{"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/7","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":7,"pages_in_order":10,"rows_per_page":100,"rows":[601,700],"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/6","next":"/task/speech-enhancement/papers/8","papers":[{"url":null,"slug":"time-domain-speech-enhancement-for-robust","title":"Time-Domain Speech Enhancement for Robust Automatic Speech Recognition","date":"2022-10-24","arxiv_id":"2210.13318","repositories_listed":0,"syntology":null},{"url":null,"slug":"tridentse-guiding-speech-enhancement-with-32","title":"TridentSE: Guiding Speech Enhancement with 32 Global Tokens","date":"2022-10-24","arxiv_id":"2210.12995","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-normalizing-flow-based-speech","title":"Improved Normalizing Flow-Based Speech Enhancement using an All-pole Gammatone Filterbank for Conditional Input Representation","date":"2022-10-21","arxiv_id":"2210.11654","repositories_listed":0,"syntology":null},{"url":null,"slug":"spatial-dccrn-dccrn-equipped-with-frame-level","title":"spatial-dccrn: dccrn equipped with frame-level angle feature and hybrid filtering for multi-channel speech enhancement","date":"2022-10-17","arxiv_id":"2210.08802","repositories_listed":0,"syntology":null},{"url":null,"slug":"accelerating-rnn-based-speech-enhancement-on","title":"Accelerating RNN-based Speech Enhancement on a Multi-Core MCU with Mixed FP16-INT8 Post-Training Quantization","date":"2022-10-14","arxiv_id":"2210.07692","repositories_listed":0,"syntology":null},{"url":null,"slug":"levoice-asr-systems-for-the-iscslp-2022","title":"LeVoice ASR Systems for the ISCSLP 2022 Intelligent Cockpit Speech Recognition Challenge","date":"2022-10-14","arxiv_id":"2210.07749","repositories_listed":0,"syntology":null},{"url":null,"slug":"binaural-speech-enhancement-using-stoi","title":"Binaural Speech Enhancement Using STOI-Optimal Masks","date":"2022-09-30","arxiv_id":"2209.15472","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-self-supervised-pre","title":"Speech Enhancement Using Self-Supervised Pre-Trained Model and Vector Quantization","date":"2022-09-28","arxiv_id":"2209.14150","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-with-perceptually","title":"Speech Enhancement with Perceptually-motivated Optimization and Dual Transformations","date":"2022-09-24","arxiv_id":"2209.11905","repositories_listed":0,"syntology":null},{"url":null,"slug":"gist-aiter-system-for-the-diarization-task-of","title":"GIST-AiTeR System for the Diarization Task of the 2022 VoxCeleb Speaker Recognition Challenge","date":"2022-09-21","arxiv_id":"2209.10357","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-universally-deployable-asr-frontend-for","title":"A Universally-Deployable ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement, and Voice Separation","date":"2022-09-14","arxiv_id":"2209.06410","repositories_listed":0,"syntology":null},{"url":null,"slug":"multimodal-speech-enhancement-using-burst","title":"Multimodal Speech Enhancement Using Burst Propagation","date":"2022-09-07","arxiv_id":"2209.03275","repositories_listed":0,"syntology":null},{"url":"/paper/multi-view-attention-transfer-for-efficient","slug":"multi-view-attention-transfer-for-efficient","title":"Multi-View Attention Transfer for Efficient Speech Enhancement","date":"2022-08-22","arxiv_id":"2208.10367","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-free-low-latency-adaptive-speech","title":"DNN-Free Low-Latency Adaptive Speech Enhancement Based on Frame-Online Beamforming Powered by Block-Online FastMNMF","date":"2022-07-22","arxiv_id":"2207.10934","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-spatial-cues-for-hearables-using-a","title":"Improving spatial cues for hearables using a parameterized binaural CDR estimator","date":"2022-07-17","arxiv_id":"2207.08314","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-target-speech-enhancement-based","title":"Multi-channel target speech enhancement based on ERB-scaled spatial coherence features","date":"2022-07-17","arxiv_id":"2207.08126","repositories_listed":0,"syntology":null},{"url":"/paper/direction-aware-joint-adaptation-of-neural","slug":"direction-aware-joint-adaptation-of-neural","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","date":"2022-07-15","arxiv_id":"2207.07273","repositories_listed":0,"syntology":null},{"url":null,"slug":"gld-net-improving-monaural-speech-enhancement","title":"GLD-Net: Improving Monaural Speech Enhancement by Learning Global and Local Dependency Features with GLD Block","date":"2022-06-30","arxiv_id":"2206.14962","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-visual-speech-enhancement-network","title":"Improving Visual Speech Enhancement Network by Learning Audio-visual Affinity with Multi-head Attention","date":"2022-06-30","arxiv_id":"2206.14964","repositories_listed":0,"syntology":null},{"url":null,"slug":"challenges-and-opportunities-in-multi-device","title":"Challenges and Opportunities in Multi-device Speech Processing","date":"2022-06-27","arxiv_id":"2206.15432","repositories_listed":0,"syntology":null},{"url":null,"slug":"saqam-spatial-audio-quality-assessment-metric","title":"SAQAM: Spatial Audio Quality Assessment Metric","date":"2022-06-24","arxiv_id":"2206.12297","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-transformer-based-speech","title":"Efficient Transformer-based Speech Enhancement Using Long Frames and STFT Magnitudes","date":"2022-06-23","arxiv_id":"2206.11703","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-channel-end-to-end-neural-network-for","title":"Multi-channel end-to-end neural network for speech enhancement, source localization, and voice activity detection","date":"2022-06-20","arxiv_id":"2206.09728","repositories_listed":0,"syntology":null},{"url":"/paper/0-1-deep-neural-networks-via-block-coordinate","slug":"0-1-deep-neural-networks-via-block-coordinate","title":"0/1 Deep Neural Networks via Block Coordinate Descent","date":"2022-06-19","arxiv_id":"2206.09379","repositories_listed":0,"syntology":null},{"url":null,"slug":"nastar-noise-adaptive-speech-enhancement-with","title":"NASTAR: Noise Adaptive Speech Enhancement with Target-Conditional Resampling","date":"2022-06-18","arxiv_id":"2206.09058","repositories_listed":0,"syntology":null},{"url":null,"slug":"epg2s-speech-generation-and-speech","title":"EPG2S: Speech Generation and Speech Enhancement based on Electropalatography and Audio Signals using Multimodal Learning","date":"2022-06-16","arxiv_id":"2206.07860","repositories_listed":0,"syntology":null},{"url":null,"slug":"to-dereverb-or-not-to-dereverb-perceptual","title":"To Dereverb Or Not to Dereverb? Perceptual Studies On Real-Time Dereverberation Targets","date":"2022-06-16","arxiv_id":"2206.07917","repositories_listed":0,"syntology":null},{"url":null,"slug":"canonical-cortical-graph-neural-networks-and","title":"Canonical Cortical Graph Neural Networks and its Application for Speech Enhancement in Audio-Visual Hearing Aids","date":"2022-06-06","arxiv_id":"2206.02671","repositories_listed":0,"syntology":null},{"url":null,"slug":"far-field-speaker-recognition-benchmark","title":"Far-Field Speaker Recognition Benchmark Derived From The DiPCo Corpus","date":"2022-06-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-training-of-speech-enhancement-and-self","title":"Joint Training of Speech Enhancement and Self-supervised Model for Noise-robust ASR","date":"2022-05-26","arxiv_id":"2205.13293","repositories_listed":0,"syntology":null},{"url":null,"slug":"neuralecho-a-self-attentive-recurrent-neural","title":"NeuralEcho: A Self-Attentive Recurrent Neural Network For Unified Acoustic Echo Suppression And Speech Enhancement","date":"2022-05-20","arxiv_id":"2205.10401","repositories_listed":0,"syntology":null},{"url":null,"slug":"dictionary-based-fusion-of-contact-and","title":"Dictionary-Based Fusion of Contact and Acoustic Microphones for Wind Noise Reduction","date":"2022-05-18","arxiv_id":"2205.09017","repositories_listed":0,"syntology":null},{"url":null,"slug":"streaming-noise-context-aware-enhancement-for","title":"Streaming Noise Context Aware Enhancement For Automatic Speech Recognition in Multi-Talker Environments","date":"2022-05-17","arxiv_id":"2205.08555","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-splitting-for-dnn-based-acoustic-echo","title":"Task splitting for DNN-based acoustic echo and noise removal","date":"2022-05-13","arxiv_id":"2205.06931","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-deep-representation-learning-speech","title":"A deep representation learning speech enhancement method using $β$-VAE","date":"2022-05-11","arxiv_id":"2205.05581","repositories_listed":0,"syntology":null},{"url":null,"slug":"generalized-fast-multichannel-nonnegative","title":"Generalized Fast Multichannel Nonnegative Matrix Factorization Based on Gaussian Scale Mixtures for Blind Source Separation","date":"2022-05-11","arxiv_id":"2205.05330","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-reinforcement-using-target-source","title":"Speaker Reinforcement Using Target Source Extraction for Robust Automatic Speech Recognition","date":"2022-05-09","arxiv_id":"2205.04433","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-echo-suppression-using-a-learning","title":"Acoustic echo suppression using a learning-based multi-frame minimum variance distortionless response filter","date":"2022-05-07","arxiv_id":"2205.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-dual-microphone-speech-enhancement","title":"Improving Dual-Microphone Speech Enhancement by Learning Cross-Channel Features with Multi-Head Attention","date":"2022-05-03","arxiv_id":"2205.01280","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-monoaural-speech-enhancement-for-automatic","title":"On monoaural speech enhancement for automatic recognition of real noisy speech using mixture invariant training","date":"2022-05-03","arxiv_id":"2205.01751","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-meeting-transcription-system-for-an-ad-hoc","title":"A Meeting Transcription System for an Ad-Hoc Acoustic Sensor Network","date":"2022-05-02","arxiv_id":"2205.00944","repositories_listed":0,"syntology":null},{"url":null,"slug":"improved-far-field-speech-recognition-using","title":"Improved far-field speech recognition using Joint Variational Autoencoder","date":"2022-04-24","arxiv_id":"2204.11286","repositories_listed":0,"syntology":null},{"url":null,"slug":"radioses-mmwave-based-audioradio-speech","title":"RadioSES: mmWave-Based Audioradio Speech Enhancement and Separation System","date":"2022-04-14","arxiv_id":"2204.07092","repositories_listed":0,"syntology":null},{"url":null,"slug":"listen-only-to-me-how-well-can-target-speech","title":"Listen only to me! How well can target speech extraction handle false alarms?","date":"2022-04-11","arxiv_id":"2204.04811","repositories_listed":0,"syntology":null},{"url":null,"slug":"expression-preserving-face-frontalization","title":"Expression-preserving face frontalization improves visually assisted speech processing","date":"2022-04-06","arxiv_id":"2204.02810","repositories_listed":0,"syntology":null},{"url":null,"slug":"ffc-se-fast-fourier-convolution-for-speech","title":"FFC-SE: Fast Fourier Convolution for Speech Enhancement","date":"2022-04-06","arxiv_id":"2204.03042","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-multi-channel-speech-separation","title":"Audio-visual multi-channel speech separation, dereverberation and recognition","date":"2022-04-05","arxiv_id":"2204.01977","repositories_listed":0,"syntology":null},{"url":null,"slug":"fast-real-time-personalized-speech","title":"Fast Real-time Personalized Speech Enhancement: End-to-End Enhancement Network (E3Net) and Knowledge Distillation","date":"2022-04-02","arxiv_id":"2204.00771","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-integration-of-speech-recognition","title":"End-to-End Integration of Speech Recognition, Speech Enhancement, and Self-Supervised Learning Representation","date":"2022-04-01","arxiv_id":"2204.00540","repositories_listed":0,"syntology":null},{"url":null,"slug":"multiple-confidence-gates-for-joint-training","title":"Multiple Confidence Gates For Joint Training Of SE And ASR","date":"2022-04-01","arxiv_id":"2204.00226","repositories_listed":0,"syntology":null},{"url":null,"slug":"specgrad-diffusion-probabilistic-model-based","title":"SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping","date":"2022-03-31","arxiv_id":"2203.16749","repositories_listed":0,"syntology":null},{"url":null,"slug":"phase-aware-deep-speech-enhancement-it-s-all","title":"Phase-Aware Deep Speech Enhancement: It's All About The Frame Length","date":"2022-03-30","arxiv_id":"2203.16222","repositories_listed":0,"syntology":null},{"url":null,"slug":"metricgan-increasing-robustness-of-noise","title":"MetricGAN+/-: Increasing Robustness of Noise Reduction on Unseen Data","date":"2022-03-23","arxiv_id":"2203.12369","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-noise-reduction-and-listening","title":"Joint Noise Reduction and Listening Enhancement for Full-End Speech Enhancement","date":"2022-03-22","arxiv_id":"2203.11500","repositories_listed":0,"syntology":null},{"url":null,"slug":"fb-mstcn-a-full-band-single-channel-speech","title":"FB-MSTCN: A Full-Band Single-Channel Speech Enhancement Method Based on Multi-Scale Temporal Convolutional Network","date":"2022-03-15","arxiv_id":"2203.07684","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-self-supervised-learning-for","title":"Investigating self-supervised learning for speech enhancement and separation","date":"2022-03-15","arxiv_id":"2203.07960","repositories_listed":0,"syntology":null},{"url":null,"slug":"integrating-statistical-uncertainty-into","title":"Integrating Statistical Uncertainty into Neural Network-Based Speech Enhancement","date":"2022-03-04","arxiv_id":"2203.02288","repositories_listed":0,"syntology":null},{"url":null,"slug":"percepnet-a-phase-and-snr-aware-percepnet-for","title":"PercepNet+: A Phase and SNR Aware PercepNet for Real-Time Speech Enhancement","date":"2022-03-04","arxiv_id":"2203.02263","repositories_listed":0,"syntology":null},{"url":null,"slug":"phase-continuity-learning-derivatives-of","title":"Phase Continuity: Learning Derivatives of Phase Spectrum for Speech Enhancement","date":"2022-02-24","arxiv_id":"2202.11918","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-low-distortion-multi-channel-speech","title":"Towards Low-distortion Multi-channel Speech Enhancement: The ESPNet-SE Submission to The L3DAS22 Challenge","date":"2022-02-24","arxiv_id":"2202.12298","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-pcg-aiid-system-for-l3das22-challenge","title":"The PCG-AIID System for L3DAS22 Challenge: MIMO and MISO convolutional recurrent Network for Multi Channel Speech Enhancement and Speech Recognition","date":"2022-02-21","arxiv_id":"2202.10017","repositories_listed":0,"syntology":null},{"url":null,"slug":"emgse-acoustic-emg-fusion-for-multimodal","title":"EMGSE: Acoustic/EMG Fusion for Multimodal Speech Enhancement","date":"2022-02-14","arxiv_id":"2202.06507","repositories_listed":0,"syntology":null},{"url":null,"slug":"low-latency-monaural-speech-enhancement-with","title":"Low-latency Monaural Speech Enhancement with Deep Filter-bank Equalizer","date":"2022-02-14","arxiv_id":"2202.06764","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-novel-speech-intelligibility-enhancement","title":"A Novel Speech Intelligibility Enhancement Model based on CanonicalCorrelation and Deep Learning","date":"2022-02-11","arxiv_id":"2202.05756","repositories_listed":0,"syntology":null},{"url":null,"slug":"royalflush-speaker-diarization-system-for","title":"Royalflush Speaker Diarization System for ICASSP 2022 Multi-channel Multi-party Meeting Transcription Challenge","date":"2022-02-10","arxiv_id":"2202.04814","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-multimodal-canonical-correlated-graph","title":"Multimodal Audio-Visual Information Fusion using Canonical-Correlated Graph Neural Network for Energy-Efficient Speech Enhancement","date":"2022-02-09","arxiv_id":"2202.04528","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-speech-intelligibility-enhancement-model","title":"A Speech Intelligibility Enhancement Model based on Canonical Correlation and Deep Learning for Hearing-Assistive Technologies","date":"2022-02-08","arxiv_id":"2202.04172","repositories_listed":0,"syntology":null},{"url":null,"slug":"optimization-of-a-real-time-wavelet-based","title":"Optimization of a Real-Time Wavelet-Based Algorithm for Improving Speech Intelligibility","date":"2022-02-05","arxiv_id":"2202.02545","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-speech-recognition-and-audio-captioning","title":"Joint Speech Recognition and Audio Captioning","date":"2022-02-03","arxiv_id":"2202.01405","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-royalflush-system-of-speech-recognition","title":"The RoyalFlush System of Speech Recognition for M2MeT Challenge","date":"2022-02-03","arxiv_id":"2202.01614","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-impact-of-removing-head-movements-on","title":"The impact of removing head movements on audio-visual speech enhancement","date":"2022-02-01","arxiv_id":"2202.00538","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-two-step-backward-compatible-fullband","title":"A two-step backward compatible fullband speech enhancement system","date":"2022-01-26","arxiv_id":"2201.10809","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-bayesian-permutation-training-deep","title":"A Bayesian Permutation training deep representation learning method for speech enhancement with variational autoencoder","date":"2022-01-24","arxiv_id":"2201.09875","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-neural-audio-coding-for-real-time","title":"End-to-End Neural Speech Coding for Real-Time Communications","date":"2022-01-24","arxiv_id":"2201.09429","repositories_listed":0,"syntology":null},{"url":null,"slug":"how-bad-are-artifacts-analyzing-the-impact-of","title":"How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR","date":"2022-01-18","arxiv_id":"2201.06685","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-to-enhance-or-not-neural-network","title":"Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition","date":"2022-01-11","arxiv_id":"2201.03881","repositories_listed":0,"syntology":null},{"url":null,"slug":"signal-aware-direction-of-arrival-estimation","title":"Signal-Aware Direction-of-Arrival Estimation Using Attention Mechanisms","date":"2022-01-03","arxiv_id":"2201.00503","repositories_listed":0,"syntology":null},{"url":null,"slug":"tfcn-temporal-frequential-convolutional","title":"TFCN: Temporal-Frequential Convolutional Network for Single-Channel Speech Enhancement","date":"2022-01-03","arxiv_id":"2201.00480","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-real-time-audio-visual-speech","title":"Towards Robust Real-time Audio-Visual Speech Enhancement","date":"2021-12-16","arxiv_id":"2112.09060","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-speech-recognition-on-noisy-speech","title":"Improving Speech Recognition on Noisy Speech via Speech Enhancement with Multi-Discriminators CycleGAN","date":"2021-12-12","arxiv_id":"2112.06309","repositories_listed":0,"syntology":null},{"url":null,"slug":"learning-based-personal-speech-enhancement","title":"Learning-based personal speech enhancement for teleconferencing by exploiting spatial-spectral features","date":"2021-12-10","arxiv_id":"2112.05686","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-training-framework-for-stereo-aware-speech","title":"A Training Framework for Stereo-Aware Speech Enhancement using Deep Neural Networks","date":"2021-12-09","arxiv_id":"2112.04939","repositories_listed":0,"syntology":null},{"url":null,"slug":"harmonic-and-non-harmonic-based-noisy","title":"Harmonic and non-Harmonic Based Noisy Reverberant Speech Enhancement in Time Domain","date":"2021-12-09","arxiv_id":"2112.04949","repositories_listed":0,"syntology":null},{"url":null,"slug":"shi-yong-di-tong-shi-xu-lie-yu-yin-te-zheng","title":"使用低通時序列語音特徵訓練理想比率遮罩法之語音強化 (Employing Low-Pass Filtered Temporal Speech Features for the Training of Ideal Ratio Mask in Speech Enhancement)","date":"2021-12-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dataset-of-spatial-room-impulse-responses-in","title":"Dataset of Spatial Room Impulse Responses in a Variable Acoustics Room for Six Degrees-of-Freedom Rendering and Analysis","date":"2021-11-23","arxiv_id":"2111.11882","repositories_listed":0,"syntology":null},{"url":null,"slug":"effect-of-noise-suppression-losses-on-speech","title":"Effect of noise suppression losses on speech distortion and ASR performance","date":"2021-11-23","arxiv_id":"2111.11606","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-conformer-based-asr-frontend-for-joint","title":"A Conformer-based ASR Frontend for Joint Acoustic Echo Cancellation, Speech Enhancement and Speech Separation","date":"2021-11-18","arxiv_id":"2111.09935","repositories_listed":0,"syntology":null},{"url":null,"slug":"s-dccrn-super-wide-band-dccrn-with-learnable","title":"S-DCCRN: Super Wide Band DCCRN with learnable complex feature for speech enhancement","date":"2021-11-16","arxiv_id":"2111.08387","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-enhancement-with-speech","title":"Unsupervised Speech Enhancement with speech recognition embedding and disentanglement losses","date":"2021-11-16","arxiv_id":"2111.08678","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-far-and-near-end-speech-intelligibility","title":"Joint Far- and Near-End Speech Intelligibility Enhancement based on the Approximated Speech Intelligibility Index","date":"2021-11-15","arxiv_id":"2111.07759","repositories_listed":0,"syntology":null},{"url":null,"slug":"ossem-one-shot-speaker-adaptive-speech","title":"OSSEM: one-shot speaker adaptive speech enhancement using meta learning","date":"2021-11-10","arxiv_id":"2111.05703","repositories_listed":0,"syntology":null},{"url":"/paper/inter-channel-conv-tasnet-for-multichannel","slug":"inter-channel-conv-tasnet-for-multichannel","title":"Inter-channel Conv-TasNet for multichannel speech enhancement","date":"2021-11-08","arxiv_id":"2111.04312","repositories_listed":0,"syntology":null},{"url":null,"slug":"seofp-net-compression-and-acceleration-of","title":"SEOFP-NET: Compression and Acceleration of Deep Neural Networks for Speech Enhancement Using Sign-Exponent-Only Floating-Points","date":"2021-11-08","arxiv_id":"2111.04436","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-noise-suppression-maximizing-non","title":"Deep Noise Suppression Maximizing Non-Differentiable PESQ Mediated by a Non-Intrusive PESQNet","date":"2021-11-06","arxiv_id":"2111.03847","repositories_listed":0,"syntology":null},{"url":null,"slug":"weight-block-or-unit-exploring-sparsity","title":"Weight, Block or Unit? Exploring Sparsity Tradeoffs for Speech Enhancement on Tiny Neural Accelerators","date":"2021-11-03","arxiv_id":"2111.02351","repositories_listed":0,"syntology":null},{"url":null,"slug":"reduction-of-subjective-listening-effort-for","title":"Reduction of Subjective Listening Effort for TV Broadcast Signals with Recurrent Neural Networks","date":"2021-11-02","arxiv_id":"2111.01914","repositories_listed":0,"syntology":null},{"url":null,"slug":"snri-target-training-for-joint-speech","title":"SNRi Target Training for Joint Speech Enhancement and Recognition","date":"2021-11-01","arxiv_id":"2111.00764","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-attention-conformer-for-context","title":"Cross-attention conformer for context modeling in speech enhancement for ASR","date":"2021-10-30","arxiv_id":"2111.00127","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robustness-of-contrastive","title":"Improving Noise Robustness of Contrastive Speech Representation Learning with Speech Reconstruction","date":"2021-10-28","arxiv_id":"2110.15430","repositories_listed":0,"syntology":null},{"url":null,"slug":"closing-the-gap-between-time-domain-multi","title":"Closing the Gap Between Time-Domain Multi-Channel Speech Enhancement on Real and Simulation Conditions","date":"2021-10-27","arxiv_id":"2110.14139","repositories_listed":0,"syntology":null}],"record_sha256":"5f6d4dc656cd04ac5fa8dd1e7aafffe35c51a1bf508cd4d24d8a302c55b3b183","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}