Article

IterVocoder: Fast High-Fidelity Speech Synthesis via GAN-Guided Iterative Refinement

2025-06-26

Abstract excerpt

Recent progress in neural vocoders has demonstrated impressive advances in natural speech synthesis. Among them, denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) stand out due to their ability to produce high-fidelity audio. However, DDPMs typically require a large number of iterative steps, and GANs often suffer from training instability. To reconcile these limitations,...

Topics

Open a Topic to create a Post that cites this publication.

Identifiers and source

Literature Corpus work: 8c57c814-8b0c-56b9-904d-2085872a27f9
DOI: 10.20944/preprints202506.2168.v1

Open publication

Related research

Semantic proximity does not establish scientific evidence.

Click a neighbor to travelStep 1 · 12 closest

IterVocoder: Fast High-Fidelity Speech Synthesis via GAN-Guided Iterative RefinementDOI 10.20944/preprints202506.2168.v1Read

Natural speech re-synthesis from direct cortical recordings using a pre-trained encoder-decoder frameworkSemantic proximity Read

Expressive Speech Synthesis by Modeling Prosody with Variational Autoencoders for Bangla Text-to-SpeechSemantic proximity Read

Introduction to Diffusion Models, Autoencoders and Transformers: Review of Current AdvancementsSemantic proximity Read

Speech-driven Facial Animations Improve Speech-in-Noise Comprehension of HumansSemantic proximity Read

End-to-End ASR Conformers: Revolutionizing Hearing-to-Speech-to-Writing Language Processing FrameworksSemantic proximity Read

Fake Voice Detection: A Comparative Analysis of Complex-Valued Deep Learning and Transformer Models across Multiple LanguagesSemantic proximity Read

Speech Emotion Recognition using Data Augmentation Method by Cycle-Generative Adversarial NetworksSemantic proximity Read

Neural prediction decorrelation reveals that adversarial robustness substantially improves DNN prediction accuracy across the entire human auditory cortexSemantic proximity Read

RAE-NeRF: Residual-Based Audio-Video Encoder with Denoising in Talking Head SynchronizationSemantic proximity Read

EnCoNet: An Ensemble-based Synthetic Speech Attribution Scheme with Convolutional Neural NetworksSemantic proximity Read

A Neural Speech Decoding Framework Leveraging Deep Learning and Speech SynthesisSemantic proximity Read

Cycle-consistent Generative Adversarial Networks (CycleGANs) for the Non-Parallel Creation of Fake Voice MediaSemantic proximity Read