{"total":27,"rows":[{"id":"2510.13747","title":"InteractiveOmni: A Unified Omni-modal Model for Audio-Visual Multi-turn Dialogue","created":"2025-10-15","cited_by_count":29,"area":null},{"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,"area":null},{"id":"2211.02250","title":"Real-Time Target Sound Extraction","created":"2022-11-04","cited_by_count":22,"area":null},{"id":"2507.02915","title":"Audio-JEPA: Joint-Embedding Predictive Architecture for Audio Representation Learning","created":"2025-06-25","cited_by_count":17,"area":null},{"id":"2403.11827","title":"Sound Event Detection and Localization with Distance Estimation","created":"2024-03-18","cited_by_count":14,"area":null},{"id":"2506.02863","title":"CapSpeech: Enabling Downstream Applications in Style-Captioned Text-to-Speech","created":"2025-06-03","cited_by_count":11,"area":null},{"id":"2206.06126","title":"Robust Time Series Denoising with Learnable Wavelet Packet Transform","created":"2022-06-13","cited_by_count":10,"area":null},{"id":"2302.12712","title":"Amortised Invariance Learning for Contrastive Self-Supervision","created":"2023-02-24","cited_by_count":8,"area":null},{"id":"2107.10716","title":"Project Achoo: A Practical Model and Application for COVID-19 Detection from Recordings of Breath, Voice, and Cough","created":"2021-07-12","cited_by_count":7,"area":null},{"id":"2102.07820","title":"Anomalous Sound Detection with Machine Learning: A Systematic Review","created":"2021-02-15","cited_by_count":5,"area":null},{"id":"2106.06858","title":"Improving weakly supervised sound event detection with self-supervised auxiliary tasks","created":"2021-06-12","cited_by_count":4,"area":null},{"id":"2109.09227","title":"ARCA23K: An audio dataset for investigating open-set label noise","created":"2021-09-19","cited_by_count":3,"area":null},{"id":"2305.17191","title":"MT-SLVR: Multi-Task Self-Supervised Learning for Transformation In(Variant) Representations","created":"2023-05-29","cited_by_count":3,"area":null},{"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":"2102.08074","title":"Semi Supervised Learning For Few-shot Audio Classification By Episodic Triplet Mining","created":"2021-02-16","cited_by_count":1,"area":null},{"id":"2209.05900","title":"Binaural Signal Representations for Joint Sound Event Detection and Acoustic Scene Classification","created":"2022-09-13","cited_by_count":1,"area":null},{"id":"2106.03851","title":"Impact of data-splits on generalization: Identifying COVID-19 from cough and context","created":"2021-06-05","cited_by_count":0,"area":null},{"id":"2201.12352","title":"Automatic Audio Captioning using Attention weighted Event based Embeddings","created":"2022-01-28","cited_by_count":0,"area":null},{"id":"2206.13476","title":"Impact of Acoustic Event Tagging on Scene Classification in a Multi-Task Learning Framework","created":"2022-06-27","cited_by_count":0,"area":null},{"id":"2208.09096","title":"Representation Learning for the Automatic Indexing of Sound Effects Libraries","created":"2022-08-18","cited_by_count":0,"area":null},{"id":"2403.09579","title":"uaMix-MAE: Efficient Tuning of Pretrained Audio Transformers with Unsupervised Audio Mixtures","created":"2024-03-14","cited_by_count":0,"area":null},{"id":"2403.14246","title":"CATSE: A Context-Aware Framework for Causal Target Sound Extraction","created":"2024-03-21","cited_by_count":0,"area":null},{"id":"2408.05950","title":"Robust online reconstruction of continuous-time signals from a lean spike train ensemble code","created":"2024-08-12","cited_by_count":0,"area":null},{"id":"2503.21826","title":"Hierarchical Label Propagation: A Model-Size-Dependent Performance Booster for AudioSet Tagging","created":"2025-03-26","cited_by_count":0,"area":null},{"id":"2607.26607","title":"Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement","created":"2026-07-29","cited_by_count":0,"area":null},{"id":"2609.18041","title":"Correlation-Guided Encoder Selection for Multi-Encoder Large Audio-Language Models","created":"2026-09-16","cited_by_count":0,"area":null},{"id":"2609.22851","title":"Discrete vs. Continuous: A Comprehensive Study of Unified Audio Understanding in LALMs","created":"2026-09-19","cited_by_count":0,"area":null}],"next_cursor":null}