{"url":"/task/bandwidth-extension","name":"Bandwidth Extension","slug":"bandwidth-extension","description_markdown":"Bandwidth extension is the task of expanding the bandwidth of a signal in a way that approximates the original or desired higher bandwidth signal.","categories":[{"name":"Audio","url":"/area/audio"},{"name":"Speech","url":"/area/speech"}],"source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","slug_source":"archive_url"},"counts":{"papers_tagged":50,"papers_with_code":18,"benchmarks":6,"benchmark_tables_in_archive":6,"benchmark_tables_shown":6,"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":6,"subtasks":0,"parent_tasks":1},"benchmarks":[{"leaderboard":"/sota/bandwidth-extension-on-vctk","slug":"bandwidth-extension-on-vctk","dataset":"VCTK","dataset_url":"/dataset/vctk","rows_in_archive":1,"metrics":["LSD"],"first_row_in_archive_order":{"model":"AERO","paper_title":"AERO: Audio Super Resolution in the Spectral Domain","paper_url":"/paper/aero-audio-super-resolution-in-the-spectral","paper_date":"2022-11-22","arxiv_id":"2211.12232","code_links":[{"title":"slp-rl/aero","url":"https://github.com/slp-rl/aero"}],"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}}},{"leaderboard":"/sota/bandwidth-extension-on-vibravox","slug":"bandwidth-extension-on-vibravox","dataset":"VibraVox (rigid in-ear microphone)","dataset_url":"/dataset/vibravox","rows_in_archive":1,"metrics":["STOI","Noresqua-MOS","PER (wav2vec2)","EER (ECAPA2)"],"first_row_in_archive_order":{"model":"Configurable EBEN (M=4, P=2, Q=4)","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-forehead","slug":"bandwidth-extension-on-vibravox-forehead","dataset":"VibraVox (forehead accelerometer)","dataset_url":"/dataset/vibravox-forehead-accelerometer","rows_in_archive":1,"metrics":["Noresqua-MOS","STOI","PER (wav2vec2)","EER (ECAPA2)"],"first_row_in_archive_order":{"model":"Configurable EBEN (M=4, P=4, Q=4)","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-soft-in-ear","slug":"bandwidth-extension-on-vibravox-soft-in-ear","dataset":"VibraVox (soft in-ear microphone)","dataset_url":"/dataset/vibravox-soft-in-ear-microphone","rows_in_archive":1,"metrics":["Noresqua-MOS","STOI","PER (wav2vec2)","EER (ECAPA2)"],"first_row_in_archive_order":{"model":"Configurable EBEN (M=4, P=2, Q=4)","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-temple","slug":"bandwidth-extension-on-vibravox-temple","dataset":"VibraVox (temple vibration pickup)","dataset_url":"/dataset/vibravox-temple-vibration-pickup","rows_in_archive":1,"metrics":["Noresqua-MOS","STOI","PER (wav2vec2)","EER (ECAPA2)"],"first_row_in_archive_order":{"model":"Configurable EBEN (M=4, P=1, Q=4)","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}},{"leaderboard":"/sota/bandwidth-extension-on-vibravox-throat","slug":"bandwidth-extension-on-vibravox-throat","dataset":"VibraVox (throat microphone)","dataset_url":"/dataset/vibravox-throat-microphone","rows_in_archive":1,"metrics":["Noresqua-MOS","STOI","PER (wav2vec2)","EER (ECAPA2)"],"first_row_in_archive_order":{"model":"Configurable EBEN (M=4, P=2, Q=4)","paper_title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","paper_url":"/paper/vibravox-a-dataset-of-french-speech-captured","paper_date":"2024-07-16","arxiv_id":"2407.11828","code_links":[{"title":"jhauret/vibravox","url":"https://github.com/jhauret/vibravox"}],"syntology":null}}],"datasets":[{"url":"/dataset/vctk","name":"VCTK","full_name":"CSTR VCTK Corpus","num_papers_in_archive":476},{"url":"/dataset/vibravox-forehead-accelerometer","name":"VibraVox (forehead accelerometer)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox","name":"VibraVox (rigid in-ear microphone)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-soft-in-ear-microphone","name":"VibraVox (soft in-ear microphone)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-temple-vibration-pickup","name":"VibraVox (temple vibration pickup)","full_name":"","num_papers_in_archive":1},{"url":"/dataset/vibravox-throat-microphone","name":"VibraVox (throat microphone)","full_name":"","num_papers_in_archive":1}],"subtasks":[],"parent_tasks":[{"url":"/task/speech-enhancement","name":"Speech Enhancement"}],"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":18,"of":18,"tagged_in_all":50,"items":[{"url":"/paper/hifi-a-unified-framework-for-neural-vocoding","title":"HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement","date":"2022-03-24","arxiv_id":"2203.13086","repositories_listed":3,"syntology":{"n":12,"n_ran":9,"n_unverified":3,"n_pointer_only":1}},{"url":"/paper/towards-high-quality-and-efficient-speech","title":"Towards High-Quality and Efficient Speech Bandwidth Extension with Parallel Amplitude and Phase Prediction","date":"2024-01-12","arxiv_id":"2401.06387","repositories_listed":2,"syntology":{"n":5,"n_ran":5,"n_unverified":0,"n_pointer_only":5}},{"url":"/paper/eben-extreme-bandwidth-extension-network-1","title":"EBEN: Extreme bandwidth extension network applied to speech signals captured with noise-resilient body-conduction microphones","date":"2022-10-25","arxiv_id":"2210.14090","repositories_listed":2,"syntology":null},{"url":"/paper/on-filter-generalization-for-music-bandwidth","title":"On Filter Generalization for Music Bandwidth Extension Using Deep Neural Networks","date":"2020-11-14","arxiv_id":"2011.07274","repositories_listed":2,"syntology":null},{"url":"/paper/generative-speech-foundation-model","title":"Generative Speech Foundation Model Pretraining for High-Quality Speech Extraction and Restoration","date":"2024-09-24","arxiv_id":"2409.16117","repositories_listed":1,"syntology":null},{"url":"/paper/vibravox-a-dataset-of-french-speech-captured","title":"Vibravox: A Dataset of French Speech Captured with Body-conduction Audio Sensors","date":"2024-07-16","arxiv_id":"2407.11828","repositories_listed":1,"syntology":null},{"url":"/paper/multi-stage-speech-bandwidth-extension-with","title":"Multi-Stage Speech Bandwidth Extension with Flexible Sampling Rate Control","date":"2024-06-04","arxiv_id":"2406.02250","repositories_listed":1,"syntology":{"n":14,"n_ran":14,"n_unverified":0,"n_pointer_only":0}},{"url":"/paper/a-diffusion-based-generative-equalizer-for","title":"A Diffusion-Based Generative Equalizer for Music Restoration","date":"2024-03-27","arxiv_id":"2403.18636","repositories_listed":1,"syntology":{"n":9,"n_ran":8,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/explicit-estimation-of-magnitude-and-phase","title":"Explicit Estimation of Magnitude and Phase Spectra in Parallel for High-Quality Speech Enhancement","date":"2023-08-17","arxiv_id":"2308.08926","repositories_listed":1,"syntology":{"n":14,"n_ran":13,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/configurable-eben-extreme-bandwidth-extension","title":"Configurable EBEN: Extreme Bandwidth Extension Network to enhance body-conducted speech capture","date":"2023-03-17","arxiv_id":"2303.10008","repositories_listed":1,"syntology":null},{"url":"/paper/aero-audio-super-resolution-in-the-spectral","title":"AERO: Audio Super Resolution in the Spectral Domain","date":"2022-11-22","arxiv_id":"2211.12232","repositories_listed":1,"syntology":{"n":8,"n_ran":0,"n_unverified":8,"n_pointer_only":0}},{"url":"/paper/analysing-diffusion-based-generative","title":"Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration","date":"2022-11-04","arxiv_id":"2211.02397","repositories_listed":1,"syntology":null},{"url":"/paper/solving-audio-inverse-problems-with-a","title":"Solving Audio Inverse Problems with a Diffusion Model","date":"2022-10-27","arxiv_id":"2210.15228","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":0}},{"url":"/paper/behm-gan-bandwidth-extension-of-historical","title":"BEHM-GAN: Bandwidth Extension of Historical Music using Generative Adversarial Networks","date":"2022-04-13","arxiv_id":"2204.06478","repositories_listed":1,"syntology":{"n":1,"n_ran":0,"n_unverified":1,"n_pointer_only":1}},{"url":"/paper/neural-vocoder-is-all-you-need-for-speech","title":"Neural Vocoder is All You Need for Speech Super-resolution","date":"2022-03-28","arxiv_id":"2203.14941","repositories_listed":1,"syntology":null},{"url":"/paper/tunet-a-block-online-bandwidth-extension","title":"TUNet: A Block-online Bandwidth Extension Model based on Transformers and Self-supervised Pretraining","date":"2021-10-26","arxiv_id":"2110.13492","repositories_listed":1,"syntology":null},{"url":"/paper/wavenet-based-low-rate-speech-coding","title":"Wavenet based low rate speech coding","date":"2017-12-01","arxiv_id":"1712.01120","repositories_listed":1,"syntology":null},{"url":"/paper/super-resolution-with-deep-convolutional","title":"Super-Resolution with Deep Convolutional Sufficient Statistics","date":"2015-11-18","arxiv_id":"1511.05666","repositories_listed":1,"syntology":null}],"syntology_records":8,"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"}}