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

• URL: http://arxiv.org/abs/2606.18611v2
• Date: Thu, 18 Jun 2026 04:10:21 GMT
• Title: QC-GAN: A Parameter-Efficient Quaternion Conformer GAN for High-Fidelity Speech Enhancement
• Abstract summary: Quaternion Conformer GAN (QC-GAN) is a parameter-efficient speech enhancement framework.<n>QC-GAN encodes magnitude and phase via structured weight sharing.<n>A metric-learning discriminator was employed to maximize perceptual quality.
• Score: 0.1817528213772209
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• Noise-Induced Landscape Distortion in QAOA for Constrained Binary Optimization: Empirical Characterization on IBM Quantum Hardware [0.0]
  We introduce and empirically validate Landscape Span Compression (LSC)<n>LSC measures how much noise flattens the energy landscape, approaching 1 as the landscape collapses toward a barren plateau.<n>We report an experience study of applying QAOA with LSC-based noise characterization on IBM's ibm_fez for three constrained QUBO portfolio instances.
  arXiv  Detail & Related papers  (2026-04-21T12:55:50Z)
• IMPQ: Interaction-Aware Layerwise Mixed Precision Quantization for LLMs [4.655407920049974]
  Mixed-precision quantization offers a compelling solution, but existing methods struggle when the average precision drops below four bits.<n>In this paper, we propose two innovations to address these limitations.<n>First, we frame the mixed-precision quantization problem as a cooperative game among layers and introduce Shapley-based Progressive Quantization Estimation (SPQE)<n>Second, we propose Interaction-aware Mixed-Precision Quantization (IMPQ) which translates these Shapley estimates into a binary quadratic optimization formulation.
  arXiv  Detail & Related papers  (2025-09-18T21:59:40Z)
• Scaling Exponents Across Parameterizations and Optimizers [94.54718325264218]
  We propose a new perspective on parameterization by investigating a key assumption in prior work. Our empirical investigation includes tens of thousands of models trained with all combinations of threes. We find that the best learning rate scaling prescription would often have been excluded by the assumptions in prior work.
  arXiv  Detail & Related papers  (2024-07-08T12:32:51Z)
• CMGAN: Conformer-Based Metric-GAN for Monaural Speech Enhancement [5.766499647507758]
  We further develop the conformer-based metric generative adversarial network (CMGAN) model for speech enhancement (SE) in the time-frequency (TF) domain. Our findings show that CMGAN outperforms existing state-of-the-art methods in the three major speech enhancement tasks: denoising, dereverberation, and super-resolution.
  arXiv  Detail & Related papers  (2022-09-22T15:50:21Z)
• CMGAN: Conformer-based Metric GAN for Speech Enhancement [6.480967714783858]
  We propose a conformer-based metric generative adversarial network (CMGAN) for time-frequency domain. In the generator, we utilize two-stage conformer blocks to aggregate all magnitude and complex spectrogram information. The estimation of magnitude and complex spectrogram is decoupled in the decoder stage and then jointly incorporated to reconstruct the enhanced speech.
  arXiv  Detail & Related papers  (2022-03-28T23:53:34Z)
• Parameterized Channel Normalization for Far-field Deep Speaker Verification [21.237143465298505]
  We focus on two parametric normalization methods: per-channel energy normalization (PCEN) and parameterized cepstral mean normalization (PCMN) We evaluate the performance on Hi-MIA, a recent large-scale far-field speech corpus, with varied microphone and positional settings. Our methods outperform conventional mel filterbank features, with maximum of 33.5% and 39.5% relative improvement on equal error rate under matched microphone and mismatched microphone conditions, respectively.
  arXiv  Detail & Related papers  (2021-09-24T16:22:31Z)
• Bayesian Learning for Deep Neural Network Adaptation [57.70991105736059]
  A key task for speech recognition systems is to reduce the mismatch between training and evaluation data that is often attributable to speaker differences. Model-based speaker adaptation approaches often require sufficient amounts of target speaker data to ensure robustness. This paper proposes a full Bayesian learning based DNN speaker adaptation framework to model speaker-dependent (SD) parameter uncertainty.
  arXiv  Detail & Related papers  (2020-12-14T12:30:41Z)
• Reduced Reference Perceptual Quality Model and Application to Rate Control for 3D Point Cloud Compression [61.110938359555895]
  In rate-distortion optimization, the encoder settings are determined by maximizing a reconstruction quality measure subject to a constraint on the bit rate. We propose a linear perceptual quality model whose variables are the V-PCC geometry and color quantization parameters. Subjective quality tests with 400 compressed 3D point clouds show that the proposed model correlates well with the mean opinion score. We show that for the same target bit rate, ratedistortion optimization based on the proposed model offers higher perceptual quality than rate-distortion optimization based on exhaustive search with a point-to-point objective quality metric.
  arXiv  Detail & Related papers  (2020-11-25T12:42:02Z)
• Conformer: Convolution-augmented Transformer for Speech Recognition [60.119604551507805]
  Recently Transformer and Convolution neural network (CNN) based models have shown promising results in Automatic Speech Recognition (ASR) We propose the convolution-augmented transformer for speech recognition, named Conformer. On the widely used LibriSpeech benchmark, our model achieves WER of 2.1%/4.3% without using a language model and 1.9%/3.9% with an external language model on test/testother.
  arXiv  Detail & Related papers  (2020-05-16T20:56:25Z)
• You Do Not Need More Data: Improving End-To-End Speech Recognition by Text-To-Speech Data Augmentation [59.31769998728787]
  We build our TTS system on an ASR training database and then extend the data with synthesized speech to train a recognition model. Our system establishes a competitive result for end-to-end ASR trained on LibriSpeech train-clean-100 set with WER 4.3% for test-clean and 13.5% for test-other.
  arXiv  Detail & Related papers  (2020-05-14T17:24:57Z)
• Towards a Competitive End-to-End Speech Recognition for CHiME-6 Dinner Party Transcription [73.66530509749305]
  In this paper, we argue that, even in difficult cases, some end-to-end approaches show performance close to the hybrid baseline. We experimentally compare and analyze CTC-Attention versus RNN-Transducer approaches along with RNN versus Transformer architectures. Our best end-to-end model based on RNN-Transducer, together with improved beam search, reaches quality by only 3.8% WER abs. worse than the LF-MMI TDNN-F CHiME-6 Challenge baseline.
  arXiv  Detail & Related papers  (2020-04-22T19:08:33Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.