{"total":132,"rows":[{"id":"2208.05830","title":"Speech Enhancement and Dereverberation with Diffusion-based Generative Models","created":"2022-08-11","cited_by_count":197,"area":"diffusion"},{"id":"2212.11851","title":"StoRM: A Diffusion-based Stochastic Regeneration Model for Speech Enhancement and Dereverberation","created":"2022-12-22","cited_by_count":105,"area":"diffusion"},{"id":"2206.08312","title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","created":"2022-06-16","cited_by_count":95,"area":null},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46,"area":null},{"id":"2402.01591","title":"BAT: Learning to Reason about Spatial Sounds with Large Language Models","created":"2024-02-02","cited_by_count":36,"area":"lr"},{"id":"2211.02397","title":"Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for Speech Restoration","created":"2022-11-04","cited_by_count":34,"area":"diffusion"},{"id":"2410.10676","title":"Both Ears Wide Open: Towards Language-Driven Spatial Audio Generation","created":"2024-10-14","cited_by_count":25,"area":"diffusion"},{"id":"2403.18821","title":"Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark","created":"2024-03-27","cited_by_count":20,"area":null},{"id":"2204.12489","title":"Sound Localization by Self-Supervised Time Delay Estimation","created":"2022-04-26","cited_by_count":18,"area":null},{"id":"2209.15483","title":"Augmentation Invariant Discrete Representation for Generative Spoken Language Modeling","created":"2022-09-30","cited_by_count":17,"area":null},{"id":"2102.03207","title":"Real-time Denoising and Dereverberation with Tiny Recurrent U-Net","created":"2021-02-05","cited_by_count":16,"area":null},{"id":"2206.13310","title":"Insights Into Deep Non-linear Filters for Improved Multi-channel Speech Enhancement","created":"2022-06-27","cited_by_count":14,"area":null},{"id":"2204.03594","title":"Heterogeneous Target Speech Separation","created":"2022-04-07","cited_by_count":13,"area":null},{"id":"2310.01688","title":"One model to rule them all ? Towards End-to-End Joint Speaker Diarization and Speech Recognition","created":"2023-10-02","cited_by_count":12,"area":null},{"id":"2401.12238","title":"Spatial Scaper: A Library to Simulate and Augment Soundscapes for Sound Event Localization and Detection in Realistic Rooms","created":"2024-01-19","cited_by_count":12,"area":null},{"id":"2406.07532","title":"Hearing Anything Anywhere","created":"2024-06-11","cited_by_count":12,"area":null},{"id":"2408.07472","title":"Unsupervised Blind Joint Dereverberation and Room Acoustics Estimation with Diffusion Models","created":"2024-08-14","cited_by_count":11,"area":"diffusion"},{"id":"2304.12023","title":"Multi-channel Speech Separation Using Spatially Selective Deep Non-linear Filters","created":"2023-04-24","cited_by_count":10,"area":null},{"id":"2406.06612","title":"SEE-2-SOUND: Zero-Shot Spatial Environment-to-Spatial Sound","created":"2024-06-06","cited_by_count":10,"area":null},{"id":"2105.02702","title":"MIMII DUE: Sound Dataset for Malfunctioning Industrial Machine Investigation and Inspection with Domain Shifts due to Changes in Operational and Environmental Conditions","created":"2021-05-06","cited_by_count":9,"area":null},{"id":"2106.07843","title":"Teacher-Student MixIT for Unsupervised and Semi-supervised Speech Separation","created":"2021-06-15","cited_by_count":9,"area":"distill"},{"id":"2306.12286","title":"Diffusion Posterior Sampling for Informed Single-Channel Dereverberation","created":"2023-06-21","cited_by_count":9,"area":"diffusion"},{"id":"2112.05893","title":"Hybrid Neural Networks for On-device Directional Hearing","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2207.09514","title":"ESPnet-SE++: Speech Enhancement for Robust Speech Recognition, Translation, and Understanding","created":"2022-07-19","cited_by_count":8,"area":null},{"id":"2504.10746","title":"Hearing Anywhere in Any Environment","created":"2025-04-14","cited_by_count":8,"area":null},{"id":"2208.04654","title":"Extending GCC-PHAT using Shift Equivariant Neural Networks","created":"2022-08-09","cited_by_count":7,"area":null},{"id":"2204.06439","title":"Receptive Field Analysis of Temporal Convolutional Networks for Monaural Speech Dereverberation","created":"2022-04-13","cited_by_count":6,"area":null},{"id":"2206.11181","title":"On the Role of Spatial, Spectral, and Temporal Processing for DNN-based Non-linear Multi-channel Speech Enhancement","created":"2022-06-22","cited_by_count":6,"area":null},{"id":"2410.11299","title":"Diff-SAGe: End-to-End Spatial Audio Generation Using Diffusion Models","created":"2024-10-15","cited_by_count":6,"area":"diffusion"},{"id":"2508.03448","title":"SonicMaster: Towards Controllable All-in-One Music Restoration and Mastering","created":"2025-08-05","cited_by_count":6,"area":null},{"id":"2601.02954","title":"The World is Not Mono: Enabling Spatial Understanding in Large Audio-Language Models","created":"2026-01-06","cited_by_count":6,"area":null},{"id":"2101.10636","title":"Semi-supervised source localization in reverberant environments with deep generative modeling","created":"2021-01-26","cited_by_count":5,"area":null},{"id":"2510.05542","title":"Sci-Phi: A Large Language Model Spatial Audio Descriptor","created":"2025-10-07","cited_by_count":5,"area":null},{"id":"2106.08873","title":"Voicy: Zero-Shot Non-Parallel Voice Conversion in Noisy Reverberant Environments","created":"2021-06-16","cited_by_count":4,"area":null},{"id":"2207.07307","title":"MIMO-DoAnet: Multi-channel Input and Multiple Outputs DoA Network with Unknown Number of Sound Sources","created":"2022-07-15","cited_by_count":4,"area":null},{"id":"2211.02420","title":"Spatially Selective Deep Non-linear Filters for Speaker Extraction","created":"2022-11-04","cited_by_count":4,"area":null},{"id":"2408.14712","title":"Is Audio Spoof Detection Robust to Laundering Attacks?","created":"2024-08-27","cited_by_count":4,"area":null},{"id":"2410.01481","title":"SonicSim: A customizable simulation platform for speech processing in moving sound source scenarios","created":"2024-10-02","cited_by_count":4,"area":null},{"id":"2604.06138","title":"Generating Synthetic Doctor-Patient Conversations for Long-form Audio Summarization","created":"2026-04-07","cited_by_count":4,"area":null},{"id":"2205.08455","title":"Utterance Weighted Multi-Dilation Temporal Convolutional Networks for Monaural Speech Dereverberation","created":"2022-05-17","cited_by_count":3,"area":null},{"id":"2302.10147","title":"A DNN based Normalized Time-frequency Weighted Criterion for Robust Wideband DoA Estimation","created":"2023-02-20","cited_by_count":3,"area":null},{"id":"2303.07449","title":"Blind Acoustic Room Parameter Estimation Using Phase Features","created":"2023-03-13","cited_by_count":3,"area":null},{"id":"2308.04169","title":"Dual input neural networks for positional sound source localization","created":"2023-08-08","cited_by_count":3,"area":null},{"id":"2506.10622","title":"SDialog: A Python Toolkit for End-to-End Agent Building, User Simulation, Dialog Generation, and Evaluation","created":"2025-06-12","cited_by_count":3,"area":"agents"},{"id":"2509.05175","title":"Room-acoustic simulations as an alternative to measurements for audio-algorithm evaluation","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2510.16834","title":"Schr\\\"odinger Bridge Mamba for One-Step Speech Enhancement","created":"2025-10-19","cited_by_count":3,"area":"ssm"},{"id":"2102.03762","title":"Time-Domain Speech Extraction with Spatial Information and Multi Speaker Conditioning Mechanism","created":"2021-02-07","cited_by_count":2,"area":null},{"id":"2111.10639","title":"Implicit Acoustic Echo Cancellation for Keyword Spotting and Device-Directed Speech Detection","created":"2021-11-20","cited_by_count":2,"area":null},{"id":"2112.06651","title":"Accoustate: Auto-annotation of IMU-generated Activity Signatures under Smart Infrastructure","created":"2021-12-08","cited_by_count":2,"area":null},{"id":"2207.10441","title":"Deep Audio Waveform Prior","created":"2022-07-21","cited_by_count":2,"area":null},{"id":"2303.00529","title":"Extending DNN-based Multiplicative Masking to Deep Subband Filtering for Improved Dereverberation","created":"2023-03-01","cited_by_count":2,"area":null},{"id":"2409.10048","title":"Audio-Driven Reinforcement Learning for Head-Orientation in Naturalistic Environments","created":"2024-09-16","cited_by_count":2,"area":"deeprl"},{"id":"2409.12415","title":"Multichannel-to-Multichannel Target Sound Extraction Using Direction and Timestamp Clues","created":"2024-09-19","cited_by_count":2,"area":null},{"id":"2410.11062","title":"CleanUMamba: A Compact Mamba Network for Speech Denoising using Channel Pruning","created":"2024-10-14","cited_by_count":2,"area":"ssm"},{"id":"2412.18217","title":"U-Mamba-Net: A highly efficient Mamba-based U-net style network for noisy and reverberant speech separation","created":"2024-12-24","cited_by_count":2,"area":"ssm"},{"id":"2501.08047","title":"Gen-A: Generalizing Ambisonics Neural Encoding to Unseen Microphone Arrays","created":"2025-01-14","cited_by_count":2,"area":null},{"id":"2502.06839","title":"A Hybrid Model for Weakly-Supervised Speech Dereverberation","created":"2025-02-06","cited_by_count":2,"area":null},{"id":"2502.11462","title":"LMFCA-Net: A Lightweight Model for Multi-Channel Speech Enhancement with Efficient Narrow-Band and Cross-Band Attention","created":"2025-02-17","cited_by_count":2,"area":null},{"id":"2506.19875","title":"Speaker Embeddings to Improve Tracking of Intermittent and Moving Speakers","created":"2025-06-23","cited_by_count":2,"area":null},{"id":"2507.18061","title":"TELEVAL: A Benchmark Designed for Spoken Language Models in Chinese Interactive Scenarios","created":"2025-07-24","cited_by_count":2,"area":null},{"id":"2602.01861","title":"RIR-Former: Coordinate-Guided Transformer for Continuous Reconstruction of Room Impulse Responses","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2603.19660","title":"Semantic Audio-Visual Navigation in Continuous Environments","created":"2026-03-20","cited_by_count":2,"area":null},{"id":"2110.08634","title":"Towards Robust Waveform-Based Acoustic Models","created":"2021-10-16","cited_by_count":1,"area":null},{"id":"2203.16757","title":"Exploiting Single-Channel Speech for Multi-Channel End-to-End Speech Recognition: A Comparative Study","created":"2022-03-31","cited_by_count":1,"area":null},{"id":"2204.00218","title":"End-to-End Multi-speaker ASR with Independent Vector Analysis","created":"2022-04-01","cited_by_count":1,"area":null},{"id":"2206.12273","title":"Iterative Sound Source Localization for Unknown Number of Sources","created":"2022-06-24","cited_by_count":1,"area":null},{"id":"2210.08493","title":"Indoor Smartphone SLAM with Learned Echoic Location Features","created":"2022-10-16","cited_by_count":1,"area":null},{"id":"2302.09409","title":"LOCUS: LOcalization with Channel Uncertainty and Sporadic Energy","created":"2023-02-18","cited_by_count":1,"area":null},{"id":"2403.20130","title":"Sound event localization and classification using WASN in Outdoor Environment","created":"2024-03-29","cited_by_count":1,"area":null},{"id":"2408.15771","title":"wav2pos: Sound Source Localization using Masked Autoencoders","created":"2024-08-28","cited_by_count":1,"area":null},{"id":"2409.14971","title":"Blind Spatial Impulse Response Generation from Separate Room- and Scene-Specific Information","created":"2024-09-23","cited_by_count":1,"area":null},{"id":"2411.14207","title":"HARP: A Large-Scale Higher-Order Ambisonic Room Impulse Response Dataset","created":"2024-11-21","cited_by_count":1,"area":null},{"id":"2504.10793","title":"SonicSieve: Bringing Directional Speech Extraction to Smartphones Using Acoustic Microstructures","created":"2025-04-15","cited_by_count":1,"area":null},{"id":"2505.13617","title":"Direction-Aware Neural Acoustic Fields for Few-Shot Interpolation of Ambisonic Impulse Responses","created":"2025-05-19","cited_by_count":1,"area":null},{"id":"2506.18714","title":"Frequency-Weighted Training Losses for Phoneme-Level DNN-based Speech Enhancement","created":"2025-06-23","cited_by_count":1,"area":null},{"id":"2507.01143","title":"A Review on Sound Source Localization in Robotics: Focusing on Deep Learning Methods","created":"2025-07-01","cited_by_count":1,"area":null},{"id":"2601.19949","title":"RIR-Mega-Speech: A Reverberant Speech Corpus with Comprehensive Acoustic Metadata and Reproducible Evaluation","created":"2026-01-25","cited_by_count":1,"area":null},{"id":"2602.17732","title":"SIRUP: A diffusion-based virtual upmixer of steering vectors for highly-directive spatialization with first-order ambisonics","created":"2026-02-18","cited_by_count":1,"area":"diffusion"},{"id":"2604.07522","title":"Training-free Spatially Grounded Geometric Shape Encoding (Technical Report)","created":"2026-04-08","cited_by_count":1,"area":null},{"id":"2102.00313","title":"Cortical Features for Defense Against Adversarial Audio Attacks","created":"2021-01-30","cited_by_count":0,"area":null},{"id":"2103.13443","title":"Blind Speech Separation and Dereverberation using Neural Beamforming","created":"2021-03-24","cited_by_count":0,"area":null},{"id":"2106.13493","title":"Online Self-Attentive Gated RNNs for Real-Time Speaker Separation","created":"2021-06-25","cited_by_count":0,"area":null},{"id":"2206.12132","title":"SANE-TTS: Stable And Natural End-to-End Multilingual Text-to-Speech","created":"2022-06-24","cited_by_count":0,"area":null},{"id":"2207.07273","title":"Direction-Aware Joint Adaptation of Neural Speech Enhancement and Recognition in Real Multiparty Conversational Environments","created":"2022-07-15","cited_by_count":0,"area":null},{"id":"2212.03401","title":"MIMO-DBnet: Multi-channel Input and Multiple Outputs DOA-aware Beamforming Network for Speech Separation","created":"2022-12-07","cited_by_count":0,"area":null},{"id":"2306.15942","title":"Enhanced Neural Beamformer with Spatial Information for Target Speech Extraction","created":"2023-06-28","cited_by_count":0,"area":null},{"id":"2309.01513","title":"RGI-Net: 3D Room Geometry Inference from Room Impulse Responses With Hidden First-Order Reflections","created":"2023-09-04","cited_by_count":0,"area":null},{"id":"2309.05287","title":"Addressing Feature Imbalance in Sound Source Separation","created":"2023-09-11","cited_by_count":0,"area":null},{"id":"2309.11462","title":"AudioFool: Fast, Universal and synchronization-free Cross-Domain Attack on Speech Recognition","created":"2023-09-20","cited_by_count":0,"area":null},{"id":"2311.00146","title":"RIR-SF: Room Impulse Response Based Spatial Feature for Target Speech Recognition in Multi-Channel Multi-Speaker Scenarios","created":"2023-10-31","cited_by_count":0,"area":null},{"id":"2401.02673","title":"A unified multichannel far-field speech recognition system: combining neural beamforming with attention based end-to-end model","created":"2024-01-05","cited_by_count":0,"area":null},{"id":"2405.02119","title":"EnvId: A Metric Learning Approach for Forensic Few-Shot Identification of Unseen Environments","created":"2024-05-03","cited_by_count":0,"area":null},{"id":"2406.11006","title":"SPEAR: Receiver-to-Receiver Acoustic Neural Warping Field","created":"2024-06-16","cited_by_count":0,"area":null},{"id":"2410.22805","title":"Run-Time Adaptation of Neural Beamforming for Robust Speech Dereverberation and Denoising","created":"2024-10-30","cited_by_count":0,"area":null},{"id":"2411.13179","title":"SONNET: Enhancing Time Delay Estimation by Leveraging Simulated Audio","created":"2024-11-20","cited_by_count":0,"area":null},{"id":"2501.03045","title":"Single-Channel Distance-Based Source Separation for Mobile GPU in Outdoor and Indoor Environments","created":"2025-01-06","cited_by_count":0,"area":null},{"id":"2505.01338","title":"How much to Dereverberate? Low-Latency Single-Channel Speech Enhancement in Distant Microphone Scenarios","created":"2025-05-02","cited_by_count":0,"area":null},{"id":"2506.00934","title":"GRAM: Spatial general-purpose audio representation models for real-world applications","created":"2025-06-01","cited_by_count":0,"area":null},{"id":"2507.03854","title":"Latent FxLMS: Accelerating Active Noise Control with Neural Adaptive Filters","created":"2025-07-05","cited_by_count":0,"area":null},{"id":"2507.14237","title":"U-DREAM: Unsupervised Dereverberation guided by a Reverberation Model","created":"2025-07-17","cited_by_count":0,"area":null}],"next_cursor":"100"}