EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech With Band-Specific Acoustic Modeling

A-Seong Moon, Dahyun Song, Jaesung Lee

IEEE Access · 2026 · 14 · 101942-101954

DOI: 10.1109/access.2026.3706694 ↗

Kurz gefasst

Fachartikel in der Zeitschrift IEEE Access, 2026. Verfasst von A-Seong Moon und 2 weiteren Autor:innen. Die Arbeit nennt 31 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Chung-Ang University Graduate Research Scholarship, Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant funded by MSIT [Artificial Intelligence Graduate School Program (Ch….

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Kein Abstract verfügbar.

Förderung

  • Chung-Ang University Graduate Research Scholarship
  • Institute of Information and Communications Technology Planning and Evaluation (IITP) Grant funded by MSIT [Artificial Intelligence Graduate School Program (Ch…

Zitieren

APA

Moon, A., Song, D., & Lee, J. (2026). Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech With Band-Specific Acoustic Modeling. IEEE Access, 14, 101942-101954. https://doi.org/10.1109/access.2026.3706694

Vancouver

Moon A, Song D, Lee J. Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech With Band-Specific Acoustic Modeling. IEEE Access. 2026;14:101942-101954. doi:10.1109/access.2026.3706694

BibTeX
@article{Moon2026,
  author = {Moon, A-Seong and Song, Dahyun and Lee, Jaesung},
  title = {Effective Mel-Spectrogram Synthesis for Multi-Speaker Text-to-Speech With Band-Specific Acoustic Modeling},
  journal = {IEEE Access},
  year = {2026},
  volume = {14},
  pages = {101942--101954},
  doi = {10.1109/access.2026.3706694}
}
Kostenlos starten →