论文解读
SALSA-V: Shortcut-Augmented Long-form Synchronized Audio from Videos
音视频生成 | 7.6/10
长音频处理
论文解读
Cross-Talk Speech Reduction, by Separation, for Separation
语音分离 | 9.1/10
论文解读
Cross-Talk Speech Reduction, by Separation, for Separation
语音分离 | 8.3/10
论文解读
MedASR: An Open-Source Model for High-Accuracy Medical Dictation
语音识别 | 7.9/10
论文解读
Stable Audio 3
音频生成 | 6.8/10
论文解读
NAACA: Training-Free NeuroAuditory Attentive Cognitive Architecture with Oscillatory Working Memory for Salience-Driven Attention Gating
音频事件检测 | 7.0/10
论文解读
Task-Aware Answer Preservation under Audio Compression for Large Audio Language Models
音频问答 | 6.5/10