Pith. sign in

REVIEW 8 cited by

FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2204.09934 v1 pith:5PERJUKB submitted 2022-04-21 eess.AS cs.LGcs.SD

Rongjie Huang , Max W. Y. Lam , Jun Wang , Dan Su , Dong Yu , Yi Ren , Zhou Zhao This is my paper
classification eess.AScs.LGcs.SD
keywords fastdiffspeechsynthesisdiffusionmodelsamplingconditionalend-to-end
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Denoising diffusion probabilistic models (DDPMs) have recently achieved leading performances in many generative tasks. However, the inherited iterative sampling process costs hindered their applications to speech synthesis. This paper proposes FastDiff, a fast conditional diffusion model for high-quality speech synthesis. FastDiff employs a stack of time-aware location-variable convolutions of diverse receptive field patterns to efficiently model long-term time dependencies with adaptive conditions. A noise schedule predictor is also adopted to reduce the sampling steps without sacrificing the generation quality. Based on FastDiff, we design an end-to-end text-to-speech synthesizer, FastDiff-TTS, which generates high-fidelity speech waveforms without any intermediate feature (e.g., Mel-spectrogram). Our evaluation of FastDiff demonstrates the state-of-the-art results with higher-quality (MOS 4.28) speech samples. Also, FastDiff enables a sampling speed of 58x faster than real-time on a V100 GPU, making diffusion models practically applicable to speech synthesis deployment for the first time. We further show that FastDiff generalized well to the mel-spectrogram inversion of unseen speakers, and FastDiff-TTS outperformed other competing methods in end-to-end text-to-speech synthesis. Audio samples are available at \url{https://FastDiff.github.io/}.

Discussion (0). Sign in to comment.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. Improved Sample Complexity For Diffusion Model Training Without Empirical Risk Minimizer Access

    cs.LG 2025-05 conditional novelty 7.0 of 10

    The paper establishes an O(ε^{-4}) sample complexity bound for score estimation in diffusion models without requiring access to the empirical risk minimizer.

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

    cs.SD 2026-07 conditional novelty 6.5 of 10

    Hierarchical multi-prompt representation generation plus generalized flow matching yields high-quality single-stage waveform diffusion from 12.5 Hz latents and efficient LDM TTS.

  3. Score-Based Generative Modeling through Anisotropic Stochastic Partial Differential Equations

    cs.CE 2026-05 unverdicted novelty 6.0 of 10

    Anisotropic SPDEs preserve geometric data structure over longer timescales in score-based generative modeling, yielding better image quality than standard SDE baselines and flow matching in unconditional and condition...

  4. Post-Hoc Guidance for Consistency Models by Joint Flow Distribution Learning

    cs.LG 2026-04 unverdicted novelty 6.0 of 10

    JFDL allows pre-trained Consistency Models to perform guided image generation post-hoc by aligning flow distributions, reducing FID scores on CIFAR-10 and ImageNet without needing a teacher model.

  5. Occlusion-robust Stylization for Drawing-based 3D Animation

    cs.GR 2025-08 conditional novelty 6.0 of 10

    OSF uses flow-depth edge detection to provide occlusion-robust edge guidance for a single-stage stylization network, improving quality and speed in drawing-based 3D animation.

  6. SmoothSinger: A Conditional Diffusion Model for Singing Voice Synthesis with Multi-Resolution Architecture

    cs.SD 2025-06 conditional novelty 5.0 of 10

    A reference-guided diffusion model with a low-frequency upsampling module achieves marginal quality improvements over prior SVS baselines on Opencpop, with significant caveats about statistical significance and reprod...

  7. A Comparison of Generative and Discriminative Methods for Speech Enhancement: Robustness, Complexity, and Hallucination

    eess.AS 2026-06 unverdicted novelty 3.0 of 10

    Comparative analysis of generative versus discriminative speech enhancement models shows differences in robustness to noise, model complexity, convergence, and hallucination measured via word error rate and phoneme si...

  8. AT-ADD: All-Type Audio Deepfake Detection Challenge Evaluation Plan

    cs.SD 2026-04 unverdicted novelty 3.0 of 10

    AT-ADD introduces standardized tracks and datasets for evaluating audio deepfake detectors on speech under real-world conditions and on diverse unknown audio types to promote generalization beyond speech-centric methods.

Pith tools