MiDashengLM: Efficient Audio Understanding with General Audio Captions. arxiv.org/abs/2508.03983

Towards Attribution of Generators and Emotional Manipulation in Cross-Lingual Synthetic Speech using Geometric Learning. arxiv.org/abs/2511.10790

Curved Worlds, Clear Boundaries: Generalizing Speech Deepfake Detection using Hyperbolic and Spherical Geometry Spaces. arxiv.org/abs/2511.10793

Proactive Hearing Assistants that Isolate Egocentric Conversations. arxiv.org/abs/2511.11473

CO-VADA: A Confidence-Oriented Voice Augmentation Debiasing Approach for Fair Speech Emotion Recognition. arxiv.org/abs/2506.06071

SPUR: A Plug-and-Play Framework for Integrating Spatial Audio Understanding and Reasoning into Large Audio-Language Models. arxiv.org/abs/2511.06606

MUDAS: Mote-scale Unsupervised Domain Adaptation in Multi-label Sound Classification. arxiv.org/abs/2506.11331

Enhancing the NAO: Extending Capabilities of Legacy Robots for Long-Term Research. arxiv.org/abs/2509.17760

Golden Tonnetz. arxiv.org/abs/2509.21428

Melodia: Training-Free Music Editing Guided by Attention Probing in Diffusion Models. arxiv.org/abs/2511.08252

How Far Do SSL Speech Models Listen for Tone? Temporal Focus of Tone Representation under Low-resource Transfer. arxiv.org/abs/2511.12285

VoiceCraft-X: Unifying Multilingual, Voice-Cloning Speech Synthesis and Speech Editing. arxiv.org/abs/2511.12347

Eardrum sound pressure prediction from ear canal reflectance based on the inverse solution of Webster's horn equation. arxiv.org/abs/2511.12552

Systematic evaluation of time-frequency features for binaural sound source localization. arxiv.org/abs/2511.13487

Real-Time Speech Enhancement via a Hybrid ViT: A Dual-Input Acoustic-Image Feature Fusion. arxiv.org/abs/2511.11825

A Smart-Glasses for Emergency Medical Services via Multimodal Multitask Learning. arxiv.org/abs/2511.13078

FoleyBench: A Benchmark For Video-to-Audio Models. arxiv.org/abs/2511.13219

Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets. arxiv.org/abs/2511.13529

Study on the Fairness of Speaker Verification Systems on Underrepresented Accents in English. arxiv.org/abs/2204.12649

Lina-Speech: Gated Linear Attention and Initial-State Tuning for Multi-Sample Prompting Text-To-Speech Synthesis. arxiv.org/abs/2410.23320