Singing Voice Synthesis Based on Generative Adversarial Networks

By Yukiya Hono, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku, Keiichi Tokuda. 2019

59 citations recorded by the source corpus.

This paper proposes a generative adversarial training method for deep neural network (DNN)-based singing voice synthesis. The DNN-based approach has been used in statistical parametric singing voice synthesis and improved the naturalness of the synthesized singing voice [1]. Recently, generative adversarial networks (GANs) [2] have attracted significant attention in various machine learning research areas including speech synthesis [3]. GANs have achieved great success in modeling the distributions of complex data, and they have the potential to alleviate over-smoothing problem on the generated speech parameters in speech synthesis. In this paper, we propose a DNN-based singing voice synthesis system incorporating the GAN. Experimental results show that the proposed method outperforms the conventional method in the naturalness of the synthesized singing voice.

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

Citations in the corpus

A Survey on Neural Speech Synthesis (2021, methodology): “Due to page limitations, we only reviewed core algorithms of TTS; readers can refer to other papers for TTS related problems and applications, such as voice conversion [302], singing voice synthesis [112, 211, 35], talking face synthesis [36], etc.”
M4Singer: A Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus (2022, unknown): “…rapid development of deep learning and the continuous breakthroughs in TTS techniques [47; 23; 52; 37; 35; 36; 18], singing voice synthesis [45; 21; 14; 5; 38; 2; 27; 40; 9; 13; 10; 51; 17; 8; 43; 1; 22; 48; 54; 41; 19; 56; 53; 25] and its related tasks (e.g., SVC [33; 42; 24; 46; 55]) have…”
A Survey on Recent Deep Learning-driven Singing Voice Synthesis Systems (2021, background): “Over the past few years, several types of neural networks have been employed for SVS, such as generic deep neural networks (DNN) [17], convolutional neural networks [20], a recurrent neural network with long-short term memory (LSTM) [18], and generative adversarial networks (GAN) [19].”
WGANSing: A Multi-Voice Singing Voice Synthesizer Based on the Wasserstein-GAN (2019, methodology): “For singing voice synthesis, [15] uses a GAN-based architecture to model frame-wise vocoder features.”
XiaoiceSing: A High-Quality and Integrated Singing Voice Synthesis System (2020, methodology): “Generative adversarial network (GAN) [9] is also applied to feed-forward neural network for alleviating the over-smoothing effect.”
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis (2020, background): “There indeed exist some works using 44.1kHz or 48kHz sampling rate (Hono et al., 2019; Chandna et al., 2019; Wu et al., 2019; Nakamura et al., 2020; Lu et al., 2020).”