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.
Recent studies in singing voice synthesis have achieved high-quality results leveraging advances in text-to-speech models based on deep neural networks. 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. The temporal alignment is a time-exhausting manual work in preparing for the training data. To address the issue, we propose a melody-unsupervision model that requires only audio-and-lyrics pairs without temporal alignment in training time but generates singing voice audio given a melody and l…
MeloDISinger: Melody-Aware & Duration-Preserving Singing Voice Editing with Audio Infilling
Graduate School of Artificial Intelligence, KAIST, South Korea（韩国釜山科学技术院人工智能研究生院）；Graduate School of Culture Technology, KAIST, South Korea（韩国釜山科学技术院文化科技研究生院）
Singing voice synthesis (SVS) systems are built to synthesize high-quality and expressive singing voice, in which the acoustic model generates the acoustic features (e.g., mel-spectrogram) given a music score. Previous singing acoustic models adopt a simple loss (e.g., L1 and L2) or generative adversarial network (GAN) to reconstruct the acoustic features, while they suffer from over-smoothing and unstable training issues respectively, which hinder the naturalness of synthesized singing. In this work, we propose DiffSinger, an acoustic model for SVS based on the diffusion probabilistic model. …
Fudan University（复旦大学）；National Institute of Informatics (NII)（国立情报学研究所）；Shanghai Key Laboratory of Intelligent Information Processing, Fudan University（复旦大学上海市智能信息处理重点实验室）
Musical audio is generally composed of three physical properties: frequency, time and magnitude. Interestingly, human auditory periphery also provides neural codes for each of these dimensions to perceive music. Inspired by these intrinsic characteristics, a frequency-temporal attention network is proposed to mimic human auditory for singing melody extraction. In particular, the proposed model contains frequency-temporal attention modules and a selective fusion module corresponding to these three physical properties. The frequency attention module is used to select the same activation frequenc…
Academia Sinica（中央研究院）；Queen Mary University of London（伦敦玛丽女王大学）；Rayark Inc.（雷亚游戏有限公司）
Singing voice correction (SVC) is an appealing application for amateur singers. Commercial products automate SVC by snapping pitch contours to equal-tempered scales, which could lead to deadpan modifications. Together with the neglect of rhythmic errors, extensive manual corrections are still necessary. In this paper, we present a streamlined system to automate expressive SVC for both pitch and rhythmic errors. Particularly, we extend a previous work by integrating advanced techniques for singing voice separation (SVS) and vocal melody extraction. SVC is achieved by temporally aligning the sou…
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. The proposed system consists of two main modules; a mel-synthesis network that generates a mel-spectrogram from the given input information, and a super-resolution network that upsamples the generated mel-spectrogram into a linear-spectrogram. In the mel-synthesis network, phonetic enhancement ma…
University of California San Diego（加州大学圣地亚哥分校）；Fudan University（复旦大学）；Smule Inc.（Smule公司）
Singing melody extraction is an important problem in the field of music information retrieval. Existing methods typically rely on frequency-domain representations to estimate the sung frequencies. However, this design does not lead to human-level performance in the perception of melody information for both tone (pitch-class) and octave. In this paper, we propose TONet, a plug-and-play model that improves both tone and octave perceptions by leveraging a novel input representation and a novel network architecture. First, we present an improved input representation, the Tone-CFP, that explicitly …
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…
Mellotron is a multispeaker voice synthesis model based on Tacotron 2 GST that can make a voice emote and sing without emotive or singing training data. By explicitly conditioning on rhythm and continuous pitch contours from an audio signal or music score, Mellotron is able to generate speech in a variety of styles ranging from read speech to expressive speech, from slow drawls to rap and from monotonous voice to singing voice. Unlike other methods, we train Mellotron using only read speech data without alignments between text and audio. We evaluate our models using the LJSpeech and LibriTTS d…
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…
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…
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 …
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…
Indian Institute of Science（印度科学学院）；Sony Group Corporation（索尼集团公司）
In this paper, we propose a model to perform style transfer of speech to singing voice. Contrary to the previous signal processing-based methods, which require high-quality singing templates or phoneme synchronization, we explore a data-driven approach for the problem of converting natural speech to singing voice. We develop a novel neural network architecture, called SymNet, which models the alignment of the input speech with the target melody while preserving the speaker identity and naturalness. The proposed SymNet model is comprised of symmetrical stack of three types of layers - convoluti…
Machine learning based singing voice models require large datasets and lengthy training times. In this work we present a lightweight architecture, based on the Differentiable Digital Signal Processing (DDSP) library, that is able to output song-like utterances conditioned only on pitch and amplitude, after twelve hours of training using small datasets of unprocessed audio. The results are promising, as both the melody and the singer's voice are recognizable. In addition, we present two zero-configuration tools to train new models and experiment with them. Currently we are exploring the latent …
Automatic note-level transcription is considered one of the most challenging tasks in music information retrieval. The specific case of flamenco singing transcription poses a particular challenge due to its complex melodic progressions, intonation inaccuracies, the use of a high degree of ornamentation and the presence of guitar accompaniment. In this study, we explore the limitations of existing state of the art transcription systems for the case of flamenco singing and propose a specific solution for this genre: We first extract the predominant melody and apply a novel contour filtering proc…
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. Existing open corpora could not meet requirements for high-fidelity singing voice synthesis because of the scale and quality weaknesses. Previous vocoders have difficulty in multi-singer modeling, and a distinct degradation emerges when conducting unseen singer singing voice generation. To accelerate singing voice researches in the community, we release a large-scale, multi-singer Chinese singing voice dataset …
This paper presents a new method of singing voice analysis that performs mutually-dependent singing voice separation and vocal fundamental frequency (F0) estimation. Vocal F0 estimation is considered to become easier if singing voices can be separated from a music audio signal, and vocal F0 contours are useful for singing voice separation. This calls for an approach that improves the performance of each of these tasks by using the results of the other. The proposed method first performs robust principal component analysis (RPCA) for roughly extracting singing voices from a target music audio s…
Query by Singing/Humming (QBSH) is a Music Information Retrieval (MIR) system with small audio excerpt as query. The rising availability of digital music stipulates effective music retrieval methods. Further, MIR systems support content based searching for music and requires no musical acquaintance. Current work on QBSH focuses mainly on melody features such as pitch, rhythm, note etc., size of databases, response time, score matching and search algorithms. Even though a variety of QBSH techniques are proposed, there is a dearth of work to analyze QBSH through query excerption. Here, we presen…
In a recent paper, we have presented a generative adversarial network (GAN)-based model for unconditional generation of the mel-spectrograms of singing voices. As the generator of the model is designed to take a variable-length sequence of noise vectors as input, it can generate mel-spectrograms of variable length. However, our previous listening test shows that the quality of the generated audio leaves room for improvement. The present paper extends and expands that previous work in the following aspects. First, we employ a hierarchical architecture in the generator to induce some structure i…
We present a new model for singing synthesis based on a modified version of the WaveNet architecture. Instead of modeling raw waveform, we model features produced by a parametric vocoder that separates the influence of pitch and timbre. This allows conveniently modifying pitch to match any target melody, facilitates training on more modest dataset sizes, and significantly reduces training and generation times. Our model makes frame-wise predictions using mixture density outputs rather than categorical outputs in order to reduce the required parameter count. As we found overfitting to be an iss…
Generative Multi-modal Feedback for Singing Voice Synthesis Evaluation
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；University of Science and Technology of China（中国科学技术大学）；Columbia University（哥伦比亚大学）；Dalian University of Technology（大连理工大学）；The Chinese University of Hong Kong（香港中文大学）
