Singing Voice Synthesis Using Deep Autoregressive Neural Networks For Acoustic Modeling

Abstract

This paper presents a method of using autoregressive neural networks for the acoustic modeling of singing voice synthesis (SVS). Singing voice differs from speech and it contains more local dynamic movements of acoustic features, e.g., vibratos. Therefore, our method adopts deep autoregressive (DAR) models to predict the F0 and spectral features of singing voice in order to better describe the dependencies among the acoustic features of consecutive frames. For F0 modeling, discretized F0 values are used and the influences of the history length in DAR are analyzed by experiments. An F0 post-processing strategy is also designed to alleviate the inconsistency between the predicted F0 contours and the F0 values determined by music notes. Furthermore, we extend the DAR model to deal with continuous spectral features, and a prenet module with self-attention layers is introduced to process historical frames. Experiments on a Chinese singing voice corpus demonstrate that our method using DARs

Stats

• citations20
• S2 citations—
• github stars0
• HF likes0
• heat score9.92
• arxiv keyyi2019singing

Related papers

• Visinger2+: End-to-end Singing Voice Synthesis Augmented By Self-supervised Learning Representation (2024)4.52
• Singgan: Generative Adversarial Network For High-fidelity Singing Voice Generation (2021)10.61
• NNSVS: A Neural Network-based Singing Voice Synthesis Toolkit (2022)13.83
• Singing Voice Synthesis Based On Convolutional Neural Networks (2019)0.00
• Mandarin Singing Voice Synthesis With Denoising Diffusion Probabilistic Wasserstein GAN (2022)6.34
• Bytesing: A Chinese Singing Voice Synthesis System Using Duration Allocated Encoder-decoder Acoustic Models And Wavernn Vocoders (2020)11.49
• Visinger: Variational Inference With Adversarial Learning For End-to-end Singing Voice Synthesis (2021)12.99
• Diffsinger: Singing Voice Synthesis Via Shallow Diffusion Mechanism (2021)23.76