{"about":{"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.","site":"https://codewithpapers.app","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","syntology":{"site":"https://syntology.ai","developers":"https://syntology.ai/developers","mcp":{"server":"https://syntology.ai/mcp","transport":"streamable-http","server_card":"https://syntology.ai/.well-known/mcp/server-card.json","auth":{"type":"trial token, no account","trial_token":"https://syntology.ai/api/oauth/trial/token","method":"POST","docs":"https://syntology.ai/developers"}},"have":"https://syntology.ai/api/graph/have?x=<method, arXiv id or title> (free, answers coverage only)","paper_base":"https://syntology.ai/paper/","atlas_base":"https://app.syntology.ai/?focus="},"machine_readable":[{"url":"https://codewithpapers.app/llms.txt","what":"the machine catalog: every machine-readable file, counted"},{"url":"https://codewithpapers.app/index/manifest.json","what":"paper-to-code index by arXiv id, with Syntology's counts"},{"url":"https://codewithpapers.app/search/manifest.json","what":"site search index (titles, authors) and its files"},{"url":"https://codewithpapers.app/download","what":"bulk files: Syntology's layer, described there"},{"url":"https://codewithpapers.app/build_manifest.json","what":"the build record: inputs, counts, exclusions, probes"}]},"url":"/paper/beat-this-accurate-beat-tracking-without-dbn","title":"Beat this! Accurate beat tracking without DBN postprocessing","arxiv_id":"2407.21658","date":"2024-07-31","proceeding":null,"authors":[],"abstract":"We propose a system for tracking beats and downbeats with two objectives: generality across a diverse music range, and high accuracy. We achieve generality by training on multiple datasets -- including solo instrument recordings, pieces with time signature changes, and classical music with high tempo variations -- and by removing the commonly used Dynamic Bayesian Network (DBN) postprocessing, which introduces constraints on the meter and tempo. For high accuracy, among other improvements, we develop a loss function tolerant to small time shifts of annotations, and an architecture alternating convolutions with transformers either over frequency or time. Our system surpasses the current state of the art in F1 score despite using no DBN. However, it can still fail, especially for difficult and underrepresented genres, and performs worse on continuity metrics, so we publish our model, code, and preprocessed datasets, and invite others to beat this.","url_abs":"https://arxiv.org/abs/2407.21658v1","url_pdf":"https://arxiv.org/pdf/2407.21658v1.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":"beat-this-accurate-beat-tracking-without-dbn","repo_url":"https://github.com/CPJKU/beat_this","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"beat-tracking","task_name":"Beat Tracking"},{"task_slug":"downbeat-tracking","task_name":"Downbeat Tracking"}],"methods":[{"method_slug":"adamw","method_name":"AdamW"},{"method_slug":"attention","method_name":"Attention"},{"method_slug":"batch-normalization","method_name":"Batch Normalization"},{"method_slug":"dense-connections","method_name":"Dense Connections"},{"method_slug":"dropout","method_name":"Dropout"},{"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":"rmsnorm","method_name":"RMSNorm"},{"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/beat-tracking-on-asap-aligned-scores-and","task":"Beat Tracking","dataset":"ASAP","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"76.3"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-ballroom","task":"Beat Tracking","dataset":"Ballroom","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"97.5"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-beatles","task":"Beat Tracking","dataset":"Beatles","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"94.5"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-candombe","task":"Beat Tracking","dataset":"Candombe","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"99.7"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-filosax","task":"Beat Tracking","dataset":"Filosax","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"99.5"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-gtzan","task":"Beat Tracking","dataset":"GTZAN","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"89.1"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-groove","task":"Beat Tracking","dataset":"Groove","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"93.7"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-guitarset","task":"Beat Tracking","dataset":"GuitarSet","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"92.0"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-hjdb","task":"Beat Tracking","dataset":"HJDB","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"98.2"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-hainsworth","task":"Beat Tracking","dataset":"Hainsworth","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"91.9"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-harmonix","task":"Beat Tracking","dataset":"Harmonix","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"95.8"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-jaah","task":"Beat Tracking","dataset":"JAAH","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"95.1"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-simac","task":"Beat Tracking","dataset":"SIMAC","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"77.9"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-smc","task":"Beat Tracking","dataset":"SMC","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"62.7"},"uses_additional_data":false},{"leaderboard":"/sota/beat-tracking-on-tapcorrect","task":"Beat Tracking","dataset":"TapCorrect","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"93.0"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-asap-aligned-scores-and","task":"Downbeat Tracking","dataset":"ASAP","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"61.2"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-ballroom","task":"Downbeat Tracking","dataset":"Ballroom","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"95.3"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-beatles","task":"Downbeat Tracking","dataset":"Beatles","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"88.8"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-candombe","task":"Downbeat Tracking","dataset":"Candombe","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"99.7"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-filosax","task":"Downbeat Tracking","dataset":"Filosax","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"98.5"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-gtzan","task":"Downbeat Tracking","dataset":"GTZAN","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"78.3"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-groove","task":"Downbeat Tracking","dataset":"Groove","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"82.1"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-guitarset","task":"Downbeat Tracking","dataset":"GuitarSet","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"88.1"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-hjdb","task":"Downbeat Tracking","dataset":"HJDB","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"96.6"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-hainsworth","task":"Downbeat Tracking","dataset":"Hainsworth","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"80.0"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-harmonix","task":"Downbeat Tracking","dataset":"Harmonix","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"90.7"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-jaah","task":"Downbeat Tracking","dataset":"JAAH","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"85.0"},"uses_additional_data":false},{"leaderboard":"/sota/downbeat-tracking-on-tapcorrect","task":"Downbeat Tracking","dataset":"TapCorrect","model":"Beat This!","rank_in_archive_order":1,"of":1,"metrics":{"F1":"86.4"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2407.21658","atlas_url":"https://app.syntology.ai/?focus=2407.21658","mcp":null,"developers":"https://syntology.ai/developers","held":true,"reason":"arxiv_id_in_atlas","checked_against":{"atlas_ids":549449,"atlas_ids_sha256":"afd72399dafd9906e9062927f70655952385a3d75488558e1f0484e950ab09b7","read_at":"2026-10-05T01:46:21Z"},"agent_calls":[{"tool":"get_citation_path","arguments":{"paper_1":"2407.21658"},"arguments_in":{"paper_2":"another paper's arXiv id or title"},"call":"get_citation_path(paper_1=\"2407.21658\", paper_2=\"…\")"},{"tool":"get_concepts_for_paper","arguments":{"arxiv_id":"2407.21658"},"call":"get_concepts_for_paper(arxiv_id=\"2407.21658\")"}],"by_repo":[{"repo":"CPJKU/beat_this","kind":"official","samples":0,"ran":0,"instrument":0,"unverified":0}],"by_repo_is":"one row per repository in the archive's code links, Syntology's graph links or the samples; samples 0 means no sample is linked to this paper, a statement about Syntology's coverage, not about the repository: with harvested_for_other_papers present, Syntology harvested the repository for that many other papers, and without it, Syntology harvested nothing from it; placed_by_identical_code counts samples whose link records no repository, placed here because identical code was harvested from this repository for another paper; ran counts executions on a synthesized input and instrument counts failures of Syntology's instrument, not of the code"},"code_links_note":null,"arxiv_metadata":null,"syntology_extracted_results":null,"record_sha256":"12a73bae87fbf2db77ac2c6b2df528f6e029fc2e1c7130225e21b18525cf2f5a","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}