paper-with-me

홈 › Papers

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

2026-06-17 · Shogo Yamauchi, Hideaki Tamori, Makoto Sakai, Yosuke Yamano, Tohru Nitta arxiv

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.

📄 PDF Abstract BibTeX arXiv:2606.18611

Code (0)

등록된 구현이 없습니다.

Tasks

Speech Enhancement

Results from the Paper

RankTaskDatasetModelMetrics
#2 Speech Enhancement DEMAND QC-GAN PESQ: 3.48
#4 Speech Enhancement VoiceBank+DEMAND QC-GAN PESQ: 3.48

Similar Papers 제목 키워드 기반

HyperConformer: Multi-head HyperMixer for Efficient Speech Recognition

2023-05-29 · Florian Mai, Juan Zuluaga-Gomez, Titouan Parcollet, Petr Motlicek

State-of-the-art ASR systems have achieved promising results by modeling local and global interactions separately. While the former can be computed efficiently, global interactions are usually modeled via attention mecha…

speech-recognitionSpeech Recognition

Fast Conformer with Linearly Scalable Attention for Efficient Speech Recognition

2023-05-08 · Dima Rekesh, Nithin Rao Koluguri, Samuel Kriman, Somshubra Majumdar 외

Conformer-based models have become the dominant end-to-end architecture for speech processing tasks. With the objective of enhancing the conformer architecture for efficient training and inference, we carefully redesigne…

Automatic Speech RecognitionDecoderspeech-recognitionSpeech Recognition+2

Hyper-parameter Adaptation of Conformer ASR Systems for Elderly and Dysarthric Speech Recognition

2023-06-27 · Tianzi Wang, Shoukang Hu, Jiajun Deng, Zengrui Jin 외

Automatic recognition of disordered and elderly speech remains highly challenging tasks to date due to data scarcity. Parameter fine-tuning is often used to exploit the large quantities of non-aged and healthy speech pre…

Domain Adaptationspeech-recognitionSpeech Recognition

Parameter-Efficient Conformers via Sharing Sparsely-Gated Experts for End-to-End Speech Recognition

2022-09-17 · Ye Bai, Jie Li, Wenjing Han, Hao Ni 외

While transformers and their variant conformers show promising performance in speech recognition, the parameterized property leads to much memory cost during training and inference. Some works use cross-layer weight-shar…

Knowledge DistillationMixture-of-Expertsspeech-recognitionSpeech Recognition

Efficient conformer: Progressive downsampling and grouped attention for automatic speech recognition

2021-08-31 · Maxime Burchi, Valentin Vielzeuf

The recently proposed Conformer architecture has shown state-of-the-art performances in Automatic Speech Recognition by combining convolution with attention to model both local and global dependencies. In this paper, we …

Automatic Speech RecognitionAutomatic Speech Recognition (ASR)Language ModelingLanguage Modelling+2