用四元数结构压缩模型，小体积实现高保真语音增强
QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
- 用四元数共用权重编码语音幅度与相位，减少参数量
- 在VoiceBank+DEMAND上仅0.89M参数即达PESQ 3.48分
- 适合资源受限场景的实时语音增强应用
我们提出一种参数高效的语音增强框架——四元数转换器生成对抗网络（QC-GAN），结合四元数转换器生成器与基于MetricGAN的训练方法。通过哈密顿乘积结构化共享权重，编码语音的幅度与相位信息，在保持二者依赖关系的同时显著减少层参数量。采用度量学习判别器，优化近似感知评估分数以提升听感质量。在VoiceBank+DEMAND数据集上，QC-GAN仅使用0.89M参数即达到3.48的语音感知质量评分（PESQ），性能媲美顶尖模型但规模不足其一半。一个仅35K参数的变体实现PESQ 3.23分，超越传统方法且参数极少。在DNS-Challenge 3数据集上的评估进一步验证了其在真实环境下的泛化能力。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。