State of Audio AI

Top papers

• PhaseCoder: Microphone Geometry-Agnostic Spatial Audio Understanding for Multimodal LLMs(8.0)
• Variable-Length Audio Fingerprinting(7.0)
• AnimalCLAP: Taxonomy-Aware Language-Audio Pretraining for Species Recognition and Trait Inference(7.0)
• Are Audio-Language Models Listening? Audio-Specialist Heads for Adaptive Audio Steering(7.0)
• AudioCapBench: Quick Evaluation on Audio Captioning across Sound, Music, and Speech(5.0)
• LipsAM: Lipschitz-Continuous Amplitude Modifier for Audio Signal Processing and its Application to Plug-and-Play Dereverberation(5.0)
• Echoes: A semantically-aligned music deepfake detection dataset(5.0)
• Towards Explicit Acoustic Evidence Perception in Audio LLMs for Speech Deepfake Detection(3.0)
• Spatial Audio Question Answering and Reasoning on Dynamic Source Movements(3.0)