paper-with-me

홈 › Papers

KaraSinger: Score-Free Singing Voice Synthesis with VQ-VAE using Mel-spectrograms

2021-10-08 · Chien-Feng Liao, Jen-Yu Liu, Yi-Hsuan Yang

In this paper, we propose a novel neural network model called KaraSinger for a less-studied singing voice synthesis (SVS) task named score-free SVS, in which the prosody and melody are spontaneously decided by machine. KaraSinger comprises a vector-quantized variational autoencoder (VQ-VAE) that compresses the Mel-spectrograms of singing audio to sequences of discrete codes, and a language model (LM) that learns to predict the discrete codes given the corresponding lyrics. For the VQ-VAE part, we employ a Connectionist Temporal Classification (CTC) loss to encourage the discrete codes to carry phoneme-related information. For the LM part, we use location-sensitive attention for learning a robust alignment between the input phoneme sequence and the output discrete code. We keep the architecture of both the VQ-VAE and LM light-weight for fast training and inference speed. We validate the effectiveness of the proposed design choices using a proprietary collection of 550 English pop songs sung by multiple amateur singers. The result of a listening test shows that KaraSinger achieves high scores in intelligibility, musicality, and the overall quality.

📄 PDF Abstract BibTeX arXiv:2110.04005

Code (0)

등록된 구현이 없습니다.

Tasks

Language ModelingLanguage ModellingSinging Voice Synthesis

Methods 이 논문이 사용한 방법론

Test 설명 없음
VQ-VAE VQ-VAE is a type of variational autoencoder that uses vector quantisation to obtain a discrete latent representation. It differs from…

Similar Papers 제목 키워드 기반

Score and Lyrics-Free Singing Voice Generation

2019-12-26 · Jen-Yu Liu, Yu-Hua Chen, Yin-Cheng Yeh, Yi-Hsuan Yang

Generative models for singing voice have been mostly concerned with the task of ``singing voice synthesis,'' i.e., to produce singing voice waveforms given musical scores and text lyrics. In this work, we explore a novel…

Audio GenerationSinging Voice Synthesis

MakeSinger: A Semi-Supervised Training Method for Data-Efficient Singing Voice Synthesis via Classifier-free Diffusion Guidance

2024-06-10 · Semin Kim, Myeonghun Jeong, Hyeonseung Lee, Minchan Kim 외

In this paper, we propose MakeSinger, a semi-supervised training method for singing voice synthesis (SVS) via classifier-free diffusion guidance. The challenge in SVS lies in the costly process of gathering aligned sets …

Singing Voice Synthesistext-to-speechText to Speech

M4Singer: a Multi-Style, Multi-Singer and Musical Score Provided Mandarin Singing Corpus

2022-12-29 · NIPS 2022 12 · Lichao Zhang, RuiQi Li, Shoutong Wang, Liqun Deng 외

The lack of publicly available high-quality and accurately labeled datasets has long been a major bottleneck for singing voice synthesis (SVS). To tackle this problem, we present M4Singer, a free-to-use Multi-style, Mult…

Music TranscriptionSinging Voice SynthesisVoice Conversion

Singing voice synthesis based on convolutional neural networks

2019-04-15 · Kazuhiro Nakamura, Kei Hashimoto, Keiichiro Oura, Yoshihiko Nankaku 외

The present paper describes a 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…

Singing Voice Synthesis

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

2019-10-24 · Kazuhiro Nakamura, Shinji Takaki, Kei Hashimoto, Keiichiro Oura 외

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 n…

Singing Voice Synthesis