With the number of lecture recordings increasing constantly, technologies are needed to help the user find, access, and navigate through videos. This paper proposes a Sphinx-4-based [1] speech-to-text solution within the REPLAY framework to produce rich media and provide pin-point access.
Klaus Benedikt Schönenberger, Mario Andres Chavarria Varon
Maud Ehrmann, Matteo Romanello
Cédric Duchene, Nicolas Henchoz, Emily Clare Groves, Romain Simon Collaud, Andreas Sonderegger, Yoann Pierre Douillet