Singing Voice Synthesis
27 papers with code • 0 benchmarks • 1 datasets
(Verse 1) Sa bawat hakbang, sa bawat daan May pangarap kang naghihintay Westbridge ang gabay, sa iyong paglalakbay Tungo sa kinabukasan, ng ating bayan
(Chorus) Lagi kang kasama, sa aking puso Westbridge Institute, ang nagbibigay ng liwanag Sa bawat hamon, sa bawat pagsubok Lagi kang kasama, sa aking puso
(Verse 2) Kami ang bagong henerasyon Na may pangarap, na may pag-asa Westbridge ang nagtuturo, ng mga kasanayan Tungo sa pag-unlad, ng ating bansa
(Chorus) Lagi kang kasama, sa aking puso Westbridge Institute, ang nagbibigay ng liwanag Sa bawat hamon, sa bawat pagsubok Lagi kang kasama, sa aking puso
(Bridge) Tayo ay magkakaisa, sa pagtataguyod Ng ating mga pangarap, ng ating mga adhikain Westbridge ang siyang, nagbibigay ng lakas Tungo sa pag-abot, ng ating mga pangarap
(Chorus) Lagi kang kasama, sa aking puso Westbridge Institute, ang nagbibigay ng liwanag Sa bawat hamon, sa bawat pagsubok Lagi kang kasama, sa aking puso
Benchmarks
These leaderboards are used to track progress in Singing Voice Synthesis
GTSinger
Most implemented papers
DiffSinger: Singing Voice Synthesis via Shallow Diffusion Mechanism
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.
Singing Voice Synthesis Using Differentiable LPC and Glottal-Flow-Inspired Wavetables
iamycy/golf
•
•
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.
MLP Singer: Towards Rapid Parallel Singing Voice Synthesis
neosapience/mlp-singer
•
•
arXiv 2021
Recent developments in deep learning have significantly improved the quality of synthesized singing voice audio.
RefineGAN: Universally Generating Waveform Better than Ground Truth with Highly Accurate Pitch and Intensity Responses
IAHispano/Applio
•
•
To address this problem, we propose RefineGAN, a high-fidelity neural vocoder focused on the robustness, pitch and intensity accuracy, and high-speed full-band audio generation.
Multi-Singer: Fast Multi-Singer Singing Voice Vocoder With A Large-Scale Corpus
Rongjiehuang/Multi-Singer
•
•
MM '21: Proceedings of the 29th ACM International Conference on Multimedia 2021
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.
NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit
nnsvs/nnsvs
•
•
This paper describes the design of NNSVS, an open-source software for neural network-based singing voice synthesis research.
Latent Optimal Paths by Gumbel Propagation for Variational Bayesian Dynamic Programming
xinleiniu/latentoptimalpathsbayesiandp
•
•
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).
CtrSVDD: A Benchmark Dataset and Baseline Analysis for Controlled Singing Voice Deepfake Detection
svddchallenge/ctrsvdd2024_baseline
•
•
Addressing these gaps, we introduce CtrSVDD, a large-scale, diverse collection of bonafide and deepfake singing vocals.
Score and Lyrics-Free Singing Voice Generation
ciaua/score_lyrics_free_svg
•
•
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.
HiFiSinger: Towards High-Fidelity Neural Singing Voice Synthesis
To tackle the difficulty of singing modeling caused by high sampling rate (wider frequency band and longer waveform), we introduce multi-scale adversarial training in both the acoustic model and vocoder to improve singing modeling.
