EndtoEnd Deep Neural Network for Automatic Speech
cs224d.stanford.edu
Author: openj-gate.com ~ Tags: cs224d.stanford.edu ~ Date: 2022/06/25
deep convolutional neural network (CNN) for phoneme recognition and a hidden Markov model (HMM) for word decoding Specifically we implemented a GPUbased - Information from cs224d.stanford.edu
Information accuracy 100%
Read more from cs224d.stanford.edu information was found here: https://cs224d.stanford.edu/reports/SongWilliam.pdf