{"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/9","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":9,"pages_in_order":10,"rows_per_page":100,"rows":[801,900],"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/8","next":"/task/speech-enhancement/papers/10","papers":[{"url":null,"slug":"tdcgan-temporal-dilated-convolutional","title":"Tdcgan: Temporal Dilated Convolutional Generative Adversarial Network for End-to-end Speech Enhancement","date":"2020-09-30","arxiv_id":"2008.07787","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-consolidated-view-of-loss-functions-for","title":"A consolidated view of loss functions for supervised deep learning-based speech enhancement","date":"2020-09-25","arxiv_id":"2009.12286","repositories_listed":0,"syntology":null},{"url":null,"slug":"correlating-subword-articulation-with-lip","title":"Correlating Subword Articulation with Lip Shapes for Embedding Aware Audio-Visual Speech Enhancement","date":"2020-09-21","arxiv_id":"2009.09561","repositories_listed":0,"syntology":null},{"url":null,"slug":"dense-cnn-with-self-attention-for-time-domain","title":"Dense CNN with Self-Attention for Time-Domain Speech Enhancement","date":"2020-09-03","arxiv_id":"2009.01941","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-view-attention-based-speech-enhancement","title":"Multi-view Attention-based Speech Enhancement Model for Noise-robust Automatic Speech Recognition","date":"2020-09-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"blind-mask-to-improve-intelligibility-of-non","title":"Blind Mask to Improve Intelligibility of Non-Stationary Noisy Speech","date":"2020-08-20","arxiv_id":"2008.09175","repositories_listed":0,"syntology":null},{"url":"/paper/exploring-the-best-loss-function-for-dnn-1","slug":"exploring-the-best-loss-function-for-dnn-1","title":"Exploring the Best Loss Function for DNN-Based Low-latency Speech Enhancement with Temporal Convolutional Networks","date":"2020-08-20","arxiv_id":"2005.11611","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-low-latency-speech-enhancement-with","title":"Efficient Low-Latency Speech Enhancement with Mobile Audio Streaming Networks","date":"2020-08-17","arxiv_id":"2008.07244","repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-broad-phonetic-information-for","title":"Incorporating Broad Phonetic Information for Speech Enhancement","date":"2020-08-13","arxiv_id":"2008.07618","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-mean-absolute-error-for-deep-neural","title":"On Mean Absolute Error for Deep Neural Network Based Vector-to-Vector Regression","date":"2020-08-12","arxiv_id":"2008.07281","repositories_listed":0,"syntology":null},{"url":"/paper/poconet-better-speech-enhancement-with","slug":"poconet-better-speech-enhancement-with","title":"PoCoNet: Better Speech Enhancement with Frequency-Positional Embeddings, Semi-Supervised Conversational Data, and Biased Loss","date":"2020-08-11","arxiv_id":"2008.04470","repositories_listed":0,"syntology":null},{"url":null,"slug":"analyzing-upper-bounds-on-mean-absolute","title":"Analyzing Upper Bounds on Mean Absolute Errors for Deep Neural Network Based Vector-to-Vector Regression","date":"2020-08-04","arxiv_id":"2008.05459","repositories_listed":0,"syntology":null},{"url":null,"slug":"utterance-wise-meeting-transcription-system","title":"Utterance-Wise Meeting Transcription System Using Asynchronous Distributed Microphones","date":"2020-07-31","arxiv_id":"2007.15868","repositories_listed":0,"syntology":null},{"url":null,"slug":"investigation-of-phase-distortion-on","title":"Investigation of Phase Distortion on Perceived Speech Quality for Hearing-impaired Listeners","date":"2020-07-29","arxiv_id":"2007.14986","repositories_listed":0,"syntology":null},{"url":null,"slug":"neural-kalman-filtering-for-speech","title":"Neural Kalman Filtering for Speech Enhancement","date":"2020-07-28","arxiv_id":"2007.13962","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-the-use-of-audio-fingerprinting-features","title":"On the Use of Audio Fingerprinting Features for Speech Enhancement with Generative Adversarial Network","date":"2020-07-27","arxiv_id":"2007.13258","repositories_listed":0,"syntology":null},{"url":null,"slug":"resource-efficient-speech-mask-estimation-for","title":"Resource-Efficient Speech Mask Estimation for Multi-Channel Speech Enhancement","date":"2020-07-22","arxiv_id":"2007.11477","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-sound-separation-using-mixtures","title":"Unsupervised Sound Separation Using Mixture Invariant Training","date":"2020-06-23","arxiv_id":"2006.12701","repositories_listed":0,"syntology":null},{"url":null,"slug":"boosting-objective-scores-of-speech","title":"Boosting Objective Scores of a Speech Enhancement Model by MetricGAN Post-processing","date":"2020-06-18","arxiv_id":"2006.10296","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-iterative-graph-spectral-subtraction","title":"An Iterative Graph Spectral Subtraction Method for Speech Enhancement","date":"2020-06-15","arxiv_id":"2006.08497","repositories_listed":0,"syntology":null},{"url":"/paper/se-melgan-speaker-agnostic-rapid-speech","slug":"se-melgan-speaker-agnostic-rapid-speech","title":"SE-MelGAN -- Speaker Agnostic Rapid Speech Enhancement","date":"2020-06-13","arxiv_id":"2006.07637","repositories_listed":0,"syntology":null},{"url":null,"slug":"dilated-u-net-based-approach-for-multichannel","title":"Dilated U-net based approach for multichannel speech enhancement from First-Order Ambisonics recordings","date":"2020-06-02","arxiv_id":"2006.01708","repositories_listed":0,"syntology":null},{"url":null,"slug":"similarity-and-independence-aware-beamformer","title":"Similarity-and-Independence-Aware Beamformer: Method for Target Source Extraction using Magnitude Spectrogram as Reference","date":"2020-06-01","arxiv_id":"2006.00772","repositories_listed":0,"syntology":null},{"url":null,"slug":"snr-based-teachers-student-technique-for","title":"SNR-Based Teachers-Student Technique for Speech Enhancement","date":"2020-05-29","arxiv_id":"2005.14441","repositories_listed":0,"syntology":null},{"url":null,"slug":"sub-band-knowledge-distillation-framework-for","title":"Sub-Band Knowledge Distillation Framework for Speech Enhancement","date":"2020-05-29","arxiv_id":"2005.14435","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-robust-tts-for-low-resource-speakers","title":"Noise Robust TTS for Low Resource Speakers using Pre-trained Model and Speech Enhancement","date":"2020-05-26","arxiv_id":"2005.12531","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-re-identification-with-speaker","title":"Speaker Re-identification with Speaker Dependent Speech Enhancement","date":"2020-05-15","arxiv_id":"2005.07818","repositories_listed":0,"syntology":null},{"url":null,"slug":"adversarial-feature-learning-and-unsupervised","title":"Adversarial Feature Learning and Unsupervised Clustering based Speech Synthesis for Found Data with Acoustic and Textual Noise","date":"2020-04-28","arxiv_id":"2004.13595","repositories_listed":0,"syntology":null},{"url":null,"slug":"self-supervised-learning-of-visual-speech","title":"On the Role of Visual Cues in Audiovisual Speech Enhancement","date":"2020-04-25","arxiv_id":"2004.12031","repositories_listed":0,"syntology":null},{"url":null,"slug":"chime-6-challenge-tackling-multispeaker","title":"CHiME-6 Challenge:Tackling Multispeaker Speech Recognition for Unsegmented Recordings","date":"2020-04-20","arxiv_id":"2004.09249","repositories_listed":0,"syntology":null},{"url":null,"slug":"snr-based-features-and-diverse-training-data","title":"SNR-Based Features and Diverse Training Data for Robust DNN-Based Speech Enhancement","date":"2020-04-07","arxiv_id":"2004.03512","repositories_listed":0,"syntology":null},{"url":null,"slug":"characterizing-speech-adversarial-examples","title":"Characterizing Speech Adversarial Examples Using Self-Attention U-Net Enhancement","date":"2020-03-31","arxiv_id":"2003.13917","repositories_listed":0,"syntology":null},{"url":null,"slug":"improving-noise-robust-automatic-speech","title":"Improving noise robust automatic speech recognition with single-channel time-domain enhancement network","date":"2020-03-09","arxiv_id":"2003.03998","repositories_listed":0,"syntology":null},{"url":null,"slug":"tackling-real-noisy-reverberant-meetings-with","title":"Tackling real noisy reverberant meetings with all-neural source separation, counting, and diarization system","date":"2020-03-09","arxiv_id":"2003.03987","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-trainable-front-ends-for-neural","title":"Efficient Trainable Front-Ends for Neural Speech Enhancement","date":"2020-02-20","arxiv_id":"2002.09286","repositories_listed":0,"syntology":null},{"url":null,"slug":"consistency-aware-multi-channel-speech","title":"Consistency-aware multi-channel speech enhancement using deep neural networks","date":"2020-02-14","arxiv_id":"2002.05831","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-self-adaptation-and","title":"Speech Enhancement using Self-Adaptation and Multi-Head Self-Attention","date":"2020-02-14","arxiv_id":"2002.05873","repositories_listed":0,"syntology":null},{"url":null,"slug":"stable-training-of-dnn-for-speech-enhancement","title":"Stable Training of DNN for Speech Enhancement based on Perceptually-Motivated Black-Box Cost Function","date":"2020-02-14","arxiv_id":"2002.05879","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-based-distributed-multichannel-mask","title":"DNN-Based Distributed Multichannel Mask Estimation for Speech Enhancement in Microphone Arrays","date":"2020-02-13","arxiv_id":"2002.06016","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-multi-channel-speech-recognition-using","title":"Robust Multi-channel Speech Recognition using Frequency Aligned Network","date":"2020-02-06","arxiv_id":"2002.02520","repositories_listed":0,"syntology":null},{"url":null,"slug":"single-channel-speech-enhancement-using-1","title":"Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks","date":"2020-02-02","arxiv_id":"2002.00319","repositories_listed":0,"syntology":null},{"url":null,"slug":"clcnet-deep-learning-based-noise-reduction","title":"CLCNet: Deep learning-based Noise Reduction for Hearing Aids using Complex Linear Coding","date":"2020-01-28","arxiv_id":"2001.10218","repositories_listed":0,"syntology":null},{"url":null,"slug":"noise-dependent-super-gaussian-coherence","title":"Noise dependent Super Gaussian-Coherence based dual microphone Speech Enhancement for hearing aid application using smartphone","date":"2020-01-27","arxiv_id":"2001.09571","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-speaker-recognition-using-speech","title":"Robust Speaker Recognition Using Speech Enhancement And Attention Model","date":"2020-01-14","arxiv_id":"2001.05031","repositories_listed":0,"syntology":null},{"url":null,"slug":"monaural-speech-enhancement-using-a-multi","title":"Monaural Speech Enhancement Using a Multi-Branch Temporal Convolutional Network","date":"2019-12-27","arxiv_id":"1912.12023","repositories_listed":0,"syntology":null},{"url":null,"slug":"mixture-of-inference-networks-for-vae-based","title":"Mixture of Inference Networks for VAE-based Audio-visual Speech Enhancement","date":"2019-12-23","arxiv_id":"1912.10647","repositories_listed":0,"syntology":null},{"url":null,"slug":"high-quality-speech-synthesis-using-super","title":"High-quality Speech Synthesis Using Super-resolution Mel-Spectrogram","date":"2019-12-03","arxiv_id":"1912.01167","repositories_listed":0,"syntology":null},{"url":null,"slug":"time-domain-multi-modal-bone-air-conducted","title":"Time-Domain Multi-modal Bone/air Conducted Speech Enhancement","date":"2019-11-22","arxiv_id":"1911.09847","repositories_listed":0,"syntology":null},{"url":null,"slug":"distributed-microphone-speech-enhancement","title":"Distributed Microphone Speech Enhancement based on Deep Learning","date":"2019-11-19","arxiv_id":"1911.08153","repositories_listed":0,"syntology":null},{"url":null,"slug":"alternating-between-spectral-and-spatial","title":"Sequential Multi-Frame Neural Beamforming for Speech Separation and Enhancement","date":"2019-11-18","arxiv_id":"1911.07953","repositories_listed":0,"syntology":null},{"url":null,"slug":"speaker-independence-of-neural-vocoders-and","title":"Speaker independence of neural vocoders and their effect on parametric resynthesis speech enhancement","date":"2019-11-14","arxiv_id":"1911.06266","repositories_listed":0,"syntology":null},{"url":null,"slug":"robust-unsupervised-audio-visual-speech","title":"Robust Unsupervised Audio-visual Speech Enhancement Using a Mixture of Variational Autoencoders","date":"2019-11-10","arxiv_id":"1911.03930","repositories_listed":0,"syntology":null},{"url":null,"slug":"the-speed-submission-to-dihard-ii","title":"The Speed Submission to DIHARD II: Contributions & Lessons Learned","date":"2019-11-06","arxiv_id":"1911.02388","repositories_listed":0,"syntology":null},{"url":null,"slug":"memory-requirement-reduction-of-deep-neural","title":"Memory Requirement Reduction of Deep Neural Networks Using Low-bit Quantization of Parameters","date":"2019-11-01","arxiv_id":"1911.00527","repositories_listed":0,"syntology":null},{"url":null,"slug":"does-speech-enhancement-of-publicly-available","title":"Does Speech enhancement of publicly available data help build robust Speech Recognition Systems?","date":"2019-10-29","arxiv_id":"1910.13488","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-recurrent-variational-autoencoder-for","title":"A Recurrent Variational Autoencoder for Speech Enhancement","date":"2019-10-24","arxiv_id":"1910.10942","repositories_listed":0,"syntology":null},{"url":null,"slug":"comparative-study-between-adversarial","title":"Comparative Study between Adversarial Networks and Classical Techniques for Speech Enhancement","date":"2019-10-21","arxiv_id":"1910.09522","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptual-speech-enhancement-via-generative","title":"AeGAN: Time-Frequency Speech Denoising via Generative Adversarial Networks","date":"2019-10-21","arxiv_id":"1910.12620","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-talker-mvdr-beamforming-based-on","title":"Multi-Talker MVDR Beamforming Based on Extended Complex Gaussian Mixture Model","date":"2019-10-17","arxiv_id":"1910.07753","repositories_listed":0,"syntology":null},{"url":null,"slug":"shi-yong-yu-zhe-zhuan-huan-ji-shu-yu-yu-yin","title":"使用語者轉換技術於語音合成資料庫之音質改進(Speech Enhancement for TTS Speech Corpora by using Voice Conversion Technologies)","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-based-on-the-integration","title":"Speech enhancement based on the integration of fully convolutional network, temporal lowpass filtering and spectrogram masking","date":"2019-10-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"av-speech-enhancement-challenge-using-a-real","title":"AV Speech Enhancement Challenge using a Real Noisy Corpus","date":"2019-09-30","arxiv_id":"1910.00424","repositories_listed":0,"syntology":null},{"url":null,"slug":"multichannel-speech-enhancement-by-raw","title":"Multichannel Speech Enhancement by Raw Waveform-mapping using Fully Convolutional Networks","date":"2019-09-26","arxiv_id":"1909.11909","repositories_listed":0,"syntology":null},{"url":null,"slug":"190910407","title":"CochleaNet: A Robust Language-independent Audio-Visual Model for Speech Enhancement","date":"2019-09-23","arxiv_id":"1909.10407","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-scalable-noisy-speech-dataset-and-online","title":"A scalable noisy speech dataset and online subjective test framework","date":"2019-09-17","arxiv_id":"1909.08050","repositories_listed":0,"syntology":null},{"url":null,"slug":"spoken-speech-enhancement-using-eeg","title":"Spoken Speech Enhancement using EEG","date":"2019-09-13","arxiv_id":"1909.09132","repositories_listed":0,"syntology":null},{"url":null,"slug":"generative-speech-enhancement-based-on-cloned","title":"Generative Speech Enhancement Based on Cloned Networks","date":"2019-09-10","arxiv_id":"1909.04776","repositories_listed":0,"syntology":null},{"url":null,"slug":"on-loss-functions-for-supervised-monaural","title":"On Loss Functions for Supervised Monaural Time-Domain Speech Enhancement","date":"2019-09-03","arxiv_id":"1909.01019","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-using-adaptive-mean-median","title":"Speech Enhancement using Adaptive Mean Median Deviation and EMD Technique","date":"2019-08-26","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"coarse-to-fine-optimization-for-speech","title":"Coarse-to-fine Optimization for Speech Enhancement","date":"2019-08-21","arxiv_id":"1908.08044","repositories_listed":0,"syntology":null},{"url":null,"slug":"efficient-context-aggregation-for-end-to-end","title":"A Dual-Staged Context Aggregation Method Towards Efficient End-To-End Speech Enhancement","date":"2019-08-18","arxiv_id":"1908.06468","repositories_listed":0,"syntology":null},{"url":null,"slug":"audio-visual-speech-enhancement-using-1","title":"Audio-visual Speech Enhancement Using Conditional Variational Auto-Encoders","date":"2019-08-07","arxiv_id":"1908.02590","repositories_listed":0,"syntology":null},{"url":null,"slug":"my-lips-are-concealed-audio-visual-speech","title":"My lips are concealed: Audio-visual speech enhancement through obstructions","date":"2019-07-11","arxiv_id":"1907.04975","repositories_listed":0,"syntology":null},{"url":null,"slug":"convolutional-neural-network-based-speech","title":"Convolutional Neural Network-based Speech Enhancement for Cochlear Implant Recipients","date":"2019-07-03","arxiv_id":"1907.02526","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-monaural-speech-enhancement-method-for","title":"A Monaural Speech Enhancement Method for Robust Small-Footprint Keyword Spotting","date":"2019-06-20","arxiv_id":"1906.08415","repositories_listed":0,"syntology":null},{"url":null,"slug":"increasing-compactness-of-deep-learning-based","title":"Increasing Compactness Of Deep Learning Based Speech Enhancement Models With Parameter Pruning And Quantization Techniques","date":"2019-05-31","arxiv_id":"1906.01078","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-learning-based-audio-visual-speech","title":"Deep-Learning-Based Audio-Visual Speech Enhancement in Presence of Lombard Effect","date":"2019-05-29","arxiv_id":"1905.12605","repositories_listed":0,"syntology":null},{"url":null,"slug":"dnn-based-multi-frame-mvdr-filtering-for","title":"DNN-Based Speech Presence Probability Estimation for Multi-Frame Single-Microphone Speech Enhancement","date":"2019-05-21","arxiv_id":"1905.08492","repositories_listed":0,"syntology":null},{"url":null,"slug":"190503330","title":"Universal Sound Separation","date":"2019-05-08","arxiv_id":"1905.03330","repositories_listed":0,"syntology":null},{"url":null,"slug":"a-statistically-principled-and","title":"A Statistically Principled and Computationally Efficient Approach to Speech Enhancement using Variational Autoencoders","date":"2019-05-03","arxiv_id":"1905.01209","repositories_listed":0,"syntology":null},{"url":null,"slug":"perceptually-motivated-environment-specific","title":"Perceptually-motivated Environment-specific Speech Enhancement","date":"2019-05-01","arxiv_id":null,"repositories_listed":0,"syntology":null},{"url":null,"slug":"incorporating-symbolic-sequential-modeling","title":"Incorporating Symbolic Sequential Modeling for Speech Enhancement","date":"2019-04-30","arxiv_id":"1904.13142","repositories_listed":0,"syntology":null},{"url":null,"slug":"frequency-domain-multi-channel-acoustic","title":"Frequency Domain Multi-channel Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.05299","repositories_listed":0,"syntology":null},{"url":null,"slug":"multi-geometry-spatial-acoustic-modeling-for","title":"Multi-Geometry Spatial Acoustic Modeling for Distant Speech Recognition","date":"2019-04-28","arxiv_id":"1903.06539","repositories_listed":0,"syntology":null},{"url":null,"slug":"dry-focus-and-transcribe-end-to-end","title":"An Investigation of End-to-End Multichannel Speech Recognition for Reverberant and Mismatch Conditions","date":"2019-04-19","arxiv_id":"1904.09049","repositories_listed":0,"syntology":null},{"url":null,"slug":"joined-audio-visual-speech-enhancement-and","title":"An Analysis of Speech Enhancement and Recognition Losses in Limited Resources Multi-talker Single Channel Audio-Visual ASR","date":"2019-04-16","arxiv_id":"1904.08248","repositories_listed":0,"syntology":null},{"url":null,"slug":"voiceid-loss-speech-enhancement-for-speaker","title":"VoiceID Loss: Speech Enhancement for Speaker Verification","date":"2019-04-07","arxiv_id":"1904.03601","repositories_listed":0,"syntology":null},{"url":null,"slug":"taco-vc-a-single-speaker-tacotron-based-voice","title":"Taco-VC: A Single Speaker Tacotron based Voice Conversion with Limited Data","date":"2019-04-06","arxiv_id":"1904.03522","repositories_listed":0,"syntology":null},{"url":null,"slug":"towards-generalized-speech-enhancement-with","title":"Towards Generalized Speech Enhancement with Generative Adversarial Networks","date":"2019-04-06","arxiv_id":"1904.03418","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-denoising-by-parametric-resynthesis","title":"Speech denoising by parametric resynthesis","date":"2019-04-02","arxiv_id":"1904.01537","repositories_listed":0,"syntology":null},{"url":null,"slug":"unsupervised-speech-enhancement-based-on","title":"Unsupervised Speech Enhancement Based on Multichannel NMF-Informed Beamforming for Noise-Robust Automatic Speech Recognition","date":"2019-03-22","arxiv_id":"1903.09341","repositories_listed":0,"syntology":null},{"url":null,"slug":"bridging-the-gap-between-monaural-speech","title":"Bridging the Gap Between Monaural Speech Enhancement and Recognition with Distortion-Independent Acoustic Modeling","date":"2019-03-11","arxiv_id":"1903.04567","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-improved-uncertainty-propagation-method","title":"An improved uncertainty propagation method for robust i-vector based speaker recognition","date":"2019-02-15","arxiv_id":"1902.05761","repositories_listed":0,"syntology":null},{"url":null,"slug":"speech-enhancement-with-variational","title":"Speech enhancement with variational autoencoders and alpha-stable distributions","date":"2019-02-08","arxiv_id":"1902.03926","repositories_listed":0,"syntology":null},{"url":null,"slug":"an-ensemble-svm-based-approach-for-voice","title":"An Ensemble SVM-based Approach for Voice Activity Detection","date":"2019-02-05","arxiv_id":"1902.01544","repositories_listed":0,"syntology":null},{"url":null,"slug":"deep-speech-enhancement-for-reverberated-and","title":"Deep Speech Enhancement for Reverberated and Noisy Signals using Wide Residual Networks","date":"2019-01-03","arxiv_id":"1901.00660","repositories_listed":0,"syntology":null},{"url":null,"slug":"end-to-end-model-for-speech-enhancement-by","title":"End-to-End Model for Speech Enhancement by Consistent Spectrogram Masking","date":"2019-01-02","arxiv_id":"1901.00295","repositories_listed":0,"syntology":null},{"url":null,"slug":"tensor-train-long-short-term-memory-for","title":"Tensor-Train Long Short-Term Memory for Monaural Speech Enhancement","date":"2018-12-25","arxiv_id":"1812.10095","repositories_listed":0,"syntology":null},{"url":null,"slug":"acoustics-guided-evaluation-age-a-new-measure","title":"Acoustics-guided evaluation (AGE): a new measure for estimating performance of speech enhancement algorithms for robust ASR","date":"2018-11-28","arxiv_id":"1811.11517","repositories_listed":0,"syntology":null},{"url":null,"slug":"analysis-of-dnn-speech-signal-enhancement-for","title":"Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition","date":"2018-11-19","arxiv_id":"1811.07629","repositories_listed":0,"syntology":null}],"record_sha256":"f17019068dc8841fdadb0a4defe153a7c790f9f453570372a7376c57f092c17c","record_changed_at":"2026-09-28","record_changed_at_basis":"first_hashed"}