Showing 1–20 of 28 results
/ Date/ Name
Feb 28, 2024Why does music source separation benefit from cacophony?Apr 4, 2023Pac-HuBERT: Self-Supervised Music Source Separation via Primitive Auditory Clustering and Hidden-Unit BERTNov 2, 2022Late Audio-Visual Fusion for In-The-Wild Speaker DiarizationJun 27, 2018Speech Denoising with Deep Feature LossesNov 4, 2022Cold Diffusion for Speech EnhancementOct 30, 2023Scenario-Aware Audio-Visual TF-GridNet for Target Speech ExtractionSep 20, 2024Leveraging Audio-Only Data for Text-Queried Target Sound ExtractionOct 16, 2023Generation or Replication: Auscultating Audio Latent Diffusion ModelsOct 31, 2024Task-Aware Unified Source SeparationFeb 27, 2024NIIRF: Neural IIR Filter Field for HRTF Upsampling and PersonalizationJun 6, 2024Sound Event Bounding BoxesSep 13, 2025Local Density-Based Anomaly Score Normalization for Domain GeneralizationSep 29, 2023Improving Audio Captioning Models with Fine-grained Audio Features, Text Embedding Supervision, and LLM Mix-up AugmentationMay 14, 2025UWAV: Uncertainty-weighted Weakly-supervised Audio-Visual Video ParsingAug 6, 2024Enhanced Reverberation as Supervision for Unsupervised Speech SeparationJan 22, 2025Retrieval-Augmented Neural Field for HRTF Upsampling and PersonalizationJul 15, 2025FasTUSS: Faster Task-Aware Unified Source SeparationMar 23, 2026Velocity Potential Neural Field for Efficient Ambisonics Impulse Response ModelingJul 9, 2025Physics-Informed Direction-Aware Neural Acoustic FieldsAug 11, 2025Exploring Disentangled Neural Speech Codecs from Self-Supervised Representations