Multi-speaker singing voice synthesis is to generate the singing voice sung by different speakers. To generalize to new speakers, previous zero-shot singing adaptation methods obtain the timbre of the target speaker with a fixed-size embedding from single reference audio. However, they face several challenges: 1) the fixed-size speaker embedding is not powerful enough to capture full details of the target timbre; 2) single reference audio does not contain sufficient timbre information of the target speaker; 3) the pitch inconsistency between different speakers also leads to a degradation in the generated voice. In this paper, we propose a new model called MR-SVS to tackle these problems. Specifically, we employ both a multi-reference encoder and a fixed-size encoder to encode the timbre of the target speaker from multiple reference audios. The Multi-reference encoder can capture more details and variations of the target timbre. Besides, we propose a well-designed pitch shift method to address the pitch inconsistency problem. Experiments indicate that our method outperforms the baseline method both in naturalness and similarity.
Renmin University of China（中国人民大学）；Carnegie Mellon University（卡内基梅隆大学）；Johns Hopkins University（约翰斯·霍普金斯大学）
Singing voice synthesis (SVS), as a specific task for generating the vocal singing voice from a music score, has drawn much attention in recent years. SVS faces the challenge that the singing has various pronunciation flexibility conditioned on the same music score. Most of the previous works of SVS can not well handle the misalignment between the music score and actual singing. In this paper, we propose an acoustic feature processing strategy, named PHONEix, with a phoneme distribution predictor, to alleviate the gap between the music score and the singing voice, which can be easily adopted i…
Singing Voice Data Scaling-up: An Introduction to ACE-Opencpop and ACE-KiSing
Carnegie Mellon University（卡内基梅隆大学）；Duke Kunshan University（昆山杜克大学）；Cornell University（康奈尔大学）；Multimodal Art Projection Community（多模态艺术投影社区）；Renmin University of China（中国人民大学）；Georgia Institute of Technology（佐治亚理工学院）
DNN-based ensemble singing voice synthesis with interactions between singers
The University of Tokyo（东京大学）；Keio University（庆应义塾大学）；National Institute of Advanced Industrial Science and Technology (AIST)（国立先进工业科学技术研究所（AIST））；Meiji University（明治大学）
Renmin University of China（中国人民大学）；Carnegie Mellon University（卡内基梅隆大学）
Deep learning based singing voice synthesis (SVS) systems have been demonstrated to flexibly generate singing with better qualities, compared to conventional statistical parametric based methods. However, neural systems are generally data-hungry and have difficulty to reach reasonable singing quality with limited public available training data. In this work, we explore different data augmentation methods to boost the training of SVS systems, including several strategies customized to SVS based on pitch augmentation and mix-up augmentation. To further stabilize the training, we introduce the cy…
Meiji University（明治大学）；The University of Tokyo（东京大学）
This paper presents a free Japanese singing voice corpus that can be used for highly applicable and reproducible singing voice synthesis research. A singing voice corpus helps develop singing voice synthesis, but existing corpora have two critical problems: data imbalance (singing voice corpora do not guarantee phoneme balance, unlike speaking-voice corpora) and copyright issues (cannot legally share data). As a way to avoid these problems, we constructed a PJS (phoneme-balanced Japanese singing voice) corpus that guarantees phoneme balance and is licensed with CC BY-SA 4.0, and we composed me…
National Tsing Hua University（国立清华大学）；Research Center for Information Technology Innovation, Academia Sinica（中央研究院资讯科技创新研究中心）；Institute of Information Science, Academia Sinica（中央研究院资讯科学研究所）
Singing voice synthesis (SVS) is the computer production of a human-like singing voice from given musical scores. To accomplish end-to-end SVS effectively and efficiently, this work adopts the acoustic model-neural vocoder architecture established for high-quality speech and singing voice synthesis. Specifically, this work aims to pursue a higher level of expressiveness in synthesized voices by combining the diffusion denoising probabilistic model (DDPM) and \emph{Wasserstein} generative adversarial network (WGAN) to construct the backbone of the acoustic model. On top of the proposed acoustic…
Graduate School of Information Science and Technology, The University of Tokyo（东京大学信息科学与技术研究生院）
Thanks to developments in machine learning techniques, it has become possible to synthesize high-quality singing voices of a single singer. An open multispeaker singing-voice corpus would further accelerate the research in singing-voice synthesis. However, conventional singing-voice corpora only consist of the singing voices of a single singer. We designed a Japanese multispeaker singing-voice corpus called "JVS-MuSiC" with the aim to analyze and synthesize a variety of voices. The corpus consists of 100 singers' recordings of the same song, Katatsumuri, which is a Japanese children's song. It…
This paper presents Sinsy, a deep neural network (DNN)-based singing voice synthesis (SVS) system. In recent years, DNNs have been utilized in statistical parametric SVS systems, and DNN-based SVS systems have demonstrated better performance than conventional hidden Markov model-based ones. SVS systems are required to synthesize a singing voice with pitch and timing that strictly follow a given musical score. Additionally, singing expressions that are not described on the musical score, such as vibrato and timing fluctuations, should be reproduced. The proposed system is composed of four modul…
Carnegie Mellon University（卡内基梅隆大学）；Renmin University of China（中国人民大学）；The University of Hong Kong（香港大学）；Human Dataware Lab. Co., Ltd.（人类数据仓库实验室有限公司）；Nagoya University（名古屋大学）；Tsinghua University（清华大学）；University of California, Berkeley（加州大学伯克利分校）
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). Muskits supports state-of-the-art SVS models, including RNN SVS, transformer SVS, and XiaoiceSing. The design of Muskits follows the style of widely-used speech processing toolkits, ESPnet and Kaldi, for data prepossessing, training, and recipe pipelines. To the best of our knowledge, this toolkit is the first platform that allows a fair and highly-reproducible comparison between several published works in SVS. In addition, we als…
Towards Improving the Expressiveness of Singing Voice Synthesis with BERT Derived Semantic Information
Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Huya Inc.（虎牙公司）；The Chinese University of Hong Kong（香港中文大学）；XVerse Inc.（XVerse公司）
Fudan University（复旦大学）；Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）；National Institute of Informatics（国立信息学研究所）
Singing voice detection (SVD), to recognize vocal parts in the song, is an essential task in music information retrieval (MIR). The task remains challenging since singing voice varies and intertwines with the accompaniment music, especially for some complicated polyphonic music such as choral music recordings. To address this problem, we investigate singing voice detection while discarding the interference from the accompaniment. The proposed SVD has two steps: i. The singing voice separation (SVS) technique is first utilized to filter out the singing voice's potential part coarsely. ii. Upon …
Separating two sources from an audio mixture is an important task with many applications. It is a challenging problem since only one signal channel is available for analysis. In this paper, we propose a novel framework for singing voice separation using the generative adversarial network (GAN) with a time-frequency masking function. The mixture spectra is considered to be a distribution and is mapped to the clean spectra which is also considered a distribtution. The approximation of distributions between mixture spectra and clean spectra is performed during the adversarial training process. In…
MINDsLab Inc.（MINDsLab公司）；Seoul National University（首尔大学）
We propose a singing decomposition system that encodes time-aligned linguistic content, pitch, and source speaker identity via Assem-VC. With decomposed speaker-independent information and the target speaker's embedding, we could synthesize the singing voice of the target speaker. In conclusion, we made a perfectly synced duet with the user's singing voice and the target singer's converted singing voice.
Academia Sinica（中央研究院）；National Taiwan University of Science and Technology（台湾科技大学）
The purpose of this study is to investigate how humans interpret musical scores expressively, and then design machines that sing like humans. We consider six factors that have a strong influence on the expression of human singing. The factors are related to the acoustic, phonetic, and musical features of a real singing signal. Given real singing voices recorded following the MIDI scores and lyrics, our analysis module can extract the expression parameters from the real singing signals semi-automatically. The expression parameters are used to control the singing voice synthesis (SVS) system for…
This paper aims to introduce a robust singing voice synthesis (SVS) system to produce very natural and realistic singing voices efficiently by leveraging the adversarial training strategy. On one hand, we designed simple but generic random area conditional discriminators to help supervise the acoustic model, which can effectively avoid the over-smoothed spectrogram prediction and improve the expressiveness of SVS. On the other hand, we subtly combined the spectrogram with the frame-level linearly-interpolated F0 sequence as the input for the neural vocoder, which is then optimized with the hel…
Singing voice synthesis has been paid rising attention with the rapid development of speech synthesis area. In general, a studio-level singing corpus is usually necessary to produce a natural singing voice from lyrics and music-related transcription. However, such a corpus is difficult to collect since it's hard for many of us to sing like a professional singer. In this paper, we propose an approach -- Learn2Sing that only needs a singing teacher to generate the target speakers' singing voice without their singing voice data. In our approach, a teacher's singing corpus and speech from multiple…
This paper proposes singing voice synthesis (SVS) based on frame-level sequence-to-sequence models considering vocal timing deviation. In SVS, it is essential to synchronize the timing of singing with temporal structures represented by scores, taking into account that there are differences between actual vocal timing and note start timing. In many SVS systems including our previous work, phoneme-level score features are converted into frame-level ones on the basis of phoneme boundaries obtained by external aligners to take into account vocal timing deviations. Therefore, the sound quality is a…
Shanghai University（上海大学）；JD AI Research（京东人工智能研究院）；Shanghai Conservatory of Music（上海音乐学院）
This paper proposes an expressive singing voice synthesis system by introducing explicit vibrato modeling and latent energy representation. Vibrato is essential to the naturalness of synthesized sound, due to the inherent characteristics of human singing. Hence, a deep learning-based vibrato model is introduced in this paper to control the vibrato's likeliness, rate, depth and phase in singing, where the vibrato likeliness represents the existence probability of vibrato and it would help improve the singing voice's naturalness. Actually, there is no annotated label about vibrato likeliness in …
Tongji University（同济大学）；Shanghai Institute of Visual Arts（上海视觉艺术学院）；Northwestern Polytechnical University（西北工业大学）；NetEase Inc.（网易公司）
This paper introduces Opencpop, a publicly available high-quality Mandarin singing corpus designed for singing voice synthesis (SVS). The corpus consists of 100 popular Mandarin songs performed by a female professional singer. Audio files are recorded with studio quality at a sampling rate of 44,100 Hz and the corresponding lyrics and musical scores are provided. All singing recordings have been phonetically annotated with phoneme boundaries and syllable (note) boundaries. To demonstrate the reliability of the released data and to provide a baseline for future research, we built baseline deep …
Recently, end-to-end Korean singing voice systems have been designed to generate realistic singing voices. However, these systems still suffer from a lack of robustness in terms of pronunciation accuracy. In this paper, we propose N-Singer, a non-autoregressive Korean singing voice system, to synthesize accurate and pronounced Korean singing voices in parallel. N-Singer consists of a Transformer-based mel-generator, a convolutional network-based postnet, and voicing-aware discriminators. It can contribute in the following ways. First, for accurate pronunciation, N-Singer separately models ling…
Ping An Technology (Shenzhen) Co., Ltd.（平安科技（深圳）有限公司）
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 such as vibrato. 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. The lyrics and music score information is encoded into a two-dimensional feature representation through the convolution layer. The two-dimensional feature and its frequency spectrum are mapped to the…
NLPR, Institute of Automation, Chinese Academy of Sciences（中国科学院自动化研究所自然语言处理实验室）；School of Artificial Intelligence, University of Chinese Academy of Sciences（中国科学院大学人工智能学院）；CAS Center for Excellence in Brain Science and Intelligence Technology（中国科学院脑科学与智能技术卓越创新中心）
End-to-end singing voice synthesis (SVS) is attractive due to the avoidance of pre-aligned data. However, the auto learned alignment of singing voice with lyrics is difficult to match the duration information in musical score, which will lead to the model instability or even failure to synthesize voice. To learn accurate alignment information automatically, this paper proposes an end-to-end SVS framework, named Singing-Tacotron. The main difference between the proposed framework and Tacotron is that the speech can be controlled significantly by the musical score's duration information. Firstly…
Zhejiang University（浙江大学）；Microsoft Research Asia（微软亚洲研究院）；Microsoft STC Asia（微软亚洲互联网工程院）
In this paper, we develop DeepSinger, a multi-lingual multi-singer singing voice synthesis (SVS) system, which is built from scratch using singing training data mined from music websites. The pipeline of DeepSinger consists of several steps, including data crawling, singing and accompaniment separation, lyrics-to-singing alignment, data filtration, and singing modeling. Specifically, we design a lyrics-to-singing alignment model to automatically extract the duration of each phoneme in lyrics starting from coarse-grained sentence level to fine-grained phoneme level, and further design a multi-l…
We propose a novel unsupervised singing voice detection method which use single-channel Blind Audio Source Separation (BASS) algorithm as a preliminary step. To reach this goal, we investigate three promising BASS approaches which operate through a morphological filtering of the analyzed mixture spectrogram. The contributions of this paper are manyfold. First, the investigated BASS methods are reworded with the same formalism and we investigate their respective hyperparameters by numerical simulations. Second, we propose an extension of the KAM method for which we propose a novel training algo…
Johns Hopkins University（约翰霍普金斯大学）；Renmin University of China（中国人民大学）
The neural network (NN) based singing voice synthesis (SVS) systems require sufficient data to train well and are prone to over-fitting due to data scarcity. However, we often encounter data limitation problem in building SVS systems because of high data acquisition and annotation costs. In this work, we propose a Perceptual Entropy (PE) loss derived from a psycho-acoustic hearing model to regularize the network. With a one-hour open-source singing voice database, we explore the impact of the PE loss on various mainstream sequence-to-sequence models, including the RNN-based, transformer-based,…
Muskits-ESPnet: A Comprehensive Toolkit for Singing Voice Synthesis in New Paradigm
Renmin University of China（中国人民大学）；Carnegie Mellon University（卡内基梅隆大学）；Georgia Institute of Technology（佐治亚理工学院）；Duke Kunshan University（昆山杜克大学）；Cornell University（康奈尔大学）
In the recent years, singing voice separation systems showed increased performance due to the use of supervised training. The design of training datasets is known as a crucial factor in the performance of such systems. We investigate on how the characteristics of the training dataset impacts the separation performances of state-of-the-art singing voice separation algorithms. We show that the separation quality and diversity are two important and complementary assets of a good training dataset. We also provide insights on possible transforms to perform data augmentation for this task.
Music and Audio Research Group (MARG), Seoul National University（首尔国立大学音乐与音频研究组（MARG））；supertone Inc.（supertone公司）
This paper proposes a controllable singing voice synthesis system capable of generating expressive singing voice with two novel methodologies. First, a local style token module, which predicts frame-level style tokens from an input pitch and text sequence, is proposed to allow the singing voice system to control musical expression often unspecified in sheet music (e.g., breathing and intensity). Second, we propose a dual-path pitch encoder with a choice of two different pitch inputs: MIDI pitch sequence or f0 contour. Because the initial generation of a singing voice is usually executed by tak…
Fraunhofer-IDMT（弗劳恩霍夫数字媒体技术研究所）；Tampere University（坦佩雷大学）；Technical University of Ilmenau（伊尔梅瑙工业大学）
In this work, we present a method for learning interpretable music signal representations directly from waveform signals. Our method can be trained using unsupervised objectives and relies on the denoising auto-encoder model that uses a simple sinusoidal model as decoding functions to reconstruct the singing voice. To demonstrate the benefits of our method, we employ the obtained representations to the task of informed singing voice separation via binary masking, and measure the obtained separation quality by means of scale-invariant signal to distortion ratio. Our findings suggest that our me…
Music source separation is important for applications such as karaoke and remixing. Much of previous research focuses on estimating short-time Fourier transform (STFT) magnitude and discarding phase information. We observe that, for singing voice separation, phase can make considerable improvement in separation quality. This paper proposes a complex ratio masking method for voice and accompaniment separation. The proposed method employs DenseUNet with self attention to estimate the real and imaginary components of STFT for each sound source. A simple ensemble technique is introduced to further…
Music information retrieval is currently an active research area that addresses the extraction of musically important information from audio signals, and the applications of such information. The extracted information can be used for search and retrieval of music in recommendation systems, or to aid musicological studies or even in music learning. Sophisticated signal processing techniques are applied to convert low-level acoustic signal properties to musical attributes which are further embedded in a rule-based or statistical classification framework to link with high-level descriptions such …
Beijing Bombax XiaoIce Technology Co., Ltd（北京木棉小冰科技有限公司）；National Institute of Informatics（国立信息学研究所）；SOKENDAI（综合研究大学院大学）
XiaoiceSing is a singing voice synthesis (SVS) system that aims at generating 48kHz singing voices. However, the mel-spectrogram generated by it is over-smoothing in middle- and high-frequency areas due to no special design for modeling the details of these parts. In this paper, we propose XiaoiceSing2, which can generate the details of middle- and high-frequency parts to better construct the full-band mel-spectrogram. Specifically, in order to alleviate this problem, XiaoiceSing2 adopts a generative adversarial network (GAN), which consists of a FastSpeech-based generator and a multi-band dis…
Microsoft STC Asia（微软亚洲软件技术中心）；Microsoft Research Asia（微软亚洲研究院）
High-fidelity singing voices usually require higher sampling rate (e.g., 48kHz) to convey expression and emotion. However, higher sampling rate causes the wider frequency band and longer waveform sequences and throws challenges for singing voice synthesis (SVS) in both frequency and time domains. Conventional SVS systems that adopt small sampling rate cannot well address the above challenges. In this paper, we develop HiFiSinger, an SVS system towards high-fidelity singing voice. HiFiSinger consists of a FastSpeech based acoustic model and a Parallel WaveGAN based vocoder to ensure fast traini…
Universitat Pompeu Fabra（庞培法布拉大学）；Joint Research Centre, European Commission（欧盟联合研究中心）
We present a deep neural network based singing voice synthesizer, inspired by the Deep Convolutions Generative Adversarial Networks (DCGAN) architecture and optimized using the Wasserstein-GAN algorithm. We use vocoder parameters for acoustic modelling, to separate the influence of pitch and timbre. This facilitates the modelling of the large variability of pitch in the singing voice. Our network takes a block of consecutive frame-wise linguistic and fundamental frequency features, along with global singer identity as input and outputs vocoder features, corresponding to the block of features. …
Techno-Speech, Inc.（Techno-Speech公司）；Nagoya Institute of Technology（名古屋工业大学）
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 naturalness of synthesized singing voices. In these systems, the relationship between musical score feature sequences and acoustic feature sequences extracted from singing voices is modeled by DNNs. Then, an acoustic feature sequence of an arbitrary musical score is output in units of frames by the trained DNNs, and a natural trajectory of a singing voice is obtained by using …
