{"total":42,"rows":[{"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":"2110.04057","title":"FAST-RIR: Fast neural diffuse room impulse response generator","created":"2021-10-07","cited_by_count":35,"area":null},{"id":"2310.05368","title":"Measuring Acoustics with Collaborative Multiple Agents","created":"2023-10-09","cited_by_count":22,"area":null},{"id":"2308.16892","title":"ReZero: Region-customizable Sound Extraction","created":"2023-08-31","cited_by_count":10,"area":null},{"id":"2310.10497","title":"LocSelect: Target Speaker Localization with an Auditory Selective Hearing Mechanism","created":"2023-10-16","cited_by_count":6,"area":null},{"id":"2103.02378","title":"Continuous Speech Separation with Ad Hoc Microphone Arrays","created":"2021-03-03","cited_by_count":5,"area":null},{"id":"2505.14517","title":"Steering Deep Non-Linear Spatially Selective Filters for Weakly Guided Extraction of Moving Speakers in Dynamic Scenarios","created":"2025-05-20","cited_by_count":4,"area":null},{"id":"2104.02819","title":"Learning to Rank Microphones for Distant Speech Recognition","created":"2021-04-06","cited_by_count":3,"area":null},{"id":"2110.04694","title":"Multi-Channel End-to-End Neural Diarization with Distributed Microphones","created":"2021-10-10","cited_by_count":3,"area":null},{"id":"2203.16940","title":"Direction of Arrival Estimation of Sound Sources Using Icosahedral CNNs","created":"2022-03-31","cited_by_count":3,"area":null},{"id":"2310.10106","title":"End-to-end Multichannel Speaker-Attributed ASR: Speaker Guided Decoder and Input Feature Analysis","created":"2023-10-16","cited_by_count":3,"area":null},{"id":"2403.06570","title":"Improving Speaker Assignment in Speaker-Attributed ASR for Real Meeting Applications","created":"2024-03-11","cited_by_count":3,"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":"2309.15938","title":"Exploring Self-Supervised Contrastive Learning of Spatial Sound Event Representation","created":"2023-09-27","cited_by_count":2,"area":null},{"id":"2507.02791","title":"Self-Steering Deep Non-Linear Spatially Selective Filters for Efficient Extraction of Moving Speakers under Weak Guidance","created":"2025-07-03","cited_by_count":2,"area":null},{"id":"2601.12345","title":"Adaptive Rotary Steering with Joint Autoregression for Robust Extraction of Closely Moving Speakers in Dynamic Scenarios","created":"2026-01-18","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":"2112.03533","title":"A Time-domain Real-valued Generalized Wiener Filter for Multi-channel Neural Separation Systems","created":"2021-12-07","cited_by_count":1,"area":null},{"id":"2307.12498","title":"Robust Automatic Speech Recognition via WavAugment Guided Phoneme Adversarial Training","created":"2023-07-24","cited_by_count":1,"area":null},{"id":"2406.03251","title":"ASoBO: Attentive Beamformer Selection for Distant Speaker Diarization in Meetings","created":"2024-06-05","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":"2603.23723","title":"Autoregressive Guidance of Deep Spatially Selective Filters using Bayesian Tracking for Efficient Extraction of Moving Speakers","created":"2026-03-24","cited_by_count":1,"area":null},{"id":"2604.05731","title":"FoleyDesigner: Immersive Stereo Foley Generation with Precise Spatio-Temporal Alignment for Film Clips","created":"2026-04-07","cited_by_count":1,"area":null},{"id":"2606.31552","title":"Improving multichannel speech enhancement through accurate room-acoustic simulations","created":"2026-06-30","cited_by_count":1,"area":null},{"id":"2607.02343","title":"SelectTSL: Prompt-Guided Selective Target Sound Localization in Complex Scenarios","created":"2026-07-02","cited_by_count":1,"area":null},{"id":"2607.03806","title":"Probing Low-Level Acoustic Attribute Encoding in CLAP Audio Embeddings","created":"2026-07-04","cited_by_count":1,"area":null},{"id":"2301.00448","title":"Unsupervised Acoustic Scene Mapping Based on Acoustic Features and Dimensionality Reduction","created":"2023-01-01","cited_by_count":0,"area":null},{"id":"2312.10756","title":"Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios","created":"2023-12-17","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":"2410.21849","title":"Joint Beamforming and Speaker-Attributed ASR for Real Distant-Microphone Meeting Transcription","created":"2024-10-29","cited_by_count":0,"area":null},{"id":"2502.07205","title":"VINP: Variational Bayesian Inference with Neural Speech Prior for Joint ASR-Effective Speech Dereverberation and Blind RIR Identification","created":"2025-02-11","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":"2508.07561","title":"A Small-footprint Acoustic Echo Cancellation Solution for Mobile Full-Duplex Speech Interactions","created":"2025-08-11","cited_by_count":0,"area":null},{"id":"2509.18561","title":"SoundCompass: Navigating Target Sound Extraction With Effective Directional Clue Integration In Complex Acoustic Scenes","created":"2025-09-23","cited_by_count":0,"area":null},{"id":"2511.08012","title":"DOA Estimation with Lightweight Network on LLM-Aided Simulated Acoustic Scenes","created":"2025-11-11","cited_by_count":0,"area":null},{"id":"2512.10375","title":"Neural personal sound zones with flexible bright zone control","created":"2025-12-11","cited_by_count":0,"area":null},{"id":"2601.17711","title":"CaSNet: Compress-and-Send Network Based Multi-Device Speech Enhancement Model for Distributed Microphone Arrays","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2606.09677","title":"MeCo: One-Step MeanFlow-based Corrector for Multi-Channel Speech Separation","created":"2026-06-08","cited_by_count":0,"area":null},{"id":"2607.23293","title":"PathRIR: Physics-Guided Acoustic Path Selection and Late-Tail Compensation for Fast Room Impulse Response Simulation","created":"2026-07-25","cited_by_count":0,"area":null},{"id":"2609.33755","title":"Transformer-based Neural Beamforming for Real-Time Speech Enhancement on Smart Low-Power Hearable Devices","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.38748","title":"Hear the World in Stereo: Learning Dynamic Spatial Correspondence for Immersive Joint Video-Audio Generation","created":"2026-09-30","cited_by_count":0,"area":null},{"id":"2609.38897","title":"FFASR: Benchmarking Far-Field Automatic Speech Recognition using High-Fidelity Simulated RIRs","created":"2026-09-30","cited_by_count":0,"area":null}],"next_cursor":null}