{"url":"/task/rhythm","name":"Rhythm","slug":"rhythm","description_markdown":null,"categories":[],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":515,"papers_with_code":137,"benchmarks":0,"benchmark_tables_in_archive":0,"benchmark_tables_shown":0,"benchmark_tables_withheld_as_spam":0,"benchmark_definition":"a leaderboard table with at least one row; benchmark_tables_shown also counts the zero-row tables; benchmark_tables_in_archive adds the tables withheld as spam","datasets":2,"subtasks":0,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/ptb-xl","name":"PTB-XL","full_name":"","num_papers_in_archive":7},{"url":"/dataset/fraxtil","name":"Fraxtil","full_name":null,"num_papers_in_archive":3}],"subtasks":[],"parent_tasks":[],"papers":{"order":"repositories listed in the archive (desc), then date (desc); the archive holds no stars","population":"papers tagged with this task that list at least one repository in the archive","shown":30,"of":137,"tagged_in_all":515,"items":[{"url":"/paper/cardiologist-level-arrhythmia-detection-with","title":"Cardiologist-Level Arrhythmia Detection with Convolutional Neural Networks","date":"2017-07-06","arxiv_id":"1707.01836","repositories_listed":7,"syntology":{"n":1,"n_ran":1,"n_unverified":0,"n_pointer_only":1}},{"url":"/paper/unsupervised-speech-decomposition-via-triple","title":"Unsupervised Speech Decomposition via Triple Information Bottleneck","date":"2020-04-23","arxiv_id":"2004.11284","repositories_listed":6,"syntology":{"n":12,"n_ran":0,"n_unverified":12,"n_pointer_only":0}},{"url":"/paper/mellotron-multispeaker-expressive-voice","title":"Mellotron: Multispeaker expressive voice synthesis by conditioning on rhythm, pitch and global style tokens","date":"2019-10-26","arxiv_id":"1910.11997","repositories_listed":5,"syntology":null},{"url":"/paper/beatnet-crnn-and-particle-filtering-for","title":"BeatNet: CRNN and Particle Filtering for Online Joint Beat Downbeat and Meter Tracking","date":"2021-08-08","arxiv_id":"2108.03576","repositories_listed":4,"syntology":null},{"url":"/paper/deep-music-analogy-via-latent-representation","title":"Deep Music Analogy Via Latent Representation Disentanglement","date":"2019-06-09","arxiv_id":"1906.03626","repositories_listed":3,"syntology":null},{"url":"/paper/mmsu-a-massive-multi-task-spoken-language","title":"MMSU: A Massive Multi-task Spoken Language Understanding and Reasoning Benchmark","date":"2025-06-05","arxiv_id":"2506.04779","repositories_listed":2,"syntology":{"n":6,"n_ran":4,"n_unverified":2,"n_pointer_only":6}},{"url":"/paper/musicongen-rhythm-and-chord-control-for","title":"MusiConGen: Rhythm and Chord Control for Transformer-Based Text-to-Music Generation","date":"2024-07-21","arxiv_id":"2407.15060","repositories_listed":2,"syntology":null},{"url":"/paper/ellipsoid-fitting-with-the-cayley-transform","title":"Ellipsoid fitting with the Cayley transform","date":"2023-04-20","arxiv_id":"2304.10630","repositories_listed":2,"syntology":null},{"url":"/paper/dancenet3d-music-based-dance-generation-with","title":"DanceFormer: Music Conditioned 3D Dance Generation with Parametric Motion Transformer","date":"2021-03-18","arxiv_id":"2103.10206","repositories_listed":2,"syntology":null},{"url":"/paper/anomaly-detection-in-time-series-with-triadic","title":"Anomaly Detection in Time Series with Triadic Motif Fields and Application in Atrial Fibrillation ECG Classification","date":"2020-12-09","arxiv_id":"2012.04936","repositories_listed":2,"syntology":null},{"url":"/paper/can-gan-originate-new-electronic-dance-music","title":"Can GAN originate new electronic dance music genres? -- Generating novel rhythm patterns using GAN with Genre Ambiguity Loss","date":"2020-11-25","arxiv_id":"2011.13062","repositories_listed":2,"syntology":null},{"url":"/paper/speech-gesture-generation-from-the-trimodal","title":"Speech Gesture Generation from the Trimodal Context of Text, Audio, and Speaker Identity","date":"2020-09-04","arxiv_id":"2009.02119","repositories_listed":2,"syntology":null},{"url":"/paper/deep-learning-for-ecg-analysis-benchmarks-and","title":"Deep Learning for ECG Analysis: Benchmarks and Insights from PTB-XL","date":"2020-04-28","arxiv_id":"2004.13701","repositories_listed":2,"syntology":null},{"url":"/paper/towards-democratizing-music-production-with","title":"Towards democratizing music production with AI-Design of Variational Autoencoder-based Rhythm Generator as a DAW plugin","date":"2020-04-01","arxiv_id":"2004.01525","repositories_listed":2,"syntology":null},{"url":"/paper/circacompare-a-method-to-estimate-and","title":"CircaCompare: a method to estimate and statistically support differences in mesor, amplitude and phase, between circadian rhythms","date":"2019-10-07","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/towards-understanding-ecg-rhythm","title":"Towards understanding ECG rhythm classification using convolutional neural networks and attention mappings","date":"2018-08-17","arxiv_id":null,"repositories_listed":2,"syntology":null},{"url":"/paper/from-generality-to-mastery-composer-style","title":"From Generality to Mastery: Composer-Style Symbolic Music Generation via Large-Scale Pre-training","date":"2025-06-20","arxiv_id":"2506.17497","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-rhythm-and-voice-conversion-to","title":"Unsupervised Rhythm and Voice Conversion to Improve ASR on Dysarthric Speech","date":"2025-06-02","arxiv_id":"2506.01618","repositories_listed":1,"syntology":null},{"url":"/paper/leveraging-am-and-fm-rhythm-spectrograms-for","title":"Leveraging AM and FM Rhythm Spectrograms for Dementia Classification and Assessment","date":"2025-06-01","arxiv_id":"2506.00861","repositories_listed":1,"syntology":null},{"url":"/paper/mavl-a-multilingual-audio-video-lyrics","title":"MAVL: A Multilingual Audio-Video Lyrics Dataset for Animated Song Translation","date":"2025-05-24","arxiv_id":"2505.18614","repositories_listed":1,"syntology":{"n":19,"n_ran":0,"n_unverified":19,"n_pointer_only":0}},{"url":"/paper/voila-voice-language-foundation-models-for","title":"Voila: Voice-Language Foundation Models for Real-Time Autonomous Interaction and Voice Role-Play","date":"2025-05-05","arxiv_id":"2505.02707","repositories_listed":1,"syntology":{"n":11,"n_ran":7,"n_unverified":4,"n_pointer_only":0}},{"url":"/paper/evolutionary-optimization-for-the","title":"Evolutionary Optimization for the Classification of Small Molecules Regulating the Circadian Rhythm Period: A Reliable Assessment","date":"2025-04-27","arxiv_id":"2505.05485","repositories_listed":1,"syntology":null},{"url":"/paper/protoecgnet-case-based-interpretable-deep","title":"ProtoECGNet: Case-Based Interpretable Deep Learning for Multi-Label ECG Classification with Contrastive Learning","date":"2025-04-11","arxiv_id":"2504.08713","repositories_listed":1,"syntology":null},{"url":"/paper/ecg-expert-qa-a-benchmark-for-evaluating","title":"ECG-Expert-QA: A Benchmark for Evaluating Medical Large Language Models in Heart Disease Diagnosis","date":"2025-02-16","arxiv_id":"2502.17475","repositories_listed":1,"syntology":null},{"url":"/paper/reading-your-heart-learning-ecg-words-and","title":"Reading Your Heart: Learning ECG Words and Sentences via Pre-training ECG Language Model","date":"2025-02-15","arxiv_id":"2502.10707","repositories_listed":1,"syntology":null},{"url":"/paper/improvnet-generating-controllable-musical","title":"ImprovNet -- Generating Controllable Musical Improvisations with Iterative Corruption Refinement","date":"2025-02-06","arxiv_id":"2502.04522","repositories_listed":1,"syntology":null},{"url":"/paper/combining-yolo-and-visual-rhythm-for-vehicle","title":"Combining YOLO and Visual Rhythm for Vehicle Counting","date":"2025-01-08","arxiv_id":"2501.04534","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-textless-dialogue-generation","title":"Real-Time Textless Dialogue Generation","date":"2025-01-08","arxiv_id":"2501.04877","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-license-plate-recognition-in-videos","title":"Efficient License Plate Recognition in Videos Using Visual Rhythm and Accumulative Line Analysis","date":"2025-01-08","arxiv_id":"2501.04750","repositories_listed":1,"syntology":null},{"url":"/paper/efficient-video-based-alpr-system-using-yolo","title":"Efficient Video-Based ALPR System Using YOLO and Visual Rhythm","date":"2025-01-04","arxiv_id":"2501.02270","repositories_listed":1,"syntology":null}],"syntology_records":5,"syntology_note":"a paper without a record is not a recorded non-run: it may lack an arXiv id or simply be absent from the graph layer"},"description_links":{"kept":0,"unwrapped_to_text":0,"bare_urls_linked":0,"relative_images_dropped":0,"rule":"internal links are kept only when the target slug exists in the catalog"},"syntology":{"read_at":"2026-09-24T18:15:14+00:00","claim":"Per-sample execution status on synthesized fixtures ('ran N of M samples'); not a correctness claim and not a ranking signal.","status_vocabulary":{"ran_honours":"ran, honoured the contract we drafted","ran_violates":"ran, violated the contract we drafted","ran_draft_wrong":"ran; our contract draft was wrong, not the code","ran_fixture":"ran; our fixture could not drive it","ran":"ran on a synthesized input","unverified":"unverified (harvested, no recorded run)"}},"not_shown":{"libraries":"the archive has no per-task library table","trend_sparklines":"the Trend column of the benchmarks table was a rendered image; it is not in the archive","social_and_latest_sorts":"stars and social signals are not in the archive"}}