Multistream neural architectures for cued speech recognition using a pre-trained visual feature extractor and constrained ctc decoding

Sanjana Sankar (ESR 10)

Abstract (pdf)

Poster (pdf)

Click on the image to join the Live on December 13, from 12:30 to 14:30. You can also leave a comment at the bottom of the page or send an email to Sanjana: sanjana.sankar@gipsa-lab.grenoble-inp.fr

Multistream neural architectures for cued speech recognition using a pre-trained visual feature extractor and constrained ctc decoding

Sanjana Sankar (ESR 10)

Abstract (pdf)

Poster (pdf)

Leave a comment!