Wavehax: Aliasing-Free Neural Waveform Synthesis Based on 2D Convolution and Harmonic Prior for Reliable Complex Spectrogram Estimation
R Yoneyama, A Miyashita, R Yamamoto… - arXiv preprint arXiv …, 2024 - arxiv.org
Neural vocoders often struggle with aliasing in latent feature spaces, caused by time-domain
nonlinear operations and resampling layers. Aliasing folds high-frequency components into …
nonlinear operations and resampling layers. Aliasing folds high-frequency components into …
Interactive tools for making temporally variable, multiple-attributes, and multiple-instances morphing accessible: Flexible manipulation of divergent speech instances …
H Kawahara, M Morise - Acoustical Science and Technology, 2025 - jstage.jst.go.jp
We generalized a voice morphing algorithm capable of handling temporally variable,
multiple-attributes, and multiple instances. The generalized morphing provides a new …
multiple-attributes, and multiple instances. The generalized morphing provides a new …
An Efficient Speech Synthesizer–A Hybrid Monotonic architecture for text-to-speech using VAE & LPC-net with independent sentence length
N NAVEENKUMAR - 2024 - researchsquare.com
In this research, it is suggested that a hybrid architecture for text-to-speech, which is named
it as Efficient Speech Synthesizer. ESS optimizes all the parameters through a consistent …
it as Efficient Speech Synthesizer. ESS optimizes all the parameters through a consistent …
A Review of the Challenges of Adaptive Filtering Technology in High-fidelity Audio Signal Processing
Z Huang - Theoretical and Natural Science, 2024 - ewadirect.com
High-fidelity audio signal processing plays an important role in modern audio technology.
With the increasing demand for this technology in various audio application scenarios, the …
With the increasing demand for this technology in various audio application scenarios, the …