{"url":"/task/audio-signal-processing","name":"Audio Signal Processing","slug":"audio-signal-processing","description_markdown":"This is a general task that covers transforming audio inputs into audio outputs, not limited to existing PaperWithCode categories of Source Separation, Denoising, Classification, Recognition, etc.","categories":[{"name":"Audio","url":"/area/audio"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":70,"papers_with_code":26,"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":3,"parent_tasks":0},"benchmarks":[],"datasets":[{"url":"/dataset/remfx","name":"RemFX","full_name":"RemFX Evaluation Datasets","num_papers_in_archive":3},{"url":"/dataset/mdrt","name":"mDRT","full_name":"Multilingual Diagnostic Rhyme Test","num_papers_in_archive":1}],"subtasks":[{"url":"/task/audio-compression","name":"Audio Compression"},{"url":"/task/audio-effects-modeling","name":"Audio Effects Modeling"},{"url":"/task/blind-source-separation","name":"blind source separation"}],"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":26,"of":26,"tagged_in_all":70,"items":[{"url":"/paper/high-fidelity-neural-audio-compression","title":"High Fidelity Neural Audio Compression","date":"2022-10-24","arxiv_id":"2210.13438","repositories_listed":6,"syntology":null},{"url":"/paper/differentiable-signal-processing-with-black","title":"Differentiable Signal Processing With Black-Box Audio Effects","date":"2021-05-11","arxiv_id":"2105.04752","repositories_listed":2,"syntology":null},{"url":"/paper/torchfx-a-modern-approach-to-audio-dsp-with","title":"TorchFX: A modern approach to Audio DSP with PyTorch and GPU acceleration","date":"2025-04-11","arxiv_id":"2504.08624","repositories_listed":1,"syntology":null},{"url":"/paper/manikin-recorded-cardiopulmonary-sounds","title":"Manikin-Recorded Cardiopulmonary Sounds Dataset Using Digital Stethoscope","date":"2024-10-04","arxiv_id":"2410.03280","repositories_listed":1,"syntology":null},{"url":"/paper/audio-driven-reinforcement-learning-for-head","title":"Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments","date":"2024-09-16","arxiv_id":"2409.10048","repositories_listed":1,"syntology":null},{"url":"/paper/spectral-mapping-of-singing-voices-u-net","title":"Spectral Mapping of Singing Voices: U-Net-Assisted Vocal Segmentation","date":"2024-05-30","arxiv_id":"2405.20059","repositories_listed":1,"syntology":null},{"url":"/paper/a-survey-on-data-augmentation-in-large-model","title":"A Survey on Data Augmentation in Large Model Era","date":"2024-01-27","arxiv_id":"2401.15422","repositories_listed":1,"syntology":null},{"url":"/paper/haaqi-net-a-non-intrusive-neural-music","title":"HAAQI-Net: A Non-intrusive Neural Music Audio Quality Assessment Model for Hearing Aids","date":"2024-01-02","arxiv_id":"2401.01145","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-harmonic-parameter-estimation","title":"Unsupervised Harmonic Parameter Estimation Using Differentiable DSP and Spectral Optimal Transport","date":"2023-12-22","arxiv_id":"2312.14507","repositories_listed":1,"syntology":{"n":6,"n_ran":6,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/audio-signal-based-danger-detection-using","title":"Audio signal based danger detection using signal processing and deep learning","date":"2023-09-19","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/energy-preservation-and-stability-of-random","title":"Instabilities in Convnets for Raw Audio","date":"2023-09-11","arxiv_id":"2309.05855","repositories_listed":1,"syntology":null},{"url":"/paper/mf-pam-accurate-pitch-estimation-through","title":"MF-PAM: Accurate Pitch Estimation through Periodicity Analysis and Multi-level Feature Fusion","date":"2023-06-16","arxiv_id":"2306.09640","repositories_listed":1,"syntology":null},{"url":"/paper/representing-input-transformations-by-low","title":"Subspace-Configurable Networks","date":"2023-05-22","arxiv_id":"2305.13536","repositories_listed":1,"syntology":null},{"url":"/paper/myriad-a-multi-array-room-acoustic-database","title":"MYRiAD: A Multi-Array Room Acoustic Database","date":"2023-01-30","arxiv_id":"2301.13057","repositories_listed":1,"syntology":null},{"url":"/paper/sound2synth-interpreting-sound-via-fm","title":"Sound2Synth: Interpreting Sound via FM Synthesizer Parameters Estimation","date":"2022-05-06","arxiv_id":"2205.03043","repositories_listed":1,"syntology":null},{"url":"/paper/visualization-of-linear-operations-in-the","title":"Visualization of Linear Operations in the Spherical Harmonics Domain","date":"2021-04-27","arxiv_id":"2104.13069","repositories_listed":1,"syntology":null},{"url":"/paper/deepspectrumlite-a-power-efficient-transfer","title":"DeepSpectrumLite: A Power-Efficient Transfer Learning Framework for Embedded Speech and Audio Processing from Decentralised Data","date":"2021-04-23","arxiv_id":"2104.11629","repositories_listed":1,"syntology":null},{"url":"/paper/l3das21-challenge-machine-learning-for-3d","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","date":"2021-04-12","arxiv_id":"2104.05499","repositories_listed":1,"syntology":null},{"url":"/paper/melon-playlist-dataset-a-public-dataset-for","title":"Melon Playlist Dataset: a public dataset for audio-based playlist generation and music tagging","date":"2021-01-30","arxiv_id":"2102.00201","repositories_listed":1,"syntology":null},{"url":"/paper/upsampling-artifacts-in-neural-audio","title":"Upsampling artifacts in neural audio synthesis","date":"2020-10-27","arxiv_id":"2010.14356","repositories_listed":1,"syntology":null},{"url":"/paper/wav2shape-hearing-the-shape-of-a-drum-machine","title":"wav2shape: Hearing the Shape of a Drum Machine","date":"2020-07-20","arxiv_id":"2007.10299","repositories_listed":1,"syntology":null},{"url":"/paper/exploring-quality-and-generalizability-in","title":"Exploring Quality and Generalizability in Parameterized Neural Audio Effects","date":"2020-06-10","arxiv_id":"2006.05584","repositories_listed":1,"syntology":null},{"url":"/paper/signaltrain-profiling-audio-compressors-with","title":"SignalTrain: Profiling Audio Compressors with Deep Neural Networks","date":"2019-05-28","arxiv_id":"1905.11928","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-audio-signal-processing","title":"Deep Learning for Audio Signal Processing","date":"2019-04-30","arxiv_id":"1905.00078","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-probabilistic-inference-for","title":"End-to-End Probabilistic Inference for Nonstationary Audio Analysis","date":"2019-01-31","arxiv_id":"1901.11436","repositories_listed":1,"syntology":null},{"url":"/paper/unifying-probabilistic-models-for-time","title":"Unifying Probabilistic Models for Time-Frequency Analysis","date":"2018-11-06","arxiv_id":"1811.02489","repositories_listed":1,"syntology":null}],"syntology_records":1,"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"}}