ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models

• URL: http://arxiv.org/abs/2607.09134v1
• Date: Fri, 10 Jul 2026 06:44:04 GMT
• Title: ReGen: Hierarchical Multi-Prompt Representation Generation for Efficient Waveform Diffusion Models
• Abstract summary: We propose ReGen that jointly estimates multiple vector fields for both representations data within a single diffusion model.<n>We also present ReGenVoice, a latent diffusion model (LDM)-based text-to-speech model that achieves strong speech intelligibility.
• Score: 22.63266813055847
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: Representation alignment (REPA) has been investigated to accelerate diffusion training, but we observe that regularizing intermediate representations in diffusion Transformers (DiT) may implicitly entangle latents and limit generative capacity. To address this issue, we propose ReGen, a hierarchical multi-prompt representation generation framework that jointly estimates multiple vector fields for both representations and data within a single diffusion model. We further introduce generalized flow matching (GFM) to improve the generalization of conditional flow matching (CFM). We validate ReGen on single-stage waveform diffusion models including neural audio codec and Wave-VAE. ReGen significantly improves waveform generation quality from highly compressed latent representations at 12.5 Hz. We also present ReGenVoice, a latent diffusion model (LDM)-based text-to-speech model that achieves strong speech intelligibility (WER) and speaker similarity (SIM) with a small dataset. Moreover, operating the LDM at 6.25 Hz with rich semantic and acoustic latent representation enables efficient training and sampling, requiring only 1 day of training on 4 GPUs and fast inference with an RTF of 0.08. Audio samples are available at https://regenvoice.github.io/demo/.

Related papers

• DiffusionGemma Technical Report [72.10570774996219]
  We introduce DiffusionGemma, a language model that uses discrete diffusion to generate text at exceptionally high speed.<n>Rather than decoding one token at a time, DiffusionGemma iteratively refines blocks of 256 tokens in parallel.<n>Our compute-efficient two-stage training pipeline uses fewer than 10% of the starting AR model's total training token budget.
  arXiv  Detail & Related papers  (2026-07-31T16:11:46Z)
• An Efficient vLLM-Based Inference Pipeline for Unified Audio Understanding and Generation [63.50393485685279]
  We present a vLLM-based inference pipeline for unified speech understanding and generation.<n>We overcome the shared intuition-Free Guidance (CFG) halves throughput.<n>By co-scheduling paired conditional and unconditional requests within a continuous batch, our CFG implementation sustains 80% of non-CFG throughput.
  arXiv  Detail & Related papers  (2026-07-02T12:55:11Z)
• Improving Progressive Generation with Decomposable Flow Matching [50.63174319509629]
  Decomposable Flow Matching (DFM) is a simple and effective framework for the progressive generation of visual media.<n>On Imagenet-1k 512px, DFM achieves 35.2% improvements in FDD scores over the base architecture and 26.4% over the best-performing baseline.
  arXiv  Detail & Related papers  (2025-06-24T17:58:02Z)
• 6G WavesFM: A Foundation Model for Sensing, Communication, and Localization [6.70088826174291]
  This paper introduces a novel Wireless Foundation Model (WFM) framework, capable of supporting a wide array of communication, sensing, and localization tasks.<n>Our proposed architecture combines a shared Vision Transformer (ViT) backbone with task-specific multi-layer perceptron heads and incorporates Low-Rank Adaptation (LoRA) for parameter-efficient fine-tuning.<n>We show that our unified WFM can support diverse tasks and deliver significant gains in both performance and efficiency.
  arXiv  Detail & Related papers  (2025-04-18T22:51:35Z)
• Accelerating High-Fidelity Waveform Generation via Adversarial Flow Matching Optimization [37.35829410807451]
  This paper introduces PeriodWave-Turbo, a high-fidelity and high-efficient waveform generation model via adversarial flow matching optimization. It only requires 1,000 steps of fine-tuning to achieve state-of-the-art performance across various objective metrics. By scaling up the backbone of PeriodWave from 29M to 70M parameters for improved generalization, PeriodWave-Turbo achieves unprecedented performance.
  arXiv  Detail & Related papers  (2024-08-15T08:34:00Z)
• Diffusion-Driven Semantic Communication for Generative Models with Bandwidth Constraints [66.63250537475973]
  This paper introduces a diffusion-driven semantic communication framework with advanced VAE-based compression for bandwidth-constrained generative model.<n>Our experimental results demonstrate significant improvements in pixel-level metrics like peak signal to noise ratio (PSNR) and semantic metrics like learned perceptual image patch similarity (LPIPS)
  arXiv  Detail & Related papers  (2024-07-26T02:34:25Z)
• Adversarial Training of Denoising Diffusion Model Using Dual Discriminators for High-Fidelity Multi-Speaker TTS [0.0]
  The diffusion model is capable of generating high-quality data through a probabilistic approach. It suffers from the drawback of slow generation speed due to the requirement of a large number of time steps. We propose a speech synthesis model with two discriminators: a diffusion discriminator for learning the distribution of the reverse process and a spectrogram discriminator for learning the distribution of the generated data.
  arXiv  Detail & Related papers  (2023-08-03T07:22:04Z)
• From Discrete Tokens to High-Fidelity Audio Using Multi-Band Diffusion [84.138804145918]
  Deep generative models can generate high-fidelity audio conditioned on various types of representations. These models are prone to generate audible artifacts when the conditioning is flawed or imperfect. We propose a high-fidelity multi-band diffusion-based framework that generates any type of audio modality from low-bitrate discrete representations.
  arXiv  Detail & Related papers  (2023-08-02T22:14:29Z)
• Boosting Fast and High-Quality Speech Synthesis with Linear Diffusion [85.54515118077825]
  This paper proposes a linear diffusion model (LinDiff) based on an ordinary differential equation to simultaneously reach fast inference and high sample quality. To reduce computational complexity, LinDiff employs a patch-based processing approach that partitions the input signal into small patches. Our model can synthesize speech of a quality comparable to that of autoregressive models with faster synthesis speed.
  arXiv  Detail & Related papers  (2023-06-09T07:02:43Z)
• Single Channel Speech Enhancement Using Temporal Convolutional Recurrent Neural Networks [23.88788382262305]
  temporal convolutional recurrent network (TCRN) is an end-to-end model that directly map noisy waveform to clean waveform. We show that our model is able to improve the performance of model, compared with existing convolutional recurrent networks.
  arXiv  Detail & Related papers  (2020-02-02T04:26:50Z)

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.