SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models 事件

SpectCount: Spectrotemporal Counting via Synthetic Signals Improves Large Audio Language Models arXiv:2606.06907v1 Announce Type: cross Abstract: Large audio language models (LALMs) extend large language models with an audio encoder and large-scale audio data. However, the scarcity of high-quality annotated audio data remains a fundamental bottleneck for scaling. Through probing signal detectability analysis, we identify fine-grained spectrotemporal perceptual weaknesses in a foundation LALM. T