{"total":22,"rows":[{"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":"2104.08955","title":"Many-Speakers Single Channel Speech Separation with Optimal Permutation Training","created":"2021-04-18","cited_by_count":11,"area":null},{"id":"2210.16472","title":"Learning Audio-Visual Dynamics Using Scene Graphs for Audio Source Separation","created":"2022-10-29","cited_by_count":11,"area":null},{"id":"2202.10372","title":"L3DAS22 Challenge: Learning 3D Audio Sources in a Real Office Environment","created":"2022-02-21","cited_by_count":10,"area":null},{"id":"2104.05499","title":"L3DAS21 Challenge: Machine Learning for 3D Audio Signal Processing","created":"2021-04-12","cited_by_count":9,"area":null},{"id":"2101.05014","title":"Effective Low-Cost Time-Domain Audio Separation Using Globally Attentive Locally Recurrent Networks","created":"2021-01-13","cited_by_count":8,"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":"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":"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":"2207.04203","title":"Learning to Separate Voices by Spatial Regions","created":"2022-07-09","cited_by_count":4,"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":"2309.17189","title":"RTFS-Net: Recurrent Time-Frequency Modelling for Efficient Audio-Visual Speech Separation","created":"2023-09-29","cited_by_count":2,"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":"2401.08864","title":"Binaural Angular Separation Network","created":"2024-01-16","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":"2312.10756","title":"Attention-Driven Multichannel Speech Enhancement in Moving Sound Source Scenarios","created":"2023-12-17","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":"2502.06285","title":"End-to-End Multi-Microphone Speaker Extraction Using Relative Transfer Functions","created":"2025-02-10","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":"2603.18082","title":"EgoAdapt: Enhancing Robustness in Egocentric Interactive Speaker Detection Under Missing Modalities","created":"2026-03-18","cited_by_count":0,"area":null}],"next_cursor":null}