Problem
Research questions and friction points this paper is trying to address.
Mean Opinion Score
self-supervised learning
acoustic details
speech quality assessment
semantic understanding
Is Semantics Enough for Speech Mean Opinion Score Prediction?
🤖 AI Summary
研究探讨了语义与声学细节对语音质量评估的影响，通过对比自监督学习模型、纯声学神经音频编码器及结合两者的模型，证明了结合语义理解和精细声学建模能更准确预测语音平均意见分。
📝 Abstract
Mean Opinion Score (MOS) is the gold standard for evaluating synthesized speech naturalness. However, current automatic MOS predictors are dominated by self-supervised learning (SSL) models that prioritize high-level semantics, potentially compromising their ability to capture critical acoustic details. In this paper, we systematically investigate representations from three paradigms: SSLs, acoustic-only neural audio codecs (NACs), and unified NACs that integrate semantics into reconstruction-based architectures. Extensive benchmarking on the standard BVCC and multiple out-of-domain (OOD) datasets demonstrates that features synergizing semantic understanding with fine-grained acoustic modeling achieve a higher performance upper bound in speech quality assessment. Ultimately, our findings highlight that semantics alone are not enough; a dual focus on semantic content and acoustic fidelity is essential for robust MOS prediction.
Innovation
Methods, ideas, or system contributions that make the work stand out.
self-supervised learning
neural audio codecs
semantic and acoustic integration
🔎 Similar Papers
No similar papers found.
