{"list":"other","total":60,"rows":[{"id":"2407.10671","title":"Qwen2 Technical Report","created":"2024-07-15","cited_by_count":2120},{"id":"2211.06687","title":"Large-scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-Caption Augmentation","created":"2022-11-12","cited_by_count":719},{"id":"1510.08484","title":"MUSAN: A Music, Speech, and Noise Corpus","created":"2015-10-28","cited_by_count":425},{"id":"1809.07454","title":"Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation","created":"2018-09-20","cited_by_count":406},{"id":"1809.02108","title":"Deep Audio-Visual Speech Recognition","created":"2018-09-06","cited_by_count":322},{"id":"2303.17395","title":"WavCaps: A ChatGPT-Assisted Weakly-Labelled Audio Captioning Dataset for Audio-Language Multimodal Research","created":"2023-03-30","cited_by_count":267},{"id":"1910.06379","title":"Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation","created":"2019-10-14","cited_by_count":182},{"id":"1907.01160","title":"WHAM!: Extending Speech Separation to Noisy Environments","created":"2019-07-02","cited_by_count":156},{"id":"2005.13981","title":"The INTERSPEECH 2020 Deep Noise Suppression Challenge: Datasets, Subjective Testing Framework, and Challenge Results","created":"2020-05-16","cited_by_count":133},{"id":"1807.00129","title":"Sound Event Localization and Detection of Overlapping Sources Using Convolutional Recurrent Neural Networks","created":"2018-06-30","cited_by_count":85},{"id":"1810.04826","title":"VoiceFilter: Targeted Voice Separation by Speaker-Conditioned Spectrogram Masking","created":"2018-10-11","cited_by_count":73},{"id":"2211.12433","title":"TF-GridNet: Integrating Full- and Sub-Band Modeling for Speech Separation","created":"2022-11-22","cited_by_count":63},{"id":"1810.11359","title":"gpuRIR: A Python Library for Room Impulse Response Simulation with GPU Acceleration","created":"2018-10-26","cited_by_count":46},{"id":"2109.03465","title":"A Survey of Sound Source Localization with Deep Learning Methods","created":"2021-09-08","cited_by_count":46},{"id":"2203.15147","title":"Separate What You Describe: Language-Queried Audio Source Separation","created":"2022-03-28","cited_by_count":45},{"id":"2308.05037","title":"Separate Anything You Describe","created":"2023-08-09","cited_by_count":43},{"id":"1911.09649","title":"Learning to Localize Sound Sources in Visual Scenes: Analysis and Applications","created":"2019-11-20","cited_by_count":31},{"id":"2009.02792","title":"Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019","created":"2020-09-06","cited_by_count":31},{"id":"2004.08326","title":"SpEx: Multi-Scale Time Domain Speaker Extraction Network","created":"2020-04-17","cited_by_count":30},{"id":"2112.07891","title":"Zero-shot Audio Source Separation through Query-based Learning from Weakly-labeled Data","created":"2021-12-15","cited_by_count":27},{"id":"2010.15306","title":"ACCDOA: Activity-Coupled Cartesian Direction of Arrival Representation for Sound Event Localization and Detection","created":"2020-10-29","cited_by_count":26},{"id":"2010.13092","title":"An Improved Event-Independent Network for Polyphonic Sound Event Localization and Detection","created":"2020-10-25","cited_by_count":25},{"id":"2110.07124","title":"Multi-ACCDOA: Localizing and Detecting Overlapping Sounds from the Same Class with Auxiliary Duplicating Permutation Invariant Training","created":"2021-10-14","cited_by_count":25},{"id":"2212.07065","title":"CLIPSep: Learning Text-queried Sound Separation with Noisy Unlabeled Videos","created":"2022-12-14","cited_by_count":23},{"id":"2006.01919","title":"A Dataset of Reverberant Spatial Sound Scenes with Moving Sources for Sound Event Localization and Detection","created":"2020-06-02","cited_by_count":21},{"id":"1605.01177","title":"A metric on the space of finite sets of trajectories for evaluation of multi-target tracking algorithms","created":"2016-05-04","cited_by_count":17},{"id":"2206.01948","title":"STARSS22: A dataset of spatial recordings of real scenes with spatiotemporal annotations of sound events","created":"2022-06-04","cited_by_count":16},{"id":"2110.00275","title":"SALSA: Spatial Cue-Augmented Log-Spectrogram Features for Polyphonic Sound Event Localization and Detection","created":"2021-10-01","cited_by_count":15},{"id":"2109.14831","title":"USEV: Universal Speaker Extraction with Visual Cue","created":"2021-09-30","cited_by_count":11},{"id":"1807.11722","title":"Multi-Speaker DOA Estimation Using Deep Convolutional Networks Trained with Noise Signals","created":"2018-07-31","cited_by_count":10},{"id":"1904.12769","title":"Localization, Detection and Tracking of Multiple Moving Sound Sources with a Convolutional Recurrent Neural Network","created":"2019-04-29","cited_by_count":10},{"id":"2111.08192","title":"SALSA-Lite: A Fast and Effective Feature for Polyphonic Sound Event Localization and Detection with Microphone Arrays","created":"2021-11-16","cited_by_count":10},{"id":"2305.19610","title":"FN-SSL: Full-Band and Narrow-Band Fusion for Sound Source Localization","created":"2023-05-31","cited_by_count":10},{"id":"2010.00140","title":"Event-Independent Network for Polyphonic Sound Event Localization and Detection","created":"2020-09-30","cited_by_count":9},{"id":"2212.10744","title":"An Audio-Visual Speech Separation Model Inspired by Cortico-Thalamo-Cortical Circuits","created":"2022-12-21","cited_by_count":9},{"id":"2402.17455","title":"CLAPSep: Leveraging Contrastive Pre-trained Model for Multi-Modal Query-Conditioned Target Sound Extraction","created":"2024-02-27","cited_by_count":9},{"id":"2111.00030","title":"Differentiable Tracking-Based Training of Deep Learning Sound Source Localizers","created":"2021-10-29","cited_by_count":8},{"id":"2312.12821","title":"CST-former: Transformer with Channel-Spectro-Temporal Attention for Sound Event Localization and Detection","created":"2023-12-20","cited_by_count":8},{"id":"2303.05023","title":"X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker Confusion","created":"2023-03-09","cited_by_count":6},{"id":"2309.13343","title":"Two vs. Four-Channel Sound Event Localization and Detection","created":"2023-09-23","cited_by_count":6},{"id":"2310.10497","title":"LocSelect: Target Speaker Localization with an Auditory Selective Hearing Mechanism","created":"2023-10-16","cited_by_count":6},{"id":"2202.07859","title":"SRP-DNN: Learning Direct-Path Phase Difference for Multiple Moving Sound Source Localization","created":"2022-02-16","cited_by_count":5},{"id":"2212.08348","title":"Towards Unified All-Neural Beamforming for Time and Frequency Domain Speech Separation","created":"2022-12-16","cited_by_count":5},{"id":"2501.07215","title":"Microphone Array Signal Processing and Deep Learning for Speech Enhancement","created":"2025-01-13","cited_by_count":5},{"id":"2107.11066","title":"SALADnet: Self-Attentive multisource Localization in the Ambisonics Domain","created":"2021-07-23","cited_by_count":4},{"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},{"id":"2409.13152","title":"Leveraging Audio-Only Data for Text-Queried Target Sound Extraction","created":"2024-09-20","cited_by_count":4},{"id":"2507.12042","title":"Stereo Sound Event Localization and Detection with Onscreen/offscreen Classification","created":"2025-07-16","cited_by_count":4},{"id":"2209.01802","title":"Sound Event Localization and Detection for Real Spatial Sound Scenes: Event-Independent Network and Data Augmentation Chains","created":"2022-09-05","cited_by_count":3},{"id":"2309.09223","title":"Zero- and Few-shot Sound Event Localization and Detection","created":"2023-09-17","cited_by_count":3},{"id":"2408.16448","title":"Enhancing Sound Source Localization via False Negative Elimination","created":"2024-08-29","cited_by_count":3},{"id":"2405.07021","title":"IPDnet: A Universal Direct-Path IPD Estimation Network for Sound Source Localization","created":"2024-05-11","cited_by_count":2},{"id":"2406.16058","title":"Text-Queried Target Sound Event Localization","created":"2024-06-23","cited_by_count":2},{"id":"2503.08798","title":"Contextual Speech Extraction: Leveraging Textual History as an Implicit Cue for Target Speech Extraction","created":"2025-03-11","cited_by_count":2},{"id":"2203.04197","title":"Locate This, Not That: Class-Conditioned Sound Event DOA Estimation","created":"2022-03-08","cited_by_count":1},{"id":"2310.04722","title":"A Holistic Evaluation of Piano Sound Quality","created":"2023-10-07","cited_by_count":1},{"id":"2310.14016","title":"SwG-former: A Sliding-Window Graph Convolutional Network for Simultaneous Spatial-Temporal Information Extraction in Sound Event Localization and Detection","created":"2023-10-21","cited_by_count":1},{"id":"2404.18501","title":"Audio-Visual Target Speaker Extraction with Reverse Selective Auditory Attention","created":"2024-04-29","cited_by_count":1},{"id":"2406.08771","title":"MFF-EINV2: Multi-scale Feature Fusion across Spectral-Spatial-Temporal Domains for Sound Event Localization and Detection","created":"2024-06-13","cited_by_count":1},{"id":"2408.17166","title":"Learning Multi-Target TDOA Features for Sound Event Localization and Detection","created":"2024-08-30","cited_by_count":1}],"next_cursor":null}