frames and solving them simultaneously, the model is able to learn more effective representations and thereby acquire a more comprehensive understanding of the speech. Quantitatively, EH-MAM outperforms several state-of-the-art baselines across various low-resource speech recognition and SUPERB benchmarks by 5%-10%. Additionally, we conduct a thorough analysis to show that the regions masked by EH-MAM effectively capture useful context across speech frames.","url_abs":"https://arxiv.org/abs/2410.13179v1","url_pdf":"https://arxiv.org/pdf/2410.13179v1.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":"eh-mam-easy-to-hard-masked-acoustic-modeling","repo_url":"https://github.com/cs20s030/ehmam","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":0,"framework":"pytorch","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"self-supervised-learning","task_name":"Self-Supervised Learning"},{"task_slug":"speech-recognition","task_name":"Speech Recognition"},{"task_slug":"speech-representation-learning","task_name":"Speech Representation Learning"},{"task_slug":"speech-recognition-1","task_name":"speech-recognition"}],"methods":[{"method_slug":"adaptive-masking","method_name":"Adaptive Masking"},{"method_slug":"l1-regularization","method_name":"L1 Regularization"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2410.13179","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.13179"}},"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":"deterministic:regex_extraction","url":"https://github.com/cs20s030/ehmam","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":6,"unverified":4},"by_repo_kind":{"official":{"samples":10,"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":"d0c01822a7592080","entry":"collate_tokens","repo":"cs20s030/ehmam","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/data_utils.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":"d0c01822a7592080"}},{"code_sha256_prefix":"64a73f82ea703bf0","entry":"get_alibi","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/utils.py","link_basis":"first_harvest_node","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":"64a73f82ea703bf0"}},{"code_sha256_prefix":"27e813fec3cb4b6f","entry":"get_annealed_rate","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/data2vec_audio.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/data2vec_audio.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":"27e813fec3cb4b6f"}},{"code_sha256_prefix":"3f903f847b8f7f28","entry":"get_layer_id_for_vit","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/mae_image_classification.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/mae_image_classification.py","link_basis":"first_harvest_node","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":"3f903f847b8f7f28"}},{"code_sha256_prefix":"beba926588613ced","entry":"masked_alibi","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/utils.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/utils.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":"beba926588613ced"}},{"code_sha256_prefix":"cf82e11f14a349c2","entry":"update_checkpoint","repo":"cs20s030/ehmam","repo_kind":"official","path":"fb_convert_beit_cp.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/fb_convert_beit_cp.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":"cf82e11f14a349c2"}},{"code_sha256_prefix":"3185afc3e87293ed","entry":"get_2d_sincos_pos_embed","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/mae.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":"3185afc3e87293ed"}},{"code_sha256_prefix":"f10004e059714d42","entry":"get_2d_sincos_pos_embed_from_grid","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/mae.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":"f10004e059714d42"}},{"code_sha256_prefix":"320ee357dd9d70f1","entry":"load_indexed_dataset","repo":"cs20s030/ehmam","repo_kind":"official","path":"data_utils.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/data_utils.py","link_basis":"first_harvest_node","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":"320ee357dd9d70f1"}},{"code_sha256_prefix":"915281feeb90ee5a","entry":"modify_relative_position_bias","repo":"cs20s030/ehmam","repo_kind":"official","path":"models/mae.py","file_url":"https://github.com/cs20s030/ehmam/blob/HEAD/models/mae.py","link_basis":"first_harvest_node","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":"915281feeb90ee5a"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}