EUVIMEDEUVIMED entdecken
Crossref

Why is a sinusoidal signal input effective in time-domain neural vocoders?

Reo Yoneyama, Tomoki Toda

The Journal of the Acoustical Society of America · 01.10.2025 · 158 (4_Supplement) · A140-A140

DOI: 10.1121/10.0040390 ↗

Kurz gefasst

Fachartikel in der Zeitschrift The Journal of the Acoustical Society of America, erschienen am 01.10.2025. Verfasst von Reo Yoneyama und 1 weiteren Autor:innen.

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Neural vocoders often use parametrically generated sinusoidal signals based on the fundamental frequency as input, in combination with other acoustic features such as a mel-spectrogram or a spectral envelope sequence. While multiple sinusoidal signals are often used to generate harmonic components, it is widely recognized that even a single sinusoid corresponding to the fundamental frequency can enhance both speech quality and the controllability of the fundamental frequency. This appears counterintuitive, given that natural speech contains a rich set of harmonic components extending well beyond the fundamental frequency. In this presentation, we theoretically analyze this phenomenon in the context of time-domain neural vocoders. Our analysis indicates that nonlinear operations within the neural network effectively generate harmonic components from a single-frequency input, functioning similarly to frequency modulation. These findings offer new insight into the internal signal processing behavior of time-domain neural vocoders and provide a foundation for understanding how a harmonic structure can emerge from a simple excitation signal. [Work supported in part by JST AIP Acceleration Research JPMJCR25U5, Japan, and in part by the Japan Society for the Promotion of Science (JSPS) Grants-in-Aid for Scientific Research (KAKENHI) under Grant 24KJ1236.]

Zitieren

APA

Yoneyama, R., & Toda, T. (2025). Why is a sinusoidal signal input effective in time-domain neural vocoders?. The Journal of the Acoustical Society of America, 158(4_Supplement), A140-A140. https://doi.org/10.1121/10.0040390

Vancouver

Yoneyama R, Toda T. Why is a sinusoidal signal input effective in time-domain neural vocoders?. The Journal of the Acoustical Society of America. 2025;158(4_Supplement):A140-A140. doi:10.1121/10.0040390

BibTeX
@article{Yoneyama2025,
  author = {Yoneyama, Reo and Toda, Tomoki},
  title = {Why is a sinusoidal signal input effective in time-domain neural vocoders?},
  journal = {The Journal of the Acoustical Society of America},
  year = {2025},
  volume = {158},
  number = {4_Supplement},
  pages = {A140--A140},
  doi = {10.1121/10.0040390}
}
Kostenlos starten →