Period Singer: Integrating Periodic and Aperiodic Variational Autoencoders for Natural-Sounding End-to-End Singing Voice Synthesis
In this paper, we present Period Singer, a novel end-to-end singing voice synthesis (SVS) model that utilizes variational inference for periodic and aperiodic components, aimed at producing natural-sounding waveforms. Recent end-to-end SVS models have demonstrated the capability of synthesizing high-fidelity singing voices. However, owing to deterministic pitch conditioning, they do not fully address the one-to-many problem. To address this problem, we present the Period Singer architecture, which integrates variational autoencoders for the periodic and aperiodic components. Additionally, our methodology eliminates the dependency on an external aligner by estimating the phoneme alignment through a monotonic alignment search within note boundaries. Our empirical evaluations show that Period Singer outperforms existing end-to-end SVS models on Mandarin and Korean datasets. The efficacy of the proposed method was further corroborated by ablation studies.
Code (0)
등록된 구현이 없습니다.
Tasks
Singing Voice SynthesisVariational InferenceMethods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
Separation and Estimation of Periodic/Aperiodic State
Periodicity and aperiodicity can exist in a state simultaneously and typically become quasi-periodicity and quasi-aperiodicity in a dynamically changing state. The quasi-periodic and quasi-aperiodic states existing in th…
PeriodNet: A non-autoregressive waveform generation model with a structure separating periodic and aperiodic components
We propose PeriodNet, a non-autoregressive (non-AR) waveform generation model with a new model structure for modeling periodic and aperiodic components in speech waveforms. The non-AR waveform generation models can gener…
Identifying epileptogenic abnormality by decomposing intracranial EEG and MEG power spectra
Identifying abnormal electroencephalographic activity is crucial in diagnosis and treatment of epilepsy. Recent studies showed that decomposing brain activity into periodic (oscillatory) and aperiodic (trend across all f…
EEGDualCast: Disentangling Aperiodic Events from Traffic Series with a Dual-Branch Model
Traffic forecasting is an important problem in the operation and optimisation of transportation systems. State-of-the-art solutions train machine learning models by minimising the mean forecasting errors on the training …
A spectral audit framework reveals task-dependent aperiodic reliance across EEG and ECG deep learning
Deep learning on physiological time series is interpreted through domain-specific features -- oscillatory rhythms in EEG, morphological complexes in ECG -- yet these signals sit atop a broadband aperiodic 1/f-like envelo…