{"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/8","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":8,"pages_in_order":10,"rows_per_page":100,"rows":[701,800],"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/7","next":"/task/speech-enhancement/papers/9","papers":[{"url":null,"slug":"one-model-to-enhance-them-all-array-geometry","title":"One model to enhance them all: array geometry agnostic multi-channel personalized speech enhancement","date":"2021-10-20","arxiv_id":"2110.10330","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-assisted-stargan-voice","title":"Speech Enhancement-assisted Voice Conversion in Noisy Environments","date":"2021-10-19","arxiv_id":"2110.09923","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-based-on-cyclegan-with","title":"Speech Enhancement Based on Cyclegan with Noise-informed Training","date":"2021-10-19","arxiv_id":"2110.09924","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-speech-enhancement-new-models","title":"Personalized Speech Enhancement: New Models and Comprehensive Evaluation","date":"2021-10-18","arxiv_id":"2110.09625","repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-and-independence-aware-beamformer-1","title":"Similarity-and-Independence-Aware Beamformer with Iterative Casting and Boost Start for Target Source Extraction Using Reference","date":"2021-10-18","arxiv_id":"2110.09019","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-character-error-rate-is-not-equal","title":"Improving Character Error Rate Is Not Equal to Having Clean Speech: Speech Enhancement for ASR Systems with Black-box Acoustic Models","date":"2021-10-12","arxiv_id":"2110.05968","repositories_listed":0,"syntology":null},{"url":null,"slug":"wav2vec-switch-contrastive-learning-from","title":"Wav2vec-Switch: Contrastive Learning from Original-noisy Speech Pairs for Robust Speech Recognition","date":"2021-10-11","arxiv_id":"2110.04934","repositories_listed":0,"syntology":null},{"url":null,"slug":"lightweight-speech-enhancement-in-unseen","title":"Lightweight Speech Enhancement in Unseen Noisy and Reverberant Conditions using KISS-GEV Beamforming","date":"2021-10-06","arxiv_id":"2110.03103","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-complex-valued-multidilated","title":"End-to-End Complex-Valued Multidilated Convolutional Neural Network for Joint Acoustic Echo Cancellation and Noise Suppression","date":"2021-10-02","arxiv_id":"2110.00745","repositories_listed":0,"syntology":null},{"url":null,"slug":"employing-low-pass-filtered-temporal-speech","title":"Employing low-pass filtered temporal speech features for the training of ideal ratio mask in speech enhancement","date":"2021-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-mlp-a-simple-mlp-architecture-for","title":"Speech-MLP: a simple MLP architecture for speech processing","date":"2021-09-29","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"dds-a-new-device-degraded-speech-dataset-for","title":"DDS: A new device-degraded speech dataset for speech enhancement","date":"2021-09-16","arxiv_id":"2109.07931","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-real-world-noisy-speech-in","title":"Incorporating Real-world Noisy Speech in Neural-network-based Speech Enhancement Systems","date":"2021-09-11","arxiv_id":"2109.05172","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-alignment-using-lip-images-for-frame","title":"Time Alignment using Lip Images for Frame-based Electrolaryngeal Voice Conversion","date":"2021-09-08","arxiv_id":"2109.03551","repositories_listed":0,"syntology":null},{"url":null,"slug":"machine-learning-challenges-limitations-and","title":"Machine Learning: Challenges, Limitations, and Compatibility for Audio Restoration Processes","date":"2021-09-06","arxiv_id":"2109.02692","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-two-stage-complex-network-using-cycle","title":"A Two-stage Complex Network using Cycle-consistent Generative Adversarial Networks for Speech Enhancement","date":"2021-09-05","arxiv_id":"2109.02011","repositories_listed":0,"syntology":null},{"url":null,"slug":"full-attention-bidirectional-deep-learning","title":"Full Attention Bidirectional Deep Learning Structure for Single Channel Speech Enhancement","date":"2021-08-27","arxiv_id":"2108.12105","repositories_listed":0,"syntology":null},{"url":null,"slug":"task-aware-warping-factors-in-mask-based","title":"Task-aware Warping Factors in Mask-based Speech Enhancement","date":"2021-08-27","arxiv_id":"2108.12128","repositories_listed":0,"syntology":null},{"url":null,"slug":"cross-domain-single-channel-speech","title":"Cross-domain Single-channel Speech Enhancement Model with Bi-projection Fusion Module for Noise-robust ASR","date":"2021-08-26","arxiv_id":"2108.11598","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-residual-echo-suppression-and-noise","title":"Deep Residual Echo Suppression and Noise Reduction: A Multi-Input FCRN Approach in a Hybrid Speech Enhancement System","date":"2021-08-06","arxiv_id":"2108.03051","repositories_listed":0,"syntology":null},{"url":null,"slug":"inplace-gated-convolutional-recurrent-neural","title":"Inplace Gated Convolutional Recurrent Neural Network For Dual-channel Speech Enhancement","date":"2021-07-26","arxiv_id":"2107.11968","repositories_listed":0,"syntology":null},{"url":null,"slug":"controlling-the-perceived-sound-quality-for","title":"Controlling the Perceived Sound Quality for Dialogue Enhancement with Deep Learning","date":"2021-07-22","arxiv_id":"2107.10562","repositories_listed":0,"syntology":null},{"url":null,"slug":"multitask-based-joint-learning-approach-to","title":"Multitask-Based Joint Learning Approach To Robust ASR For Radio Communication Speech","date":"2021-07-22","arxiv_id":"2107.10701","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-multi-target-in-multi-stage","title":"Incorporating Multi-Target in Multi-Stage Speech Enhancement Model for Better Generalization","date":"2021-07-09","arxiv_id":"2107.04232","repositories_listed":0,"syntology":null},{"url":null,"slug":"df-conformer-integrated-architecture-of-conv","title":"DF-Conformer: Integrated architecture of Conv-TasNet and Conformer using linear complexity self-attention for speech enhancement","date":"2021-06-30","arxiv_id":"2106.15813","repositories_listed":0,"syntology":null},{"url":null,"slug":"srib-leap-submission-to-far-field-multi","title":"SRIB-LEAP submission to Far-field Multi-Channel Speech Enhancement Challenge for Video Conferencing","date":"2021-06-24","arxiv_id":"2106.12763","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-neural-network-based-low-latency-speech","title":"Deep neural network Based Low-latency Speech Separation with Asymmetric analysis-Synthesis Window Pair","date":"2021-06-22","arxiv_id":"2106.11794","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-flow-based-neural-network-for-time-domain","title":"A Flow-Based Neural Network for Time Domain Speech Enhancement","date":"2021-06-16","arxiv_id":"2106.09008","repositories_listed":0,"syntology":null},{"url":null,"slug":"dccrn-channel-wise-subband-dccrn-with-snr","title":"DCCRN+: Channel-wise Subband DCCRN with SNR Estimation for Speech Enhancement","date":"2021-06-16","arxiv_id":"2106.08672","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-interaction-between-masking-and-mapping","title":"Deep Interaction between Masking and Mapping Targets for Single-Channel Speech Enhancement","date":"2021-06-09","arxiv_id":"2106.04878","repositories_listed":0,"syntology":null},{"url":null,"slug":"human-listening-and-live-captioning-multi","title":"Human Listening and Live Captioning: Multi-Task Training for Speech Enhancement","date":"2021-06-05","arxiv_id":"2106.02896","repositories_listed":0,"syntology":null},{"url":null,"slug":"should-we-always-separate-switching-between","title":"Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition","date":"2021-06-02","arxiv_id":"2106.00949","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-neural-acoustic-echo-canceller-optimized","title":"A Neural Acoustic Echo Canceller Optimized Using An Automatic Speech Recognizer And Large Scale Synthetic Data","date":"2021-06-01","arxiv_id":"2106.00856","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-ratio-mask-estimation-for","title":"Phoneme-Based Ratio Mask Estimation for Reverberant Speech Enhancement in Cochlear Implant Processors","date":"2021-05-28","arxiv_id":"2105.14135","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-measure-of-musical-noise-based-on","title":"An Improved Measure of Musical Noise Based on Spectral Kurtosis","date":"2021-05-27","arxiv_id":"2105.13079","repositories_listed":0,"syntology":null},{"url":null,"slug":"training-speech-enhancement-systems-with","title":"Training Speech Enhancement Systems with Noisy Speech Datasets","date":"2021-05-26","arxiv_id":"2105.12315","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-time-domain-nearfield-frequency-invariant","title":"A time-domain nearfield frequency-invariant beamforming method","date":"2021-05-18","arxiv_id":"2105.08219","repositories_listed":0,"syntology":null},{"url":null,"slug":"dual-stage-low-complexity-reconfigurable","title":"Dual-Stage Low-Complexity Reconfigurable Speech Enhancement","date":"2021-05-17","arxiv_id":"2105.07632","repositories_listed":0,"syntology":null},{"url":null,"slug":"test-time-adaptation-toward-personalized","title":"Test-Time Adaptation Toward Personalized Speech Enhancement: Zero-Shot Learning with Knowledge Distillation","date":"2021-05-08","arxiv_id":"2105.03544","repositories_listed":0,"syntology":null},{"url":null,"slug":"zero-shot-personalized-speech-enhancement","title":"Zero-Shot Personalized Speech Enhancement through Speaker-Informed Model Selection","date":"2021-05-08","arxiv_id":"2105.03542","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-separable-polling","title":"Speech Enhancement using Separable Polling Attention and Global Layer Normalization followed with PReLU","date":"2021-05-06","arxiv_id":"2105.02509","repositories_listed":0,"syntology":null},{"url":null,"slug":"nonlinear-spatial-filtering-in-multichannel","title":"Nonlinear Spatial Filtering in Multichannel Speech Enhancement","date":"2021-04-22","arxiv_id":"2104.11033","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparison-of-remote-experiments-using","title":"Comparison of remote experiments using crowdsourcing and laboratory experiments on speech intelligibility","date":"2021-04-17","arxiv_id":"2104.10001","repositories_listed":0,"syntology":null},{"url":null,"slug":"complex-spectral-mapping-with-attention-based","title":"Complex Spectral Mapping With Attention Based Convolution Recurrent Neural Network for Speech Enhancement","date":"2021-04-12","arxiv_id":"2104.05267","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-ntnu-system-for-formosa-speech","title":"The NTNU Taiwanese ASR System for Formosa Speech Recognition Challenge 2020","date":"2021-04-09","arxiv_id":"2104.04221","repositories_listed":0,"syntology":null},{"url":null,"slug":"phoneme-based-distribution-regularization-for","title":"Phoneme-based Distribution Regularization for Speech Enhancement","date":"2021-04-08","arxiv_id":"2104.03759","repositories_listed":0,"syntology":null},{"url":null,"slug":"personalized-speech-enhancement-through-self","title":"Personalized Speech Enhancement through Self-Supervised Data Augmentation and Purification","date":"2021-04-05","arxiv_id":"2104.02018","repositories_listed":0,"syntology":null},{"url":null,"slug":"real-time-streaming-wave-u-net-with-temporal","title":"Real-time Streaming Wave-U-Net with Temporal Convolutions for Multichannel Speech Enhancement","date":"2021-04-05","arxiv_id":"2104.01923","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-for-personalized","title":"Efficient Personalized Speech Enhancement through Self-Supervised Learning","date":"2021-04-05","arxiv_id":"2104.02017","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-joint-training-with-self","title":"Adversarial Joint Training with Self-Attention Mechanism for Robust End-to-End Speech Recognition","date":"2021-04-03","arxiv_id":"2104.01471","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-noise-suppression-with-non-intrusive","title":"Deep Noise Suppression With Non-Intrusive PESQNet Supervision Enabling the Use of Real Training Data","date":"2021-03-31","arxiv_id":"2103.17088","repositories_listed":0,"syntology":null},{"url":null,"slug":"tstnn-two-stage-transformer-based-neural","title":"TSTNN: Two-stage Transformer based Neural Network for Speech Enhancement in the Time Domain","date":"2021-03-18","arxiv_id":"2103.09963","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-robust-speaker-verification-with","title":"Towards Robust Speaker Verification with Target Speaker Enhancement","date":"2021-03-16","arxiv_id":"2103.08781","repositories_listed":0,"syntology":null},{"url":null,"slug":"transformers-with-competitive-ensembles-of-1","title":"Transformers with Competitive Ensembles of Independent Mechanisms","date":"2021-02-27","arxiv_id":"2103.00336","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-multi-stage-self","title":"Speech Enhancement Using Multi-Stage Self-Attentive Temporal Convolutional Networks","date":"2021-02-24","arxiv_id":"2102.12078","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-robust-maximum-likelihood-distortionless","title":"A Robust Maximum Likelihood Distortionless Response Beamformer based on a Complex Generalized Gaussian Distribution","date":"2021-02-19","arxiv_id":"2102.09838","repositories_listed":0,"syntology":null},{"url":null,"slug":"variational-autoencoder-for-speech","title":"Variational Autoencoder for Speech Enhancement with a Noise-Aware Encoder","date":"2021-02-17","arxiv_id":"2102.08706","repositories_listed":0,"syntology":null},{"url":null,"slug":"guided-variational-autoencoder-for-speech","title":"Guided Variational Autoencoder for Speech Enhancement With a Supervised Classifier","date":"2021-02-12","arxiv_id":"2102.06454","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-with-mixture-of-deep","title":"Speech enhancement with mixture-of-deep-experts with clean clustering pre-training","date":"2021-02-11","arxiv_id":"2102.06034","repositories_listed":0,"syntology":null},{"url":"/paper/real-time-monaural-speech-enhancement-with","slug":"real-time-monaural-speech-enhancement-with","title":"Real-time Monaural Speech Enhancement With Short-time Discrete Cosine Transform","date":"2021-02-09","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"switching-variational-auto-encoders-for-noise","title":"Switching Variational Auto-Encoders for Noise-Agnostic Audio-visual Speech Enhancement","date":"2021-02-08","arxiv_id":"2102.04144","repositories_listed":0,"syntology":null},{"url":null,"slug":"vsegan-visual-speech-enhancement-generative","title":"VSEGAN: Visual Speech Enhancement Generative Adversarial Network","date":"2021-02-04","arxiv_id":"2102.02599","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-fidelity-speech-regeneration-with","title":"High Fidelity Speech Regeneration with Application to Speech Enhancement","date":"2021-01-31","arxiv_id":"2102.00429","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustic-structure-inverse-design-and","title":"Acoustic Structure Inverse Design and Optimization Using Deep Learning","date":"2021-01-29","arxiv_id":"2102.02063","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-for-wake-up-word-detection","title":"Speech Enhancement for Wake-Up-Word detection in Voice Assistants","date":"2021-01-29","arxiv_id":"2101.12732","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-efficient-models-for-real-time-deep","title":"Towards efficient models for real-time deep noise suppression","date":"2021-01-22","arxiv_id":"2101.09249","repositories_listed":0,"syntology":null},{"url":null,"slug":"noisy-target-training-a-training-strategy-for","title":"Noisy-target Training: A Training Strategy for DNN-based Speech Enhancement without Clean Speech","date":"2021-01-21","arxiv_id":"2101.08625","repositories_listed":0,"syntology":null},{"url":null,"slug":"attentional-multi-layer-feature-fusion","title":"AMFFCN: Attentional Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement","date":"2021-01-15","arxiv_id":"2101.06268","repositories_listed":0,"syntology":null},{"url":null,"slug":"mffcn-multi-layer-feature-fusion-convolution","title":"Multi-layer Feature Fusion Convolution Network for Audio-visual Speech Enhancement","date":"2021-01-15","arxiv_id":"2101.05975","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-network-based-virtual-microphone","title":"Neural Network-based Virtual Microphone Estimator","date":"2021-01-12","arxiv_id":"2101.04315","repositories_listed":0,"syntology":null},{"url":null,"slug":"dccrgan-deep-complex-convolution-recurrent","title":"DCCRGAN: Deep Complex Convolution Recurrent Generator Adversarial Network for Speech Enhancement","date":"2020-12-19","arxiv_id":"2012.10732","repositories_listed":0,"syntology":null},{"url":"/paper/interactive-speech-and-noise-modeling-for-1","slug":"interactive-speech-and-noise-modeling-for-1","title":"Interactive Speech and Noise Modeling for Speech Enhancement","date":"2020-12-17","arxiv_id":"2012.09408","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-speech-enhancement-using-a","title":"Towards speech enhancement using a variational U-Net architecture","date":"2020-12-07","arxiv_id":"2012.03594","repositories_listed":0,"syntology":null},{"url":null,"slug":"combining-spatial-clustering-with-lstm-speech","title":"Combining Spatial Clustering with LSTM Speech Models for Multichannel Speech Enhancement","date":"2020-12-02","arxiv_id":"2012.03388","repositories_listed":0,"syntology":null},{"url":null,"slug":"enhancement-of-spatial-clustering-based-time","title":"Enhancement of Spatial Clustering-Based Time-Frequency Masks using LSTM Neural Networks","date":"2020-12-02","arxiv_id":"2012.01576","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-recognition-based-on-deep-learning-an","title":"Speaker Recognition Based on Deep Learning: An Overview","date":"2020-12-02","arxiv_id":"2012.00931","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-ad-hoc-beamforming-based-on-speaker","title":"Deep Ad-hoc Beamforming Based on Speaker Extraction for Target-Dependent Speech Separation","date":"2020-12-01","arxiv_id":"2012.00403","repositories_listed":0,"syntology":null},{"url":null,"slug":"ultra-lightweight-speech-separation-via-group","title":"Ultra-Lightweight Speech Separation via Group Communication","date":"2020-11-18","arxiv_id":"2011.08397","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-task-single-channel-speech-enhancement","title":"Multi-task single channel speech enhancement using speech presence probability as a secondary task training target","date":"2020-11-15","arxiv_id":"2011.07547","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-guided-by-contextual","title":"Improving Speech Enhancement Performance by Leveraging Contextual Broad Phonetic Class Information","date":"2020-11-15","arxiv_id":"2011.07442","repositories_listed":0,"syntology":null},{"url":null,"slug":"evaluating-the-intelligibility-benefits-of","title":"Evaluating the Intelligibility Benefits of Neural Speech Enrichment for Listeners with Normal Hearing and Hearing Impairment using the Greek Harvard Corpus","date":"2020-11-12","arxiv_id":"2011.06548","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-time-delay-neural-network-for-speech","title":"Deep Time Delay Neural Network for Speech Enhancement with Full Data Learning","date":"2020-11-11","arxiv_id":"2011.05591","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-empirical-study-of-visual-features-for-dnn","title":"An Empirical Study of Visual Features for DNN based Audio-Visual Speech Enhancement in Multi-talker Environments","date":"2020-11-09","arxiv_id":"2011.04359","repositories_listed":0,"syntology":null},{"url":null,"slug":"gated-recurrent-fusion-with-joint-training","title":"Gated Recurrent Fusion with Joint Training Framework for Robust End-to-End Speech Recognition","date":"2020-11-09","arxiv_id":"2011.04249","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-gating-improved-convolutional","title":"Frequency Gating: Improved Convolutional Neural Networks for Speech Enhancement in the Time-Frequency Domain","date":"2020-11-08","arxiv_id":"2011.04092","repositories_listed":0,"syntology":null},{"url":null,"slug":"espnet-se-end-to-end-speech-enhancement-and","title":"ESPnet-se: end-to-end speech enhancement and separation toolkit designed for asr integration","date":"2020-11-07","arxiv_id":"2011.03706","repositories_listed":0,"syntology":null},{"url":null,"slug":"can-we-trust-deep-speech-prior","title":"Can We Trust Deep Speech Prior?","date":"2020-11-04","arxiv_id":"2011.02110","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-study-of-incorporating-articulatory","title":"A Study of Incorporating Articulatory Movement Information in Speech Enhancement","date":"2020-11-03","arxiv_id":"2011.01691","repositories_listed":0,"syntology":null},{"url":null,"slug":"unetgan-a-robust-speech-enhancement-approach","title":"UNetGAN: A Robust Speech Enhancement Approach in Time Domain for Extremely Low Signal-to-noise Ratio Condition","date":"2020-10-29","arxiv_id":"2010.15521","repositories_listed":0,"syntology":null},{"url":null,"slug":"phase-aware-speech-enhancement-using","title":"Phase Aware Speech Enhancement using Realisation of Complex-valued LSTM","date":"2020-10-27","arxiv_id":"2010.14122","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-noise-aware-memory-attention-network","title":"A Noise-Aware Memory-Attention Network Architecture for Regression-Based Speech Enhancement","date":"2020-10-25","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"exploring-multi-channel-features-for-speaker","title":"Multi-Channel Speaker Verification for Single and Multi-talker Speech","date":"2020-10-23","arxiv_id":"2010.12692","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-aided-end-to-end-multi","title":"Speech enhancement aided end-to-end multi-task learning for voice activity detection","date":"2020-10-23","arxiv_id":"2010.12484","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-huawei-speaker-diarisation-system-for-the","title":"The HUAWEI Speaker Diarisation System for the VoxCeleb Speaker Diarisation Challenge","date":"2020-10-22","arxiv_id":"2010.11657","repositories_listed":0,"syntology":null},{"url":null,"slug":"bert-for-joint-multichannel-speech","title":"BERT for Joint Multichannel Speech Dereverberation with Spatial-aware Tasks","date":"2020-10-21","arxiv_id":"2010.10892","repositories_listed":0,"syntology":null},{"url":null,"slug":"joint-blind-room-acoustic-characterization","title":"Joint Blind Room Acoustic Characterization From Speech And Music Signals Using Convolutional Recurrent Neural Networks","date":"2020-10-21","arxiv_id":"2010.11167","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigating-cross-domain-losses-for-speech","title":"Investigating Cross-Domain Losses for Speech Enhancement","date":"2020-10-20","arxiv_id":"2010.10468","repositories_listed":0,"syntology":null},{"url":null,"slug":"non-intrusive-speech-intelligibility","title":"Non-intrusive speech intelligibility prediction using automatic speech recognition derived measures","date":"2020-10-16","arxiv_id":"2010.08574","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-model-compression-method-with-matrix","title":"A Model Compression Method with Matrix Product Operators for Speech Enhancement","date":"2020-10-10","arxiv_id":"2010.04950","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-unified-deep-learning-framework-for-short","title":"A Unified Deep Learning Framework for Short-Duration Speaker Verification in Adverse Environments","date":"2020-10-06","arxiv_id":"2010.02477","repositories_listed":0,"syntology":null}],"record_sha256":"442da4bb2a549c3c0fab957a0951d3e775450d98af33637713b6b65f2ad3c975","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}