Reshaping automatic speech transcripts for robust high-level spoken document analysis

Julien Fayolle (1) , Fabienne Moreau (1) , Christian Raymond (1) , Guillaume Gravier (2)

1 TEXMEX - Multimedia content-based indexing
2 METISS - Speech and sound data modeling and processing

Domains: Signal and Image Processing; Signal and Image processing

Julien Fayolle, Fabienne Moreau, Christian Raymond, Guillaume Gravier. Reshaping automatic speech transcripts for robust high-level spoken document analysis. Proc. Workshop on Analytics for Noisy Unstructured Text Data, Oct 2010, Toronto, Canada. ⟨inria-00555790⟩