Search Results for author: Ha-Yeong Choi

Found 7 papers, 5 papers with code

VoicePrompter: Robust Zero-Shot Voice Conversion with Voice Prompt and Conditional Flow Matching

no code implementations29 Jan 2025 Ha-Yeong Choi, JaeHan Park

VoicePrompter is composed of (1) a factorization method that disentangles speech components and (2) a DiT-based conditional flow matching (CFM) decoder that conditions on these factorized features and voice prompts.

Decoder In-Context Learning +1

Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization

1 code implementation15 Aug 2024 Sang-Hoon Lee, Ha-Yeong Choi, Seong-Whan Lee

This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization.

Speech Synthesis

PeriodWave: Multi-Period Flow Matching for High-Fidelity Waveform Generation

1 code implementation14 Aug 2024 Sang-Hoon Lee, Ha-Yeong Choi, Seong-Whan Lee

Additionally, we utilize a multi-period estimator that avoids overlaps to capture different periodic features of waveform signals.

Speech Synthesis Text to Speech

HierVST: Hierarchical Adaptive Zero-shot Voice Style Transfer

no code implementations30 Jul 2023 Sang-Hoon Lee, Ha-Yeong Choi, Hyung-Seok Oh, Seong-Whan Lee

With a hierarchical adaptive structure, the model can adapt to a novel voice style and convert speech progressively.

Style Transfer Variational Inference

DDDM-VC: Decoupled Denoising Diffusion Models with Disentangled Representation and Prior Mixup for Verified Robust Voice Conversion

1 code implementation25 May 2023 Ha-Yeong Choi, Sang-Hoon Lee, Seong-Whan Lee

To address the above problem, this paper presents decoupled denoising diffusion models (DDDMs) with disentangled representations, which can control the style for each attribute in generative models.

Denoising Style Transfer +1

Cannot find the paper you are looking for? You can Submit a new open access paper.