{"total":27,"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":"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":"2110.05745","title":"VarArray: Array-Geometry-Agnostic Continuous Speech Separation","created":"2021-10-12","cited_by_count":10,"area":null},{"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":"2308.16892","title":"ReZero: Region-customizable Sound Extraction","created":"2023-08-31","cited_by_count":10,"area":null},{"id":"2312.03464","title":"Subnetwork-to-go: Elastic Neural Network with Dynamic Training and Customizable Inference","created":"2023-12-06","cited_by_count":9,"area":null},{"id":"2112.05893","title":"Hybrid Neural Networks for On-device Directional Hearing","created":"2021-12-11","cited_by_count":8,"area":null},{"id":"2209.04974","title":"VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational Speech Recognition","created":"2022-09-12","cited_by_count":7,"area":null},{"id":"2206.15423","title":"Implicit Neural Spatial Filtering for Multichannel Source Separation in the Waveform Domain","created":"2022-06-30","cited_by_count":6,"area":null},{"id":"2406.08396","title":"Neural Blind Source Separation and Diarization for Distant Speech Recognition","created":"2024-06-12","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":"2404.04947","title":"Gull: A Generative Multifunctional Audio Codec","created":"2024-04-07","cited_by_count":5,"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":"2111.04614","title":"Learning Filterbanks for End-to-End Acoustic Beamforming","created":"2021-11-08","cited_by_count":1,"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":"2303.07486","title":"Guided Speech Enhancement Network","created":"2023-03-13","cited_by_count":1,"area":null},{"id":"2308.04798","title":"Enhancing Mobile Privacy and Security: A Face Skin Patch-Based Anti-Spoofing Approach","created":"2023-08-09","cited_by_count":1,"area":null},{"id":"2201.09586","title":"PickNet: Real-Time Channel Selection for Ad Hoc Microphone Arrays","created":"2022-01-24","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":"2309.05287","title":"Addressing Feature Imbalance in Sound Source Separation","created":"2023-09-11","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":"2509.01399","title":"CabinSep: IR-Augmented Mask-Based MVDR for Real-Time In-Car Speech Separation with Distributed Heterogeneous Arrays","created":"2025-09-01","cited_by_count":0,"area":null},{"id":"2601.02688","title":"Multi-channel multi-speaker transformer for speech recognition","created":"2026-01-06","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":"2601.18037","title":"SpatialEmb: Extract and Encode Spatial Information for 1-Stage Multi-channel Multi-speaker ASR on Arbitrary Microphone Arrays","created":"2026-01-25","cited_by_count":0,"area":null},{"id":"2606.21635","title":"Time-Frequency Weighted Losses for Phoneme Reconstruction in DNN-Based Speech Enhancement","created":"2026-06-19","cited_by_count":0,"area":null}],"next_cursor":null}