Customizable multilingual zero-shot singing voice synthesis (SVS) has various potential applications in music composition and short video dubbing. However, existing SVS models overly depend on phoneme and note boundary annotations, limiting their robustness in zero-shot scenarios and producing poor transitions between phonemes and notes. Moreover, they also lack effective multi-level style control via diverse prompts. To overcome these challenges, we introduce TCSinger 2, a multi-task multilingual zero-shot SVS model with style transfer and style control based on various prompts. TCSinger 2 mainly includes three key modules: 1) Blurred Boundary Content (BBC) Encoder, predicts duration, extends content embedding, and applies masking to the boundaries to enable smooth transitions. 2) Custom Audio Encoder, uses contrastive learning to extract aligned representations from singing, speech, and textual prompts. 3) Flow-based Custom Transformer, leverages Cus-MOE, with F0 supervision, enhancing both the synthesis quality and style modeling of the generated singing voice. Experimental results show that TCSinger 2 outperforms baseline models in both subjective and objective metrics across multiple related tasks. Singing voice samples are available at https://aaronz345.github.io/TCSinger2Demo/.
Zero-shot singing voice synthesis (SVS) with style transfer and style control aims to generate high-quality singing voices with unseen timbres and styles (including singing method, emotion, rhythm, technique, and pronunciation) from audio and text prompts. However, the multifaceted nature of singing styles poses a significant challenge for effective modeling, transfer, and control. Furthermore, current SVS models often fail to generate singing voices rich in stylistic nuances for unseen singers. To address these challenges, we introduce TCSinger, the first zero-shot SVS model for style transfer across cross-lingual speech and singing styles, along with multi-level style control. Specifically, TCSinger proposes three primary modules: 1) the clustering style encoder employs a clustering vector quantization model to stably condense style information into a compact latent space; 2) the Style and Duration Language Model (S\&D-LM) concurrently predicts style information and phoneme duration, which benefits both; 3) the style adaptive decoder uses a novel mel-style adaptive normalization method to generate singing voices with enhanced details. Experimental results show that TCSinger outperforms all baseline models in synthesis quality, singer similarity, and style controllability across various tasks, including zero-shot style transfer, multi-level style control, cross-lingual style transfer, and speech-to-singing style transfer. Singing voice samples can be accessed at https://aaronz345.github.io/TCSingerDemo/.
The scarcity of high-quality and multi-task singing datasets significantly hinders the development of diverse controllable and personalized singing tasks, as existing singing datasets suffer from low quality, limited diversity of languages and singers, absence of multi-technique information and realistic music scores, and poor task suitability. To tackle these problems, we present GTSinger, a large global, multi-technique, free-to-use, high-quality singing corpus with realistic music scores, designed for all singing tasks, along with its benchmarks. Particularly, (1) we collect 80.59 hours of high-quality singing voices, forming the largest recorded singing dataset; (2) 20 professional singers across nine widely spoken languages offer diverse timbres and styles; (3) we provide controlled comparison and phoneme-level annotations of six commonly used singing techniques, helping technique modeling and control; (4) GTSinger offers realistic music scores, assisting real-world musical composition; (5) singing voices are accompanied by manual phoneme-to-audio alignments, global style labels, and 16.16 hours of paired speech for various singing tasks. Moreover, to facilitate the use of GTSinger, we conduct four benchmark experiments: technique-controllable singing voice synthesis, technique recognition, style transfer, and speech-to-singing conversion. The corpus and demos can be found at http://aaronz345.github.io/GTSingerDemo/. We provide the dataset and the code for processing data and conducting benchmarks at https://huggingface.co/datasets/AaronZ345/GTSinger and https://github.com/AaronZ345/GTSinger.
With the advancements in singing voice generation and the growing presence of AI singers on media platforms, the inaugural Singing Voice Deepfake Detection (SVDD) Challenge aims to advance research in identifying AI-generated singing voices from authentic singers. This challenge features two tracks: a controlled setting track (CtrSVDD) and an in-the-wild scenario track (WildSVDD). The CtrSVDD track utilizes publicly available singing vocal data to generate deepfakes using state-of-the-art singing voice synthesis and conversion systems. Meanwhile, the WildSVDD track expands upon the existing SingFake dataset, which includes data sourced from popular user-generated content websites. For the CtrSVDD track, we received submissions from 47 teams, with 37 surpassing our baselines and the top team achieving a 1.65% equal error rate. For the WildSVDD track, we benchmarked the baselines. This paper reviews these results, discusses key findings, and outlines future directions for SVDD research.
Recent singing voice synthesis and conversion advancements necessitate robust singing voice deepfake detection (SVDD) models. Current SVDD datasets face challenges due to limited controllability, diversity in deepfake methods, and licensing restrictions. Addressing these gaps, we introduce CtrSVDD, a large-scale, diverse collection of bonafide and deepfake singing vocals. These vocals are synthesized using state-of-the-art methods from publicly accessible singing voice datasets. CtrSVDD includes 47.64 hours of bonafide and 260.34 hours of deepfake singing vocals, spanning 14 deepfake methods and involving 164 singer identities. We also present a baseline system with flexible front-end features, evaluated against a structured train/dev/eval split. The experiments show the importance of feature selection and highlight a need for generalization towards deepfake methods that deviate further from training distribution. The CtrSVDD dataset and baselines are publicly accessible.
Recent singing-voice-synthesis (SVS) methods have achieved remarkable audio quality and naturalness, yet they lack the capability to control the style attributes of the synthesized singing explicitly. We propose Prompt-Singer, the first SVS method that enables attribute controlling on singer gender, vocal range and volume with natural language. We adopt a model architecture based on a decoder-only transformer with a multi-scale hierarchy, and design a range-melody decoupled pitch representation that enables text-conditioned vocal range control while keeping melodic accuracy. Furthermore, we explore various experiment settings, including different types of text representations, text encoder fine-tuning, and introducing speech data to alleviate data scarcity, aiming to facilitate further research. Experiments show that our model achieves favorable controlling ability and audio quality. Audio samples are available at http://prompt-singer.github.io .
Style transfer for out-of-domain (OOD) singing voice synthesis (SVS) focuses on generating high-quality singing voices with unseen styles (such as timbre, emotion, pronunciation, and articulation skills) derived from reference singing voice samples. However, the endeavor to model the intricate nuances of singing voice styles is an arduous task, as singing voices possess a remarkable degree of expressiveness. Moreover, existing SVS methods encounter a decline in the quality of synthesized singing voices in OOD scenarios, as they rest upon the assumption that the target vocal attributes are discernible during the training phase. To overcome these challenges, we propose StyleSinger, the first singing voice synthesis model for zero-shot style transfer of out-of-domain reference singing voice samples. StyleSinger incorporates two critical approaches for enhanced effectiveness: 1) the Residual Style Adaptor (RSA) which employs a residual quantization module to capture diverse style characteristics in singing voices, and 2) the Uncertainty Modeling Layer Normalization (UMLN) to perturb the style attributes within the content representation during the training phase and thus improve the model generalization. Our extensive evaluations in zero-shot style transfer undeniably establish that StyleSinger outperforms baseline models in both audio quality and similarity to the reference singing voice samples. Access to singing voice samples can be found at https://aaronz345.github.io/StyleSingerDemo/.
Although Singing Voice Synthesis (SVS) has made great strides with Text-to-Speech (TTS) techniques, multilingual singing voice modeling remains relatively unexplored. This paper presents BiSinger, a bilingual pop SVS system for English and Chinese Mandarin. Current systems require separate models per language and cannot accurately represent both Chinese and English, hindering code-switch SVS. To address this gap, we design a shared representation between Chinese and English singing voices, achieved by using the CMU dictionary with mapping rules. We fuse monolingual singing datasets with open-source singing voice conversion techniques to generate bilingual singing voices while also exploring the potential use of bilingual speech data. Experiments affirm that our language-independent representation and incorporation of related datasets enable a single model with enhanced performance in English and code-switch SVS while maintaining Chinese song performance. Audio samples are available at https://bisinger-svs.github.io.
The rise of singing voice synthesis presents critical challenges to artists and industry stakeholders over unauthorized voice usage. Unlike synthesized speech, synthesized singing voices are typically released in songs containing strong background music that may hide synthesis artifacts. Additionally, singing voices present different acoustic and linguistic characteristics from speech utterances. These unique properties make singing voice deepfake detection a relevant but significantly different problem from synthetic speech detection. In this work, we propose the singing voice deepfake detection task. We first present SingFake, the first curated in-the-wild dataset consisting of 28.93 hours of bonafide and 29.40 hours of deepfake song clips in five languages from 40 singers. We provide a train/validation/test split where the test sets include various scenarios. We then use SingFake to evaluate four state-of-the-art speech countermeasure systems trained on speech utterances. We find these systems lag significantly behind their performance on speech test data. When trained on SingFake, either using separated vocal tracks or song mixtures, these systems show substantial improvement. However, our evaluations also identify challenges associated with unseen singers, communication codecs, languages, and musical contexts, calling for dedicated research into singing voice deepfake detection. The SingFake dataset and related resources are available at https://www.singfake.org/.
Singing voice synthesis and singing voice conversion have significantly advanced, revolutionizing musical experiences. However, the rise of "Deepfake Songs" generated by these technologies raises concerns about authenticity. Unlike Audio DeepFake Detection (ADD), the field of song deepfake detection lacks specialized datasets or methods for song authenticity verification. In this paper, we initially construct a Chinese Fake Song Detection (FSD) dataset to investigate the field of song deepfake detection. The fake songs in the FSD dataset are generated by five state-of-the-art singing voice synthesis and singing voice conversion methods. Our initial experiments on FSD revealed the ineffectiveness of existing speech-trained ADD models for the task of song deepFake detection. Thus, we employ the FSD dataset for the training of ADD models. We subsequently evaluate these models under two scenarios: one with the original songs and another with separated vocal tracks. Experiment results show that song-trained ADD models exhibit a 38.58% reduction in average equal error rate compared to speech-trained ADD models on the FSD test set.
This paper introduces GlOttal-flow LPC Filter (GOLF), a novel method for singing voice synthesis (SVS) that exploits the physical characteristics of the human voice using differentiable digital signal processing. GOLF employs a glottal model as the harmonic source and IIR filters to simulate the vocal tract, resulting in an interpretable and efficient approach. We show it is competitive with state-of-the-art singing voice vocoders, requiring fewer synthesis parameters and less memory to train, and runs an order of magnitude faster for inference. Additionally, we demonstrate that GOLF can model the phase components of the human voice, which has immense potential for rendering and analysing singing voices in a differentiable manner. Our results highlight the effectiveness of incorporating the physical properties of the human voice mechanism into SVS and underscore the advantages of signal-processing-based approaches, which offer greater interpretability and efficiency in synthesis.
We propose the stochastic optimal path which solves the classical optimal path problem by a probability-softening solution. This unified approach transforms a wide range of DP problems into directed acyclic graphs in which all paths follow a Gibbs distribution. We show the equivalence of the Gibbs distribution to a message-passing algorithm by the properties of the Gumbel distribution and give all the ingredients required for variational Bayesian inference of a latent path, namely Bayesian dynamic programming (BDP). We demonstrate the usage of BDP in the latent space of variational autoencoders (VAEs) and propose the BDP-VAE which captures structured sparse optimal paths as latent variables. This enables end-to-end training for generative tasks in which models rely on unobserved structural information. At last, we validate the behavior of our approach and showcase its applicability in two real-world applications: text-to-speech and singing voice synthesis. Our implementation code is available at \url{https://github.com/XinleiNIU/LatentOptimalPathsBayesianDP}.
Denoising diffusion probabilistic models (DDPMs) have shown promising performance for speech synthesis. However, a large number of iterative steps are required to achieve high sample quality, which restricts the inference speed. Maintaining sample quality while increasing sampling speed has become a challenging task. In this paper, we propose a "Co"nsistency "Mo"del-based "Speech" synthesis method, CoMoSpeech, which achieve speech synthesis through a single diffusion sampling step while achieving high audio quality. The consistency constraint is applied to distill a consistency model from a well-designed diffusion-based teacher model, which ultimately yields superior performances in the distilled CoMoSpeech. Our experiments show that by generating audio recordings by a single sampling step, the CoMoSpeech achieves an inference speed more than 150 times faster than real-time on a single NVIDIA A100 GPU, which is comparable to FastSpeech2, making diffusion-sampling based speech synthesis truly practical. Meanwhile, objective and subjective evaluations on text-to-speech and singing voice synthesis show that the proposed teacher models yield the best audio quality, and the one-step sampling based CoMoSpeech achieves the best inference speed with better or comparable audio quality to other conventional multi-step diffusion model baselines. Audio samples are available at https://comospeech.github.io/.
Pitch is a foundational aspect of our perception of audio signals. Pitch contours are commonly used to analyze speech and music signals and as input features for many audio tasks, including music transcription, singing voice synthesis, and prosody editing. In this paper, we describe a set of techniques for improving the accuracy of widely-used neural pitch and periodicity estimators to achieve state-of-the-art performance on both speech and music. We also introduce a novel entropy-based method for extracting periodicity and per-frame voiced-unvoiced classifications from statistical inference-based pitch estimators (e.g., neural networks), and show how to train a neural pitch estimator to simultaneously handle both speech and music data (i.e., cross-domain estimation) without performance degradation. Our estimator implementations run 11.2x faster than real-time on a Intel i9-9820X 10-core 3.30 GHz CPU$\unicode{x2014}$approaching the speed of state-of-the-art DSP-based pitch estimators$\unicode{x2014}$or 408x faster than real-time on a NVIDIA GeForce RTX 3090 GPU. We release all of our code and models as Pitch-Estimating Neural Networks (penn), an open-source, pip-installable Python module for training, evaluating, and performing inference with pitch- and periodicity-estimating neural networks. The code for penn is available at https://github.com/interactiveaudiolab/penn.
This paper describes the design of NNSVS, an open-source software for neural network-based singing voice synthesis research. NNSVS is inspired by Sinsy, an open-source pioneer in singing voice synthesis research, and provides many additional features such as multi-stream models, autoregressive fundamental frequency models, and neural vocoders. Furthermore, NNSVS provides extensive documentation and numerous scripts to build complete singing voice synthesis systems. Experimental results demonstrate that our best system significantly outperforms our reproduction of Sinsy and other baseline systems. The toolkit is available at https://github.com/nnsvs/nnsvs.
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 discriminator. We improve the feed-forward Transformer (FFT) block by adding multiple residual convolutional blocks in parallel with the self-attention block to balance the local and global features. The multi-band discriminator contains three sub-discriminators responsible for low-, middle-, and high-frequency parts of the mel-spectrogram, respectively. Each sub-discriminator is composed of several segment discriminators (SD) and detail discriminators (DD) to distinguish the audio from different aspects. The experiment on our internal 48kHz singing voice dataset shows XiaoiceSing2 significantly improves the quality of the singing voice over XiaoiceSing.
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 OpenSinger. To tackle the difficulty in unseen singer modeling, we propose Multi-Singer, a fast multi-singer vocoder with generative adversarial networks. Specifically, 1) Multi-Singer uses a multi-band generator to speed up both training and inference procedure. 2) to capture and rebuild singer identity from the acoustic feature (i.e., mel-spectrogram), Multi-Singer adopts a singer conditional discriminator and conditional adversarial training objective. 3) to supervise the reconstruction of singer identity in the spectrum envelopes in frequency domain, we propose an auxiliary singer perceptual loss. The joint training approach effectively works in GANs for multi-singer voices modeling. Experimental results verify the effectiveness of OpenSinger and show that Multi-Singer improves unseen singer singing voices modeling in both speed and quality over previous methods. The further experiment proves that combined with FastSpeech 2 as the acoustic model, Multi-Singer achieves strong robustness in the multi-singer singing voice synthesis pipeline. Samples are available at https://Multi-Singer.github.io/
Recent developments in deep learning have significantly improved the quality of synthesized singing voice audio. 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. To the best of our knowledge, this is the first work that uses an entirely MLP-based architecture for voice synthesis. Listening tests demonstrate that MLP Singer outperforms a larger autoregressive GAN-based system, both in terms of audio quality and synthesis speed. In particular, MLP Singer achieves a real-time factor of up to 200 and 3400 on CPUs and GPUs respectively, enabling order of magnitude faster generation on both environments.
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. DiffSinger is a parameterized Markov chain that iteratively converts the noise into mel-spectrogram conditioned on the music score. By implicitly optimizing variational bound, DiffSinger can be stably trained and generate realistic outputs. To further improve the voice quality and speed up inference, we introduce a shallow diffusion mechanism to make better use of the prior knowledge learned by the simple loss. Specifically, DiffSinger starts generation at a shallow step smaller than the total number of diffusion steps, according to the intersection of the diffusion trajectories of the ground-truth mel-spectrogram and the one predicted by a simple mel-spectrogram decoder. Besides, we propose boundary prediction methods to locate the intersection and determine the shallow step adaptively. The evaluations conducted on a Chinese singing dataset demonstrate that DiffSinger outperforms state-of-the-art SVS work. Extensional experiments also prove the generalization of our methods on text-to-speech task (DiffSpeech). Audio samples: https://diffsinger.github.io. Codes: https://github.com/MoonInTheRiver/DiffSinger. The old title of this work: "Diffsinger: Diffusion acoustic model for singing voice synthesis".
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 space representation, which is included in the DDSP library, but not in the original DDSP examples. Our results indicate that the latent space improves both the identification of the singer as well as the comprehension of the lyrics. Our code is available at https://github.com/juanalonso/DDSP-singing-experiments with links to the zero-configuration notebooks, and our sound examples are at https://juanalonso.github.io/DDSP-singing-experiments/ .