paper-with-me

Papers

DiffWave: A Versatile Diffusion Model for Audio Synthesis

2020-09-21 · ICLR 2021 1 · Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, Bryan Catanzaro

In this work, we propose DiffWave, a versatile diffusion probabilistic model for conditional and unconditional waveform generation. The model is non-autoregressive, and converts the white noise signal into structured waveform through a Markov chain with a constant number of steps at synthesis. It is efficiently trained by optimizing a variant of variational bound on the data likelihood. DiffWave produces high-fidelity audios in different waveform generation tasks, including neural vocoding conditioned on mel spectrogram, class-conditional generation, and unconditional generation. We demonstrate that DiffWave matches a strong WaveNet vocoder in terms of speech quality (MOS: 4.44 versus 4.43), while synthesizing orders of magnitude faster. In particular, it significantly outperforms autoregressive and GAN-based waveform models in the challenging unconditional generation task in terms of audio quality and sample diversity from various automatic and human evaluations.

📄 PDF Abstract BibTeX arXiv:2009.09761

Code (11)

albertfgu/diffwave-sashimi pytorch
keonlee9420/DiffSinger pytorch
lmnt-com/diffwave pytorch
neillu23/DiffuSE pytorch
neillu23/cdiffuse pytorch
philsyn/diffwave-unconditional pytorch
philsyn/diffwave-vocoder pytorch
revsic/jax-variational-diffwave jax
revsic/tf-diffwave tf
revsic/torch-diffusion-wavegan pytorch
rf5/diffwave-unconditional pytorch

Tasks

Audio SynthesisDiversitymodelSpeech Synthesis

Methods 이 논문이 사용한 방법론

Diffusion Diffusion models generate samples by gradually removing noise from a signal, and their training objective can be expressed as a reweighted variational lower-bound…
Dilated Causal Convolution A Dilated Causal Convolution is a causal convolution where the filter is applied over an area larger than its length by…
Mixture of Logistic Distributions 설명 없음
WaveNet WaveNet is an audio generative model based on the PixelCNN architecture. In order to deal with long-range temporal dependencies…

Similar Papers 제목 키워드 기반

Towards the Synthesis of Non-speech Vocalizations

2024-10-12 · Enjamamul Hoq, Ifeoma Nwogu

In this report, we focus on the unconditional generation of infant cry sounds using the DiffWave framework, which has shown great promise in generating high-quality audio from noise. We use two distinct datasets of infan…

Diversity

Listen, Denoise, Action! Audio-Driven Motion Synthesis with Diffusion Models

2022-11-17 · Simon Alexanderson, Rajmund Nagy, Jonas Beskow, Gustav Eje Henter

Diffusion models have experienced a surge of interest as highly expressive yet efficiently trainable probabilistic models. We show that these models are an excellent fit for synthesising human motion that co-occurs with …

Gesture GenerationMotion Synthesis

BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis

2022-03-25 · ICLR 2022 4 · Max W. Y. Lam, Jun Wang, Dan Su, Dong Yu

Diffusion probabilistic models (DPMs) and their extensions have emerged as competitive generative models yet confront challenges of efficient sampling. We propose a new bilateral denoising diffusion model (BDDM) that par…

Image GenerationSpeech Synthesis

Restoring degraded speech via a modified diffusion model

2021-04-22 · Jianwei Zhang, Suren Jayasuriya, Visar Berisha

There are many deterministic mathematical operations (e.g. compression, clipping, downsampling) that degrade speech quality considerably. In this paper we introduce a neural network architecture, based on a modification …

model

A Study on Speech Enhancement Based on Diffusion Probabilistic Model

2021-07-25 · Yen-Ju Lu, Yu Tsao, Shinji Watanabe

Diffusion probabilistic models have demonstrated an outstanding capability to model natural images and raw audio waveforms through a paired diffusion and reverse processes. The unique property of the reverse process (nam…

Speech Enhancement