{"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/voice2series-reprogramming-acoustic-models","title":"Voice2Series: Reprogramming Acoustic Models for Time Series Classification","arxiv_id":"2106.09296","date":"2021-06-17","proceeding":null,"authors":["Chao-Han Huck Yang","Yun-Yun Tsai","Pin-Yu Chen"],"abstract":"Learning to classify time series with limited data is a practical yet challenging problem. Current methods are primarily based on hand-designed feature extraction rules or domain-specific data augmentation. Motivated by the advances in deep speech processing models and the fact that voice data are univariate temporal signals, in this paper, we propose Voice2Series (V2S), a novel end-to-end approach that reprograms acoustic models for time series classification, through input transformation learning and output label mapping. Leveraging the representation learning power of a large-scale pre-trained speech processing model, on 30 different time series tasks we show that V2S performs competitive results on 19 time series classification tasks. We further provide a theoretical justification of V2S by proving its population risk is upper bounded by the source risk and a Wasserstein distance accounting for feature alignment via reprogramming. Our results offer new and effective means to time series classification.","url_abs":"https://arxiv.org/abs/2106.09296v3","url_pdf":"https://arxiv.org/pdf/2106.09296v3.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":"voice2series-reprogramming-acoustic-models","repo_url":"https://github.com/huckiyang/Voice2Series-Reprogramming","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"voice2series-reprogramming-acoustic-models","repo_url":"https://github.com/dodohow1011/speechadvreprogram","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"tf","reach":null},{"paper_slug":"voice2series-reprogramming-acoustic-models","repo_url":"https://github.com/srijith-rkr/kaust-whisper-adapter","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok"}}],"tasks":[{"task_slug":"classification-1","task_name":"Classification"},{"task_slug":"data-augmentation","task_name":"Data Augmentation"},{"task_slug":"ecg-classification","task_name":"ECG Classification"},{"task_slug":"representation-learning","task_name":"Representation Learning"},{"task_slug":"time-series-1","task_name":"Time Series"},{"task_slug":"time-series","task_name":"Time Series Analysis"},{"task_slug":"time-series-classification","task_name":"Time Series Classification"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/ecg-classification-on-ucr-time-series","task":"ECG Classification","dataset":"UCR Time Series Classification Archive","model":"V2Sa","rank_in_archive_order":1,"of":1,"metrics":{"Accuracy (Test)":"93.96"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-earthquakes","task":"Time Series Classification","dataset":"Earthquakes","model":"V2Sa","rank_in_archive_order":1,"of":2,"metrics":{"Accuracy (Test)":"78.42"},"uses_additional_data":false},{"leaderboard":"/sota/time-series-classification-on-forda","task":"Time Series Classification","dataset":"FordA","model":"V2Sa","rank_in_archive_order":1,"of":2,"metrics":{"Acc. (test)":"100"},"uses_additional_data":false}],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=2106.09296","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2106.09296"}},"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/dodohow1011/speechadvreprogram","reach":null},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/srijith-rkr/kaust-whisper-adapter","reach":{"status":"ok"}},{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/huckiyang/Voice2Series-Reprogramming","reach":null}],"summary":{"ran":1,"unverified":6},"by_repo_kind":{"official":{"samples":4,"ran":1,"repositories":1},"listed":{"samples":3,"ran":0,"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":3,"samples":[{"code_sha256_prefix":"153caf7d3bfcd33b","entry":"ARTLayer","repo":"huckiyang/Voice2Series-Reprogramming","repo_kind":"official","path":"ts_model.py","file_url":"https://github.com/huckiyang/Voice2Series-Reprogramming/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"153caf7d3bfcd33b"}},{"code_sha256_prefix":"9accaf09272fa8de","entry":"ARTLayer","repo":"dodohow1011/speechadvreprogram","repo_kind":"listed","path":"ts_model.py","file_url":"https://github.com/dodohow1011/speechadvreprogram/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"9accaf09272fa8de"}},{"code_sha256_prefix":"dd2707972254321a","entry":"SegZeroPadding1D","repo":"huckiyang/Voice2Series-Reprogramming","repo_kind":"official","path":"ts_model.py","file_url":"https://github.com/huckiyang/Voice2Series-Reprogramming/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"dd2707972254321a"}},{"code_sha256_prefix":"842dae934f36948c","entry":"WARTmodel","repo":"huckiyang/Voice2Series-Reprogramming","repo_kind":"official","path":"ts_model.py","file_url":"https://github.com/huckiyang/Voice2Series-Reprogramming/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"842dae934f36948c"}},{"code_sha256_prefix":"357bdf0c9486647f","entry":"WARTmodel","repo":"dodohow1011/speechadvreprogram","repo_kind":"listed","path":"ts_model.py","file_url":"https://github.com/dodohow1011/speechadvreprogram/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"357bdf0c9486647f"}},{"code_sha256_prefix":"096ee24533130aea","entry":"multi_mapping","repo":"huckiyang/Voice2Series-Reprogramming","repo_kind":"official","path":"ts_model.py","file_url":"https://github.com/huckiyang/Voice2Series-Reprogramming/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"096ee24533130aea"}},{"code_sha256_prefix":"0f90ec13976b2e46","entry":"multi_mapping","repo":"dodohow1011/speechadvreprogram","repo_kind":"listed","path":"ts_model.py","file_url":"https://github.com/dodohow1011/speechadvreprogram/blob/HEAD/ts_model.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"NONE","inline_ok":false,"mcp_get_code":{"code_sha256":"0f90ec13976b2e46"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}