QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement

arXiv:2606.18611 · cs.SD, cs.AI, cs.LG, stat.ML · Submitted 2026-06-17 · Read on arXiv

Shogo Yamauchi, Hideaki Tamori, Makoto Sakai, Yosuke Yamano, Tohru Nitta

cs.SD, cs.AI, cs.LG, stat.ML

Submitted: 2026-06-17

Comments: 10 pages, 6 figures and 5 tables. Accepted at Interspeech2026

Code: https://github.com/asahi-research/QC-GAN

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Generator — 12× in this paper · explained in 2 episodes
• Ablation — 9× in this paper · explained in 1 episode
• Parameter Efficiency — 6× in this paper · explained in 3 episodes
• Transformer — 6× in this paper · explained in 2 episodes
• Ablation Study — 5× in this paper · explained in 3 episodes
• Decoder — 5× in this paper · explained in 2 episodes
• Loss Function — 5× in this paper · explained in 2 episodes
• Generalization — 4× in this paper · explained in 14 episodes
• Inductive Bias — 4× in this paper · explained in 3 episodes
• Attention Mechanism — 3× in this paper · explained in 3 episodes
• Fidelity — 3× in this paper · explained in 2 episodes
• Transformers — 3× in this paper · explained in 2 episodes
• Accuracy — 2× in this paper · explained in 1 episode
• Consistency — 2× in this paper · explained in 3 episodes
• Localization — 2× in this paper · explained in 2 episodes
• Perceptual Evaluation of Speech Quality — 2× in this paper
• Ablation Studies — 1× in this paper · explained in 1 episode
• Augmentation — 1× in this paper · explained in 2 episodes
• Automatic Speech Recognition (ASR) — 1× in this paper · explained in 2 episodes
• Benchmark — 1× in this paper · explained in 2 episodes
• Computational overhead — 1× in this paper · explained in 2 episodes
• Convolutional Neural Network (CNN) — 1× in this paper · explained in 2 episodes
• Data Augmentation — 1× in this paper · explained in 10 episodes
• Feature Extraction — 1× in this paper · explained in 3 episodes
• Gating Mechanism — 1× in this paper · explained in 2 episodes
• Generative AI — 1× in this paper · explained in 2 episodes
• Generative Model — 1× in this paper · explained in 2 episodes
• Gradient Flow — 1× in this paper · explained in 2 episodes
• Group Delay — 1× in this paper
• Instantaneous Phase — 1× in this paper
• International Joint Conference on Neural Networks — 1× in this paper
• Latent Representation — 1× in this paper · explained in 2 episodes
• Model Compression — 1× in this paper · explained in 3 episodes
• Performance Gap — 1× in this paper · explained in 2 episodes
• Pruning — 1× in this paper · explained in 4 episodes
• Quaternion Gated — 1× in this paper
• Regularization — 1× in this paper · explained in 3 episodes
• Robustness — 1× in this paper · explained in 6 episodes
• Short-Time Objective Intelligibility — 1× in this paper
• Structural Constraints — 1× in this paper · explained in 2 episodes
• Temporal Consistency — 1× in this paper · explained in 3 episodes
• Weight Decay — 1× in this paper · explained in 2 episodes

Sources

• Data augmentation and loss normalization for deep noise suppression

Related papers

• Few-Shot Open-Set Audio Classification via Transductive Prototype Refinement and Class Logit Enhancement
• Spectral Masking and Interpolation Attack (SMIA): A Black-box Adversarial Attack against Voice Authentication and Anti-Spoofing Systems
• Remix the Timbre: Diffusion-Based Style Transfer Across Polyphonic Stems
• Harmonic Representations in Symbolic Music Transformers are Localized and Controllable
• AVMeme Exam: A Multimodal Multilingual Multicultural Benchmark for LLMs' Contextual and Cultural Knowledge and Thinking
• SoundWeaver: Compositional Warm-Starting for Text-to-Audio Diffusion Serving