2 papers
cs.CL2021
Shrinking Bigfoot: Reducing wav2vec 2.0 footprint
Zilun Peng, Akshay Budhkar, Ilana Tuil +4
Wav2vec 2.0 is a state-of-the-art speech recognition model which maps speech audio waveforms into latent representations. The largest version of wav2vec 2.0 contains 317 million pa…
cs.CV2018
Writing Style Invariant Deep Learning Model for Historical Manuscripts Alignment
Majeed Kassis, Jumana Nassour, Jihad El-Sana
Historical manuscript alignment is a widely known problem in document analysis. Finding the differences between manuscript editions is mostly done manually. In this paper, we prese…