Fast and High-Quality Singing Voice Synthesis System based on Convolutional Neural Networks

10/24/2019
by   Kazuhiro Nakamura, et al.
0

The present paper describes singing voice synthesis based on convolutional neural networks (CNNs). Singing voice synthesis systems based on deep neural networks (DNNs) are currently being proposed and are improving the naturalness of synthesized singing voices. As singing voices represent a rich form of expression, a powerful technique to model them accurately is required. In the proposed technique, long-term dependencies of singing voices are modeled by CNNs. An acoustic feature sequence is generated for each segment that consists of long-term frames, and a natural trajectory is obtained without the parameter generation algorithm. Furthermore, a computational complexity reduction technique, which drives the DNNs in different time units depending on type of musical score features, is proposed. Experimental results show that the proposed method can synthesize natural sounding singing voices much faster than the conventional method.

READ FULL TEXT

page 1

page 2

page 3

page 4

research
04/15/2019

Singing voice synthesis based on convolutional neural networks

The present paper describes a singing voice synthesis based on convoluti...
research
08/05/2021

Sinsy: A Deep Neural Network-Based Singing Voice Synthesis System

This paper presents Sinsy, a deep neural network (DNN)-based singing voi...
research
07/12/2017

Score-informed syllable segmentation for a cappella singing voice with convolutional neural networks

This paper introduces a new score-informed method for the segmentation o...
research
10/15/2018

The Trajectory of Voice Onset Time with Vocal Aging

Vocal aging, a universal process of human aging, can largely affect one'...
research
07/13/2023

Real-time Percussive Technique Recognition and Embedding Learning for the Acoustic Guitar

Real-time music information retrieval (RT-MIR) has much potential to aug...
research
10/08/2020

Tatum-Level Drum Transcription Based on a Convolutional Recurrent Neural Network with Language Model-Based Regularized Training

This paper describes a neural drum transcription method that detects fro...
research
02/09/2019

Generative Moment Matching Network-based Random Modulation Post-filter for DNN-based Singing Voice Synthesis and Neural Double-tracking

This paper proposes a generative moment matching network (GMMN)-based po...

Please sign up or login with your details

Forgot password? Click here to reset