SpecGrad: Diffusion Probabilistic Model based Neural Vocoder with Adaptive Noise Spectral Shaping
Neural vocoder using denoising diffusion probabilistic model (DDPM) has been improved by adaptation of the diffusion noise distribution to given acoustic features. In this study, we propose SpecGrad that adapts the diffusion noise so that its time-varying spectral envelope becomes close to the conditioning log-mel spectrogram. This adaptation by time-varying filtering improves the sound quality especially in the high-frequency bands. It is processed in the time-frequency domain to keep the computational cost almost the same as the conventional DDPM-based neural vocoders. Experimental results showed that SpecGrad generates higher-fidelity speech waveform than conventional DDPM-based neural vocoders in both analysis-synthesis and speech enhancement scenarios. Audio demos are available at wavegrad.github.io/specgrad/.
Code (0)
등록된 구현이 없습니다.
Tasks
DenoisingSpeech EnhancementMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
PeriodGrad: Towards Pitch-Controllable Neural Vocoder Based on a Diffusion Probabilistic Model
This paper presents a neural vocoder based on a denoising diffusion probabilistic model (DDPM) incorporating explicit periodic signals as auxiliary conditioning signals. Recently, DDPM-based neural vocoders have gained p…
DenoisingPitch controlSinging Voice SynthesisPriorGrad: Improving Conditional Denoising Diffusion Models with Data-Dependent Adaptive Prior
Denoising diffusion probabilistic models have been recently proposed to generate high-quality samples by estimating the gradient of the data density. The framework defines the prior noise as a standard Gaussian distribut…
Audio GenerationDenoisingSpeech SynthesisText-To-Speech SynthesisWaveFit: An Iterative and Non-autoregressive Neural Vocoder based on Fixed-Point Iteration
Denoising diffusion probabilistic models (DDPMs) and generative adversarial networks (GANs) are popular generative models for neural vocoders. The DDPMs and GANs can be characterized by the iterative denoising framework …
DenoisingNU-Wave: A Diffusion Probabilistic Model for Neural Audio Upsampling
In this work, we introduce NU-Wave, the first neural audio upsampling model to produce waveforms of sampling rate 48kHz from coarse 16kHz or 24kHz inputs, while prior works could generate only up to 16kHz. NU-Wave is the…
Audio Super-ResolutionSuper-ResolutionInferGrad: Improving Diffusion Models for Vocoder by Considering Inference in Training
Denoising diffusion probabilistic models (diffusion models for short) require a large number of iterations in inference to achieve the generation quality that matches or surpasses the state-of-the-art generative models, …
Denoising