Search papers, labs, and topics across Lattice.
This paper introduces GatherMOS, a framework that uses LLMs to predict speech quality by aggregating acoustic descriptors with pseudo-labels from DNSMOS and VQScore. By using the LLM as a meta-evaluator, the system can reason over heterogeneous inputs to infer perceptual mean opinion scores (MOS). Experiments on the VoiceBank-DEMAND dataset show that GatherMOS outperforms existing methods, particularly in low-data regimes, demonstrating the potential of LLMs for non-intrusive speech quality evaluation.
LLMs can effectively aggregate diverse speech quality metrics, even outperforming specialized models when labeled data is scarce.
In this paper, we introduce GatherMOS, a novel framework that leverages large language models (LLM) as meta-evaluators to aggregate diverse signals into quality predictions. GatherMOS integrates lightweight acoustic descriptors with pseudo-labels from DNSMOS and VQScore, enabling the LLM to reason over heterogeneous inputs and infer perceptual mean opinion scores (MOS). We further explore both zero-shot and few-shot in-context learning setups, showing that zero-shot GatherMOS maintains stable performance across diverse conditions, while few-shot guidance yields large gains when support samples match the test conditions. Experiments on the VoiceBank-DEMAND dataset demonstrate that GatherMOS consistently outperforms DNSMOS, VQScore, naive score averaging, and even learning-based models such as CNN-BLSTM and MOS-SSL when trained under limited labeled-data conditions. These results highlight the potential of LLM-based aggregation as a practical strategy for non-intrusive speech quality evaluation.
