{"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":"/task/speech-enhancement/papers/3","list_of":"/task/speech-enhancement","task":"Speech Enhancement","archive":{"snapshot":"2025-07-28"},"key_notes":{"n_ran_checked":"legacy name, kept unchanged so existing readers do not break: it counts the samples that ran with no instrument failure (honoured, violated, and ran with no contract checked); it does not mean a contract was checked, and the pages print it as 'K with no instrument failure', not 'K checked'","n_constructed":"a sub-count of the samples that ran, never subtracted from them and never a failure: an executed sample whose run returned an instance of its own class (fixture_out_type equals the entry name): the run built an object and did not compute a result (Syntology's RAN record, counts.constructed)"},"syntology_read_at":"2026-09-28T10:30:06+00:00","order":"archive","order_definition":"repositories listed in the archive (most first), then date (newest first), then slug","page":3,"pages_in_order":10,"rows_per_page":100,"rows":[201,300],"of":982,"counts":{"archive_papers_tagged":982,"with_a_code_link":280,"where_syntology_ran_a_sample":54,"not_listed_spam_title":0,"listed":982,"listed_where_code_ran":54,"where_syntology_ran_a_sample_split":{"with_a_run_with_no_instrument_failure":45,"every_run_a_failure_of_syntologys_instrument":9,"listed_with_a_run_with_no_instrument_failure":45,"listed_every_run_a_failure_of_syntologys_instrument":9,"filter":{"states":["a run with no instrument failure","any run, instrument failures included"],"default":"a run with no instrument failure","note":"on the 'only where code ran' pages the default hides, in the browser, the rows where every run was a failure of Syntology's instrument; the second state shows them again. Rows are hidden, never re-ordered; these twins list every row"}},"definition":"distinct papers the archive tags; 'where Syntology ran a sample' counts papers with at least one harvested sample that ran, which is not a correctness claim"},"first_page":"/task/speech-enhancement","prev":"/task/speech-enhancement/papers/2","next":"/task/speech-enhancement/papers/4","papers":[{"url":"/paper/aura-privacy-preserving-augmentation-to","slug":"aura-privacy-preserving-augmentation-to","title":"Aura: Privacy-preserving Augmentation to Improve Test Set Diversity in Speech Enhancement","date":"2021-10-08","arxiv_id":"2110.04391","repositories_listed":1,"syntology":null},{"url":"/paper/pl-eesr-perceptual-loss-based-end-to-end","slug":"pl-eesr-perceptual-loss-based-end-to-end","title":"PL-EESR: Perceptual Loss Based END-TO-END Robust Speaker Representation Extraction","date":"2021-10-03","arxiv_id":"2110.00940","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":0,"n_instrument":1,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 0 with no instrument failure: 0 honoured, 0 violated, 0 with no contract checked; 1 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/pl-eesr-perceptual-loss-based-end-to-end#ran","syntology_url":"https://syntology.ai/paper/2110.00940","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2110.00940"}},"official":{"repos":["mmmmayi/pl-eesr"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":0,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/masks-fusion-with-multi-target-learning-for","slug":"masks-fusion-with-multi-target-learning-for","title":"Masks Fusion with Multi-Target Learning For Speech Enhancement","date":"2021-09-23","arxiv_id":"2109.11164","repositories_listed":1,"syntology":null},{"url":"/paper/noresqa-a-framework-for-speech-quality","slug":"noresqa-a-framework-for-speech-quality","title":"NORESQA: A Framework for Speech Quality Assessment using Non-Matching References","date":"2021-09-16","arxiv_id":"2109.08125","repositories_listed":1,"syntology":null},{"url":"/paper/a-deep-learning-loss-function-based-on","slug":"a-deep-learning-loss-function-based-on","title":"A Deep Learning Loss Function based on Auditory Power Compression for Speech Enhancement","date":"2021-08-26","arxiv_id":"2108.11877","repositories_listed":1,"syntology":null},{"url":"/paper/complex-valued-spatial-autoencoders-for","slug":"complex-valued-spatial-autoencoders-for","title":"Complex-valued Spatial Autoencoders for Multichannel Speech Enhancement","date":"2021-08-06","arxiv_id":"2108.03130","repositories_listed":1,"syntology":null},{"url":"/paper/microphone-array-generalization-for","slug":"microphone-array-generalization-for","title":"Microphone Array Generalization for Multichannel Narrowband Deep Speech Enhancement","date":"2021-07-27","arxiv_id":"2107.12601","repositories_listed":1,"syntology":null},{"url":"/paper/a-study-on-speech-enhancement-based-on","slug":"a-study-on-speech-enhancement-based-on","title":"A Study on Speech Enhancement Based on Diffusion Probabilistic Model","date":"2021-07-25","arxiv_id":"2107.11876","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":1,"n_violates":0,"n_no_contract":0,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 1 honoured, 0 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/a-study-on-speech-enhancement-based-on#ran","syntology_url":"https://syntology.ai/paper/2107.11876","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2107.11876"}},"official":null}},{"url":"/paper/multi-task-audio-source-separation","slug":"multi-task-audio-source-separation","title":"Multi-Task Audio Source Separation","date":"2021-07-14","arxiv_id":"2107.06467","repositories_listed":1,"syntology":null},{"url":"/paper/easycom-an-augmented-reality-dataset-to","slug":"easycom-an-augmented-reality-dataset-to","title":"EasyCom: An Augmented Reality Dataset to Support Algorithms for Easy Communication in Noisy Environments","date":"2021-07-09","arxiv_id":"2107.04174","repositories_listed":1,"syntology":null},{"url":"/paper/tenet-a-time-reversal-enhancement-network-for","slug":"tenet-a-time-reversal-enhancement-network-for","title":"TENET: A Time-reversal Enhancement Network for Noise-robust ASR","date":"2021-07-04","arxiv_id":"2107.01531","repositories_listed":1,"syntology":null},{"url":"/paper/unsupervised-speech-enhancement-using","slug":"unsupervised-speech-enhancement-using","title":"Unsupervised Speech Enhancement using Dynamical Variational Auto-Encoders","date":"2021-06-23","arxiv_id":"2106.12271","repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-distributed-speech","slug":"attention-based-distributed-speech","title":"Attention-based distributed speech enhancement for unconstrained microphone arrays with varying number of nodes","date":"2021-06-15","arxiv_id":"2106.07939","repositories_listed":1,"syntology":null},{"url":"/paper/learning-audio-visual-dereverberation","slug":"learning-audio-visual-dereverberation","title":"Learning Audio-Visual Dereverberation","date":"2021-06-14","arxiv_id":"2106.07732","repositories_listed":1,"syntology":null},{"url":"/paper/disentanglement-learning-for-variational","slug":"disentanglement-learning-for-variational","title":"Disentanglement Learning for Variational Autoencoders Applied to Audio-Visual Speech Enhancement","date":"2021-05-19","arxiv_id":"2105.08970","repositories_listed":1,"syntology":null},{"url":"/paper/separate-but-together-unsupervised-federated","slug":"separate-but-together-unsupervised-federated","title":"Separate but Together: Unsupervised Federated Learning for Speech Enhancement from Non-IID Data","date":"2021-05-11","arxiv_id":"2105.04727","repositories_listed":1,"syntology":null},{"url":"/paper/l3das21-challenge-machine-learning-for-3d","slug":"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/interspeech-2021-conferencingspeech-challenge","slug":"interspeech-2021-conferencingspeech-challenge","title":"INTERSPEECH 2021 ConferencingSpeech Challenge: Towards Far-field Multi-Channel Speech Enhancement for Video Conferencing","date":"2021-04-02","arxiv_id":"2104.00960","repositories_listed":1,"syntology":null},{"url":"/paper/time-domain-speech-enhancement-with","slug":"time-domain-speech-enhancement-with","title":"Time-domain Speech Enhancement with Generative Adversarial Learning","date":"2021-03-30","arxiv_id":"2103.16149","repositories_listed":1,"syntology":null},{"url":"/paper/a-modulation-domain-loss-for-neural-network-1","slug":"a-modulation-domain-loss-for-neural-network-1","title":"A Modulation-Domain Loss for Neural-Network-based Real-time Speech Enhancement","date":"2021-02-15","arxiv_id":"2102.07330","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-of-end-to-end-models-for","slug":"an-investigation-of-end-to-end-models-for","title":"An Investigation of End-to-End Models for Robust Speech Recognition","date":"2021-02-11","arxiv_id":"2102.06237","repositories_listed":1,"syntology":null},{"url":"/paper/cdpam-contrastive-learning-for-perceptual","slug":"cdpam-contrastive-learning-for-perceptual","title":"CDPAM: Contrastive learning for perceptual audio similarity","date":"2021-02-09","arxiv_id":"2102.05109","repositories_listed":1,"syntology":null},{"url":"/paper/real-time-denoising-and-dereverberation-with","slug":"real-time-denoising-and-dereverberation-with","title":"Real-time Denoising and Dereverberation with Tiny Recurrent U-Net","date":"2021-02-05","arxiv_id":"2102.03207","repositories_listed":1,"syntology":null},{"url":"/paper/attention-based-multi-task-learning-for","slug":"attention-based-multi-task-learning-for","title":"Attention-based multi-task learning for speech-enhancement and speaker-identification in multi-speaker dialogue scenario","date":"2021-01-07","arxiv_id":"2101.02550","repositories_listed":1,"syntology":null},{"url":"/paper/visual-speech-enhancement-without-a-real","slug":"visual-speech-enhancement-without-a-real","title":"Visual Speech Enhancement Without A Real Visual Stream","date":"2020-12-20","arxiv_id":"2012.10852","repositories_listed":1,"syntology":null},{"url":"/paper/speech-enhancement-with-zero-shot-model","slug":"speech-enhancement-with-zero-shot-model","title":"Speech Enhancement with Zero-Shot Model Selection","date":"2020-12-17","arxiv_id":"2012.09359","repositories_listed":1,"syntology":null},{"url":"/paper/group-communication-with-context-codec-for","slug":"group-communication-with-context-codec-for","title":"Group Communication with Context Codec for Lightweight Source Separation","date":"2020-12-14","arxiv_id":"2012.07291","repositories_listed":1,"syntology":null},{"url":"/paper/speech-denoising-with-auditory-models","slug":"speech-denoising-with-auditory-models","title":"Speech Denoising with Auditory Models","date":"2020-11-21","arxiv_id":"2011.10706","repositories_listed":1,"syntology":null},{"url":"/paper/deep-multi-frame-mvdr-filtering-for-single","slug":"deep-multi-frame-mvdr-filtering-for-single","title":"Deep Multi-Frame MVDR Filtering for Single-Microphone Speech Enhancement","date":"2020-11-20","arxiv_id":"2011.10345","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-learning-from-contrastive","slug":"self-supervised-learning-from-contrastive","title":"Self-Supervised Learning from Contrastive Mixtures for Personalized Speech Enhancement","date":"2020-11-06","arxiv_id":"2011.03426","repositories_listed":1,"syntology":null},{"url":"/paper/dnn-based-mask-estimation-for-distributed","slug":"dnn-based-mask-estimation-for-distributed","title":"DNN-based mask estimation for distributed speech enhancement in spatially unconstrained microphone arrays","date":"2020-11-03","arxiv_id":"2011.01714","repositories_listed":1,"syntology":null},{"url":"/paper/self-supervised-pre-training-reduces-label","slug":"self-supervised-pre-training-reduces-label","title":"Stabilizing Label Assignment for Speech Separation by Self-supervised Pre-training","date":"2020-10-29","arxiv_id":"2010.15366","repositories_listed":1,"syntology":null},{"url":"/paper/improving-perceptual-quality-by-phone","slug":"improving-perceptual-quality-by-phone","title":"Improving Perceptual Quality by Phone-Fortified Perceptual Loss using Wasserstein Distance for Speech Enhancement","date":"2020-10-28","arxiv_id":"2010.15174","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/improving-perceptual-quality-by-phone#ran","syntology_url":"https://syntology.ai/paper/2010.15174","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2010.15174"}},"official":{"repos":["aleXiehta/PhoneFortifiedPerceptualLoss"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/self-attention-generative-adversarial-network","slug":"self-attention-generative-adversarial-network","title":"Self-Attention Generative Adversarial Network for Speech Enhancement","date":"2020-10-18","arxiv_id":"2010.09132","repositories_listed":1,"syntology":null},{"url":"/paper/seanet-a-multi-modal-speech-enhancement","slug":"seanet-a-multi-modal-speech-enhancement","title":"SEANet: A Multi-modal Speech Enhancement Network","date":"2020-09-04","arxiv_id":"2009.02095","repositories_listed":1,"syntology":null},{"url":"/paper/improved-lite-audio-visual-speech-enhancement","slug":"improved-lite-audio-visual-speech-enhancement","title":"Improved Lite Audio-Visual Speech Enhancement","date":"2020-08-30","arxiv_id":"2008.13222","repositories_listed":1,"syntology":null},{"url":"/paper/an-overview-of-deep-learning-based-audio","slug":"an-overview-of-deep-learning-based-audio","title":"An Overview of Deep-Learning-Based Audio-Visual Speech Enhancement and Separation","date":"2020-08-21","arxiv_id":"2008.09586","repositories_listed":1,"syntology":null},{"url":"/paper/citisen-a-deep-learning-based-speech-signal","slug":"citisen-a-deep-learning-based-speech-signal","title":"CITISEN: A Deep Learning-Based Speech Signal-Processing Mobile Application","date":"2020-08-21","arxiv_id":"2008.09264","repositories_listed":1,"syntology":null},{"url":"/paper/storir-stochastic-room-impulse-response","slug":"storir-stochastic-room-impulse-response","title":"StoRIR: Stochastic Room Impulse Response Generation for Audio Data Augmentation","date":"2020-08-17","arxiv_id":"2008.07231","repositories_listed":1,"syntology":null},{"url":"/paper/instantaneous-psd-estimation-for-speech","slug":"instantaneous-psd-estimation-for-speech","title":"Instantaneous PSD Estimation for Speech Enhancement based on Generalized Principal Components","date":"2020-07-01","arxiv_id":"2007.00542","repositories_listed":1,"syntology":null},{"url":"/paper/clc-complex-linear-coding-for-the-dns-2020","slug":"clc-complex-linear-coding-for-the-dns-2020","title":"CLC: Complex Linear Coding for the DNS 2020 Challenge","date":"2020-06-23","arxiv_id":"2006.13077","repositories_listed":1,"syntology":null},{"url":"/paper/hifi-gan-high-fidelity-denoising-and","slug":"hifi-gan-high-fidelity-denoising-and","title":"HiFi-GAN: High-Fidelity Denoising and Dereverberation Based on Speech Deep Features in Adversarial Networks","date":"2020-06-10","arxiv_id":"2006.05694","repositories_listed":1,"syntology":null},{"url":"/paper/a-fully-recurrent-feature-extraction-for-1","slug":"a-fully-recurrent-feature-extraction-for-1","title":"A fully recurrent feature extraction for single channel speech enhancement","date":"2020-06-09","arxiv_id":"2006.05233","repositories_listed":1,"syntology":null},{"url":"/paper/a-non-causal-fftnet-architecture-for-speech","slug":"a-non-causal-fftnet-architecture-for-speech","title":"A non-causal FFTNet architecture for speech enhancement","date":"2020-06-08","arxiv_id":"2006.04469","repositories_listed":1,"syntology":null},{"url":"/paper/phase-aware-single-stage-speech-denoising-and-1","slug":"phase-aware-single-stage-speech-denoising-and-1","title":"Phase-aware Single-stage Speech Denoising and Dereverberation with U-Net","date":"2020-06-01","arxiv_id":"2006.00687","repositories_listed":1,"syntology":null},{"url":"/paper/lite-audio-visual-speech-enhancement","slug":"lite-audio-visual-speech-enhancement","title":"Lite Audio-Visual Speech Enhancement","date":"2020-05-24","arxiv_id":"2005.11769","repositories_listed":1,"syntology":null},{"url":"/paper/seril-noise-adaptive-speech-enhancement-using","slug":"seril-noise-adaptive-speech-enhancement-using","title":"SERIL: Noise Adaptive Speech Enhancement using Regularization-based Incremental Learning","date":"2020-05-24","arxiv_id":"2005.11760","repositories_listed":1,"syntology":{"n":2,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":1,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 1 unverified","sample_list":"/paper/seril-noise-adaptive-speech-enhancement-using#ran","syntology_url":"https://syntology.ai/paper/2005.11760","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.11760"}},"official":{"repos":["ChangLee0903/SERIL"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":1,"ran_from_kinds":["official"]}}},{"url":"/paper/tinylstms-efficient-neural-speech-enhancement","slug":"tinylstms-efficient-neural-speech-enhancement","title":"TinyLSTMs: Efficient Neural Speech Enhancement for Hearing Aids","date":"2020-05-20","arxiv_id":"2005.11138","repositories_listed":1,"syntology":null},{"url":"/paper/sparse-mixture-of-local-experts-for-efficient","slug":"sparse-mixture-of-local-experts-for-efficient","title":"Sparse Mixture of Local Experts for Efficient Speech Enhancement","date":"2020-05-16","arxiv_id":"2005.08128","repositories_listed":1,"syntology":null},{"url":"/paper/the-interspeech-2020-deep-noise-suppression-1","slug":"the-interspeech-2020-deep-noise-suppression-1","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","date":"2020-05-16","arxiv_id":"2005.13981","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-interspeech-2020-deep-noise-suppression-1#ran","syntology_url":"https://syntology.ai/paper/2005.13981","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2005.13981"}},"official":{"repos":["microsoft/DNS-Challenge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/towards-a-competitive-end-to-end-speech","slug":"towards-a-competitive-end-to-end-speech","title":"Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription","date":"2020-04-22","arxiv_id":"2004.10799","repositories_listed":1,"syntology":null},{"url":"/paper/phonetic-feedback-for-speech-enhancement-with","slug":"phonetic-feedback-for-speech-enhancement-with","title":"Phonetic Feedback for Speech Enhancement With and Without Parallel Speech Data","date":"2020-03-03","arxiv_id":"2003.01769","repositories_listed":1,"syntology":null},{"url":"/paper/isegan-improved-speech-enhancement-generative","slug":"isegan-improved-speech-enhancement-generative","title":"iSEGAN: Improved Speech Enhancement Generative Adversarial Networks","date":"2020-02-20","arxiv_id":"2002.08796","repositories_listed":1,"syntology":null},{"url":"/paper/boosted-locality-sensitive-hashing","slug":"boosted-locality-sensitive-hashing","title":"Boosted Locality Sensitive Hashing: Discriminative Binary Codes for Source Separation","date":"2020-02-14","arxiv_id":"2002.06239","repositories_listed":1,"syntology":null},{"url":"/paper/channel-attention-dense-u-net-for","slug":"channel-attention-dense-u-net-for","title":"Channel-Attention Dense U-Net for Multichannel Speech Enhancement","date":"2020-01-30","arxiv_id":"2001.11542","repositories_listed":1,"syntology":null},{"url":"/paper/deep-xi-as-a-front-end-for-robust-automatic","slug":"deep-xi-as-a-front-end-for-robust-automatic","title":"Deep Xi as a Front-End for Robust Automatic Speech Recognition","date":"2020-01-28","arxiv_id":"1906.07319","repositories_listed":1,"syntology":null},{"url":"/paper/the-interspeech-2020-deep-noise-suppression","slug":"the-interspeech-2020-deep-noise-suppression","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Speech Quality and Testing Framework","date":"2020-01-23","arxiv_id":"2001.08662","repositories_listed":1,"syntology":{"n":1,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":0,"n_honours":0,"n_violates":1,"n_no_contract":0,"n_pointer_only":1,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 1 violated, 0 with no contract checked; 0 where Syntology's instrument failed) · 0 unverified","sample_list":"/paper/the-interspeech-2020-deep-noise-suppression#ran","syntology_url":"https://syntology.ai/paper/2001.08662","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2001.08662"}},"official":{"repos":["microsoft/DNS-Challenge"],"state":"official (archive's flag): 1 ran","n_ran":1,"n_constructed":0,"n_ran_no_instrument_failure":1,"n_unverified":0,"ran_from_kinds":["official"]}}},{"url":"/paper/a-differentiable-perceptual-audio-metric","slug":"a-differentiable-perceptual-audio-metric","title":"A Differentiable Perceptual Audio Metric Learned from Just Noticeable Differences","date":"2020-01-13","arxiv_id":"2001.04460","repositories_listed":1,"syntology":null},{"url":"/paper/speech-enhancement-based-on-denoising","slug":"speech-enhancement-based-on-denoising","title":"Speech Enhancement based on Denoising Autoencoder with Multi-branched Encoders","date":"2020-01-06","arxiv_id":"2001.01538","repositories_listed":1,"syntology":null},{"url":"/paper/mmtm-multimodal-transfer-module-for-cnn","slug":"mmtm-multimodal-transfer-module-for-cnn","title":"MMTM: Multimodal Transfer Module for CNN Fusion","date":"2019-11-20","arxiv_id":"1911.08670","repositories_listed":1,"syntology":{"n":3,"n_ran":1,"n_constructed":0,"n_ran_checked":1,"n_instrument":0,"n_unverified":2,"n_honours":0,"n_violates":0,"n_no_contract":1,"n_pointer_only":0,"phrase":"1 ran (of which 0 constructed an object rather than computing a result; 1 with no instrument failure: 0 honoured, 0 violated, 1 with no contract checked; 0 where Syntology's instrument failed) · 2 unverified","sample_list":"/paper/mmtm-multimodal-transfer-module-for-cnn#ran","syntology_url":"https://syntology.ai/paper/1911.08670","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"1911.08670"}},"official":null}},{"url":"/paper/what-does-a-network-layer-hear-analyzing","slug":"what-does-a-network-layer-hear-analyzing","title":"What does a network layer hear? Analyzing hidden representations of end-to-end ASR through speech synthesis","date":"2019-11-04","arxiv_id":"1911.01102","repositories_listed":1,"syntology":null},{"url":"/paper/feature-enhancement-with-deep-feature-losses","slug":"feature-enhancement-with-deep-feature-losses","title":"Feature Enhancement with Deep Feature Losses for Speaker Verification","date":"2019-10-25","arxiv_id":"1910.11905","repositories_listed":1,"syntology":null},{"url":"/paper/semi-supervised-multichannel-speech-1","slug":"semi-supervised-multichannel-speech-1","title":"Semi-Supervised Multichannel Speech Enhancement With a Deep Speech Prior","date":"2019-10-07","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/fasnet-low-latency-adaptive-beamforming-for","slug":"fasnet-low-latency-adaptive-beamforming-for","title":"FaSNet: Low-latency Adaptive Beamforming for Multi-microphone Audio Processing","date":"2019-09-29","arxiv_id":"1909.13387","repositories_listed":1,"syntology":null},{"url":"/paper/an-investigation-into-the-effectiveness-of","slug":"an-investigation-into-the-effectiveness-of","title":"An Investigation into the Effectiveness of Enhancement in ASR Training and Test for CHiME-5 Dinner Party Transcription","date":"2019-09-26","arxiv_id":"1909.12208","repositories_listed":1,"syntology":null},{"url":"/paper/deep-learning-for-minimum-mean-square-error","slug":"deep-learning-for-minimum-mean-square-error","title":"Deep learning for minimum mean-square error approaches to speech enhancement","date":"2019-08-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/the-second-dihard-diarization-challenge","slug":"the-second-dihard-diarization-challenge","title":"The Second DIHARD Diarization Challenge: Dataset, task, and baselines","date":"2019-06-18","arxiv_id":"1906.07839","repositories_listed":1,"syntology":null},{"url":"/paper/guided-source-separation-meets-a-strong-asr","slug":"guided-source-separation-meets-a-strong-asr","title":"Guided Source Separation Meets a Strong ASR Backend: Hitachi/Paderborn University Joint Investigation for Dinner Party ASR","date":"2019-05-29","arxiv_id":"1905.12230","repositories_listed":1,"syntology":null},{"url":"/paper/190509754","slug":"190509754","title":"A Perceptual Weighting Filter Loss for DNN Training in Speech Enhancement","date":"2019-05-23","arxiv_id":"1905.09754","repositories_listed":1,"syntology":null},{"url":"/paper/learning-with-learned-loss-function-speech","slug":"learning-with-learned-loss-function-speech","title":"Learning with Learned Loss Function: Speech Enhancement with Quality-Net to Improve Perceptual Evaluation of Speech Quality","date":"2019-05-06","arxiv_id":"1905.01898","repositories_listed":1,"syntology":null},{"url":"/paper/deep-complex-valued-neural-beamformers","slug":"deep-complex-valued-neural-beamformers","title":"DEEP COMPLEX-VALUED NEURAL BEAMFORMERS","date":"2019-05-01","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/a-variance-modeling-framework-based-on","slug":"a-variance-modeling-framework-based-on","title":"A variance modeling framework based on variational autoencoders for speech enhancement","date":"2019-02-05","arxiv_id":"1902.01605","repositories_listed":1,"syntology":null},{"url":"/paper/end-to-end-multi-task-denoising-for-joint-sdr","slug":"end-to-end-multi-task-denoising-for-joint-sdr","title":"End-to-End Multi-Task Denoising for joint SDR and PESQ Optimization","date":"2019-01-26","arxiv_id":"1901.09146","repositories_listed":1,"syntology":null},{"url":"/paper/speech-enhancement-based-on-reducing-the","slug":"speech-enhancement-based-on-reducing-the","title":"Speech Enhancement Based on Reducing the Detail Portion of Speech Spectrograms in Modulation Domain via Discrete Wavelet Transform","date":"2018-11-08","arxiv_id":"1811.03486","repositories_listed":1,"syntology":null},{"url":"/paper/face-landmark-based-speaker-independent-audio","slug":"face-landmark-based-speaker-independent-audio","title":"Face Landmark-based Speaker-Independent Audio-Visual Speech Enhancement in Multi-Talker Environments","date":"2018-11-06","arxiv_id":"1811.02480","repositories_listed":1,"syntology":null},{"url":"/paper/unpaired-speech-enhancement-by-acoustic-and","slug":"unpaired-speech-enhancement-by-acoustic-and","title":"Unpaired Speech Enhancement by Acoustic and Adversarial Supervision for Speech Recognition","date":"2018-11-06","arxiv_id":"1811.02182","repositories_listed":1,"syntology":null},{"url":"/paper/investigating-the-effect-of-residual-and","slug":"investigating-the-effect-of-residual-and","title":"Investigating the effect of residual and highway connections in speech enhancement models","date":"2018-10-22","arxiv_id":null,"repositories_listed":1,"syntology":null},{"url":"/paper/investigating-generative-adversarial-networks","slug":"investigating-generative-adversarial-networks","title":"Investigating Generative Adversarial Networks based Speech Dereverberation for Robust Speech Recognition","date":"2018-03-27","arxiv_id":"1803.10132","repositories_listed":1,"syntology":null},{"url":"/paper/contaminated-speech-training-methods-for","slug":"contaminated-speech-training-methods-for","title":"Contaminated speech training methods for robust DNN-HMM distant speech recognition","date":"2017-10-10","arxiv_id":"1710.03538","repositories_listed":1,"syntology":null},{"url":"/paper/supervised-and-unsupervised-speech","slug":"supervised-and-unsupervised-speech","title":"Supervised and Unsupervised Speech Enhancement Using Nonnegative Matrix Factorization","date":"2017-09-15","arxiv_id":"1709.05362","repositories_listed":1,"syntology":null},{"url":null,"slug":"autoregressive-speech-enhancement-via","title":"Autoregressive Speech Enhancement via Acoustic Tokens","date":"2025-07-17","arxiv_id":"2507.12825","repositories_listed":0,"syntology":null},{"url":null,"slug":"p-808-multilingual-speech-enhancement-testing","title":"P.808 Multilingual Speech Enhancement Testing: Approach and Results of URGENT 2025 Challenge","date":"2025-07-15","arxiv_id":"2507.11306","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-quality-assessment-model-based-on","title":"Speech Quality Assessment Model Based on Mixture of Experts: System-Level Performance Enhancement and Utterance-Level Challenge Analysis","date":"2025-07-08","arxiv_id":"2507.06116","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-weighted-training-losses-for","title":"Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement","date":"2025-06-23","arxiv_id":"2506.18714","repositories_listed":0,"syntology":null},{"url":null,"slug":"ednet-a-distortion-agnostic-speech","title":"EDNet: A Distortion-Agnostic Speech Enhancement Framework with Gating Mamba Mechanism and Phase Shift-Invariant Training","date":"2025-06-19","arxiv_id":"2506.16231","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-comparative-evaluation-of-deep-learning-1","title":"A Comparative Evaluation of Deep Learning Models for Speech Enhancement in Real-World Noisy Environments","date":"2025-06-17","arxiv_id":"2506.15000","repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-length-generalization-for","title":"Exploring Length Generalization For Transformer-based Speech Enhancement","date":"2025-06-07","arxiv_id":"2506.06697","repositories_listed":0,"syntology":null},{"url":null,"slug":"french-listening-tests-for-the-assessment-of","title":"French Listening Tests for the Assessment of Intelligibility, Quality, and Identity of Body-Conducted Speech Enhancement","date":"2025-06-04","arxiv_id":"2506.04495","repositories_listed":0,"syntology":null},{"url":null,"slug":"diffusion-buffer-online-diffusion-based","title":"Diffusion Buffer: Online Diffusion-based Speech Enhancement with Sub-Second Latency","date":"2025-06-03","arxiv_id":"2506.02908","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-two-stage-hierarchical-deep-filtering","title":"A Two-Stage Hierarchical Deep Filtering Framework for Real-Time Speech Enhancement","date":"2025-06-01","arxiv_id":"2506.01023","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-composite-predictive-generative-approach-to","title":"A Composite Predictive-Generative Approach to Monaural Universal Speech Enhancement","date":"2025-05-30","arxiv_id":"2505.24576","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-domain-incremental-learning","title":"Boosting Domain Incremental Learning: Selecting the Optimal Parameters is All You Need","date":"2025-05-29","arxiv_id":"2505.23744","repositories_listed":0,"syntology":null},{"url":null,"slug":"deepfiltergan-a-full-band-real-time-speech","title":"DeepFilterGAN: A Full-band Real-time Speech Enhancement System with GAN-based Stochastic Regeneration","date":"2025-05-29","arxiv_id":"2505.23515","repositories_listed":0,"syntology":null},{"url":null,"slug":"interspeech-2025-urgent-speech-enhancement","title":"Interspeech 2025 URGENT Speech Enhancement Challenge","date":"2025-05-29","arxiv_id":"2505.23212","repositories_listed":0,"syntology":null},{"url":null,"slug":"arise-auto-regressive-multi-channel-speech","title":"ARiSE: Auto-Regressive Multi-Channel Speech Enhancement","date":"2025-05-28","arxiv_id":"2505.22051","repositories_listed":0,"syntology":null},{"url":null,"slug":"model-as-loss-a-self-consistent-training","title":"Model as Loss: A Self-Consistent Training Paradigm","date":"2025-05-27","arxiv_id":"2505.21156","repositories_listed":0,"syntology":null},{"url":null,"slug":"study-of-lightweight-transformer","title":"Study of Lightweight Transformer Architectures for Single-Channel Speech Enhancement","date":"2025-05-27","arxiv_id":"2505.21057","repositories_listed":0,"syntology":null},{"url":null,"slug":"stack-less-repeat-more-a-block-reusing","title":"Stack Less, Repeat More: A Block Reusing Approach for Progressive Speech Enhancement","date":"2025-05-26","arxiv_id":"2505.19401","repositories_listed":0,"syntology":null},{"url":null,"slug":"ts-urgenet-a-three-stage-universal-robust-and","title":"TS-URGENet: A Three-stage Universal Robust and Generalizable Speech Enhancement Network","date":"2025-05-24","arxiv_id":"2505.18533","repositories_listed":0,"syntology":null},{"url":null,"slug":"active-speech-enhancement-active-speech","title":"Active Speech Enhancement: Active Speech Denoising Decliping and Deveraberation","date":"2025-05-22","arxiv_id":"2505.16911","repositories_listed":0,"syntology":null}],"record_sha256":"3ab71b18b88733645e6f552ba1f6abf4d493c52e1a9b91eae38cbaf3bfd54eb6","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}