QC-GAN: 一种参数高效的四元数Conformer GAN用于高保真语音增强
QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
AI总结：
提出参数高效的QC-GAN，结合四元数Conformer生成器和MetricGAN训练，通过汉密尔顿积共享权重减少参数量，在VoiceBank+DEMAND上以0.89M参数达到PESQ 3.48，性能媲美两倍大小模型。
摘要：
我们提出了一种参数高效的语音增强框架——四元数Conformer GAN（QC-GAN），它将四元数Conformer生成器与基于MetricGAN的训练相结合。汉密尔顿积通过结构化权重共享对幅度和相位进行编码，在减少层参数数量的同时保持其相互依赖性。采用度量学习判别器，通过优化近似感知评估分数来最大化感知质量。在VoiceBank+DEMAND数据集上，QC-GAN仅用0.89M参数就达到了3.48的语音质量感知评估（PESQ）分数，其性能与最先进模型相当，而参数量不到后者的一半。一个35K参数的变体实现了3.23的PESQ分数，以显著更少的参数超越了传统方法。在DNS-Challenge 3数据集上的评估进一步证实了其在真实世界条件下的泛化能力。
英文摘要：
We propose a parameter-efficient speech enhancement framework, Quaternion Conformer GAN (QC-GAN), which combines a Quaternion Conformer generator with MetricGAN-based training. The Hamilton product encodes the magnitude and phase via structured weight sharing, reducing the number of layer parameters while preserving their interdependencies. A metric-learning discriminator was employed to maximize perceptual quality by optimizing the approximate perceptual evaluation scores. On the VoiceBank+DEMAND dataset, QC-GAN achieved a Perceptual Evaluation of Speech Quality (PESQ) score of 3.48 with only 0.89M parameters, delivering a performance comparable to state-of-the-art models at less than half their size. A 35K-parameter variant achieved a PESQ score of 3.23, surpassing conventional methods with significantly fewer parameters. Evaluation on the DNS-Challenge 3 dataset further confirmed generalization to real-world conditions.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
