Filters








213 Hits in 5.7 sec

Adversarially Trained End-to-end Korean Singing Voice Synthesis System [article]

Juheon Lee, Hyeong-Seok Choi, Chang-Bin Jeon, Junghyun Koo, Kyogu Lee
2019 arXiv   pre-print
In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning  ...  of text and pitch to the super-resolution network, and 3) conditional adversarial training.  ...  Conclusions In this paper, we proposed the end-to-end Korean singing vocie synthesis system.  ... 
arXiv:1908.01919v1 fatcat:322co346tffcvohc6dcajoulj4

Adversarially Trained End-to-End Korean Singing Voice Synthesis System

Juheon Lee, Hyeong-Seok Choi, Chang-Bin Jeon, Junghyun Koo, Kyogu Lee
2019 Interspeech 2019  
In this paper, we propose an end-to-end Korean singing voice synthesis system from lyrics and a symbolic melody using the following three novel approaches: 1) phonetic enhancement masking, 2) local conditioning  ...  of text and pitch to the superresolution network, and 3) conditional adversarial training.  ...  Conclusions In this paper, we proposed the end-to-end Korean singing vocie synthesis system.  ... 
doi:10.21437/interspeech.2019-1722 dblp:conf/interspeech/LeeCJKL19 fatcat:uz3ekgg24zeerczcewvjmfbx5a

N-Singer: A Non-Autoregressive Korean Singing Voice Synthesis System for Pronunciation Enhancement [article]

Gyeong-Hoon Lee, Tae-Woo Kim, Hanbin Bae, Min-Ji Lee, Young-Ik Kim, Hoon-Young Cho
2022 arXiv   pre-print
Recently, end-to-end Korean singing voice systems have been designed to generate realistic singing voices.  ...  In this paper, we propose N-Singer, a non-autoregressive Korean singing voice system, to synthesize accurate and pronounced Korean singing voices in parallel.  ...  The adversarially trained end-to-end Korean SVS system (ATK) [2] has shown the best performance among Korean SVS systems [1] [2] [3] .  ... 
arXiv:2106.15205v2 fatcat:6zikmdahkfa67pjbdym3zqbppi

A Melody-Unsupervision Model for Singing Voice Synthesis [article]

Soonbeom Choi, Juhan Nam
2022 arXiv   pre-print
The proposed model is composed of a phoneme classifier and a singing voice generator jointly trained in an end-to-end manner.  ...  One of the main issues in training singing voice synthesis models is that they require melody and lyric labels to be temporally aligned with audio data.  ...  We compared our model to the adversarially trained end-to-end Korean SVS model (ATK) [12] as a reference.  ... 
arXiv:2110.06546v2 fatcat:ren3oknserelvn62ysct2y5q74

SUSing: SU-net for Singing Voice Synthesis [article]

Xulong Zhang, Jianzong Wang, Ning Cheng, Jing Xiao
2022 arXiv   pre-print
In this paper, we proposed SU-net for singing voice synthesis named SUSing. Synthesizing singing voice is treated as a translation task between lyrics and music score and spectrum.  ...  Singing voice synthesis is a generative task that involves multi-dimensional control of the singing model, including lyrics, pitch, and duration, and includes the timbre of the singer and singing skills  ...  In this paper, we propose an end-to-end singing voice synthesis method with a Striped U-net (SU-net).  ... 
arXiv:2205.11841v1 fatcat:eaqmugcyk5elfaakkwkoxiiqia

Rapping-Singing Voice Synthesis based on Phoneme-level Prosody Control [article]

Konstantinos Markopoulos, Nikolaos Ellinas, Alexandra Vioni, Myrsini Christidou, Panos Kakoulidis, Georgios Vamvoukakis, Georgia Maniati, June Sig Sung, Hyoungmin Park, Pirros Tsiakoulis, Aimilios Chalamandaris
2021 arXiv   pre-print
In this paper, a text-to-rapping/singing system is introduced, which can be adapted to any speaker's voice.  ...  The proposed system is evaluated via subjective listening tests as well as in comparison to an available alternate system which also aims to produce synthetic singing voice from read-only training data  ...  trained, pitch conditioned sequence-to-sequence Korean singing model [11] .  ... 
arXiv:2111.09146v1 fatcat:fonznraxrvcu7kvaxubkmpe35m

Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus [article]

Rongjie Huang, Feiyang Chen, Yi Ren, Jinglin Liu, Chenye Cui, Zhou Zhao
2021 arXiv   pre-print
High-fidelity multi-singer singing voice synthesis is challenging for neural vocoder due to the singing voice data shortage, limited singer generalization, and large computational cost.  ...  To accelerate singing voice researches in the community, we release a large-scale, multi-singer Chinese singing voice dataset OpenSinger.  ...  Choi at all [6] build a Korean singing voice synthesis system using an autoregressive algorithm that generates spectrogram with the boundary equilibrium GAN objective.  ... 
arXiv:2112.10358v1 fatcat:nmnbeshurbb7xlhlvki4ogguye

MLP Singer: Towards Rapid Parallel Korean Singing Voice Synthesis [article]

Jaesung Tae, Hyeongju Kim, Younggun Lee
2021 arXiv   pre-print
However, prominent neural singing voice synthesis systems suffer from slow inference speed due to their autoregressive design.  ...  Inspired by MLP-Mixer, a novel architecture introduced in the vision literature for attention-free image classification, we propose MLP Singer, a parallel Korean singing voice synthesis system.  ...  CONCLUSION We present MLP Singer, an all-MLP parallel Korean singing voice synthesis system.  ... 
arXiv:2106.07886v2 fatcat:zgn4upopl5ecxnt6pz6puvw5we

U-Singer: Multi-Singer Singing Voice Synthesizer that Controls Emotional Intensity [article]

Sungjae Kim, Kihyun Na, Choonghyeon Lee, Jehyeon An, Injung Kim
2022 arXiv   pre-print
in the training data.  ...  During synthesizing singing voices according to the lyrics, pitch, and duration of the music score, U-Singer reflects singer characteristics and emotional intensity by adding variances in pitch, energy  ...  Introduction The singing voice synthesis (SVS) system is a generative model that synthesizes singing voices from the lyric, note pitch, and note duration of the music score.  ... 
arXiv:2203.00931v1 fatcat:s7lk5lq27bdgnapqyp57saaa5a

A Survey on Recent Deep Learning-driven Singing Voice Synthesis Systems [article]

Yin-Ping Cho, Fu-Rong Yang, Yung-Chuan Chang, Ching-Ting Cheng, Xiao-Han Wang, Yi-Wen Liu
2021 arXiv   pre-print
Singing voice synthesis (SVS) is a task that aims to generate audio signals according to musical scores and lyrics.  ...  This paper aims to review some of the state-of-the-art deep learning-driven SVS systems.  ...  INTRODUCTION A singing voice synthesis (SVS) system is able to generate singing voice from a given musical score.  ... 
arXiv:2110.02511v1 fatcat:4ou5xepnjbg2todhfu3vrn7p44

Muskits: an End-to-End Music Processing Toolkit for Singing Voice Synthesis [article]

Jiatong Shi, Shuai Guo, Tao Qian, Nan Huo, Tomoki Hayashi, Yuning Wu, Frank Xu, Xuankai Chang, Huazhe Li, Peter Wu, Shinji Watanabe, Qin Jin
2022 arXiv   pre-print
This paper introduces a new open-source platform named Muskits for end-to-end music processing, which mainly focuses on end-to-end singing voice synthesis (E2E-SVS).  ...  In addition, we also demonstrate several advanced usages based on the toolkit functionalities, including multilingual training and transfer learning.  ...  Introduction Singing voice synthesis (SVS) uses music score and lyrics to generate natural singing voices of a target singer.  ... 
arXiv:2205.04029v1 fatcat:pp7ozdwwdzgqvgjqnxjpyetqpy

A Comprehensive Survey on Deep Music Generation: Multi-level Representations, Algorithms, Evaluations, and Future Directions [article]

Shulei Ji, Jing Luo, Xinyu Yang
2020 arXiv   pre-print
Especially music, the topic of this paper, has attracted widespread attention of countless researchers.The whole process of producing music can be divided into three stages, corresponding to the three  ...  This paper attempts to provide an overview of various composition tasks under different music generation levels, covering most of the currently popular music generation tasks using deep learning.  ...  [89] proposed a Korean singing voice synthesis system based on LSTM-RNN, and focused on a novel feature synthesis method based on Korean syllable structure, including linguistic features and musical  ... 
arXiv:2011.06801v1 fatcat:cixou3d2jzertlcpb7kb5x5ery

Hybrid Reality: The Rise of Deepfakes and Diverging Truths

Miriam Meckel, Léa Steinacker
2021 Morals & Machines  
We synthesize implications and conclude with recommendations for how to reach a new consensus on the construction of reality.  ...  We argue that this development contributes to a "hybrid reality", a construct of both human perception and technologically driven fabrications.  ...  A synthetic video of a Hollywood actor can be used to congratulate friends on their birthday, or the user can sing "My heart will go on" in the voice of Celine Dion.  ... 
doi:10.5771/2747-5182-2021-1-10 fatcat:tmcjex73uzbxbjlkehvvgmihpm

Hybrid Reality: The Rise of Deepfakes and Diverging Truths

Miriam Meckel, Léa Steinacker
2021 Morals & Machines  
We synthesize implications and conclude with recommendations for how to reach a new consensus on the construction of reality.  ...  We argue that this development contributes to a "hybrid reality", a construct of both human perception and technologically driven fabrications.  ...  A synthetic video of a Hollywood actor can be used to congratulate friends on their birthday, or the user can sing "My heart will go on" in the voice of Celine Dion.  ... 
doi:10.5771/2747-5174-2021-1-10 fatcat:tf4ru5yaybc3tl3ecpcz37mrwy

Hybrid Reality: The Rise of Deepfakes and Diverging Truths

Miriam Meckel, Léa Steinacker
2021 Morals & Machines  
We synthesize implications and conclude with recommendations for how to reach a new consensus on the construction of reality.  ...  We argue that this development contributes to a "hybrid reality", a construct of both human perception and technologically driven fabrications.  ...  A synthetic video of a Hollywood actor can be used to congratulate friends on their birthday, or the user can sing "My heart will go on" in the voice of Celine Dion.  ... 
doi:10.5771/2747-5182-2021-1-12 fatcat:gm5q3yiqg5ep7c7kyr3dmd7ley
« Previous Showing results 1 — 15 out of 213 results