Teaching Audio Models to Reason: A Unified Framework for Source- and Layer-wise Distillation
This addresses the problem of enhancing reasoning in audio models for AI applications, representing a novel method for a known bottleneck rather than a foundational advance.
The paper tackles the problem of audio models struggling with complex reasoning due to modality gaps and lack of structured supervision by proposing a unified knowledge distillation framework that transfers reasoning capabilities from textual teachers to audio students while preserving acoustic competence. Experimental results show significant improvements in audio reasoning performance.
While large audio language models excel at tasks like ASR and emotion recognition, they still struggle with complex reasoning due to the modality gap between audio and text as well as the lack of structured intermediate supervision. To address this, we propose a unified knowledge distillation framework to transfer reasoning capabilities from a high-capacity textual teacher model to a student audio models while preserving its acoustic competence. Our method introduces two key dimensions: source-wise distillation, which leverages both textual and acoustic teachers to provide complementary modality-specific supervision; and layer-wise distillation, which aligns teacher signals with appropriate student layers to improve transfer efficiency. This dual-dimensional strategy enables fine-grained control over the distillation process, effectively bridging the gap between symbolic reasoning and speech representations. Experimental results show significant improvements in audio reasoning performance, demonstrating the effectiveness of our framework as a reasoning transfer solution for audio modeling.