EUVIMEDEUVIMED entdecken
Systematische ÜbersichtOpen Access · CC BY 4.0

A Systematic Review on Audio-Visual Speech-To-Speech Translation Models

Alexandre de Godoy Pereira, Renato Cordeiro Ferreira, Alfredo Goldman

SBC Reviews on Computer Science · 06.08.2026 · 5 (1) · 40-54

DOI: 10.5753/reviews.2026.6237 ↗

Kurz gefasst

Systematische Übersicht in der Zeitschrift SBC Reviews on Computer Science, online erschienen am 06.08.2026. Verfasst von Alexandre de Godoy Pereira und 2 weiteren Autor:innen. Die Arbeit nennt 28 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

This systematic literature review summarizes the evolution of Audio-Visual Speech-to-Speech Translation (AV-S2ST), focusing on the shift from cascaded systems to direct end-to-end models. Key advancements utilize self-supervised learning (SSL) (e.g. AV-HuBERT) and discrete units (e.g. TransFace) to overcome data scarcity and enable textless multilingual translation. Current research tackles challenges in noise robustness, lip-synchrony, isometric translation, and speaker preservation. Techniques like cross-modal distillation show promise, driving progress towards robust, real-time AV-S2ST with enhanced zero-shot capabilities.

Zitieren

APA

Pereira, A. D. G., Ferreira, R. C., & Goldman, A. (2026). A Systematic Review on Audio-Visual Speech-To-Speech Translation Models. SBC Reviews on Computer Science, 5(1), 40-54. https://doi.org/10.5753/reviews.2026.6237

Vancouver

Pereira ADG, Ferreira RC, Goldman A. A Systematic Review on Audio-Visual Speech-To-Speech Translation Models. SBC Reviews on Computer Science. 2026;5(1):40-54. doi:10.5753/reviews.2026.6237

BibTeX
@article{Pereira2026,
  author = {Pereira, Alexandre de Godoy and Ferreira, Renato Cordeiro and Goldman, Alfredo},
  title = {A Systematic Review on Audio-Visual Speech-To-Speech Translation Models},
  journal = {SBC Reviews on Computer Science},
  year = {2026},
  volume = {5},
  number = {1},
  pages = {40--54},
  doi = {10.5753/reviews.2026.6237}
}
Kostenlos starten →