Crnn - Open Access .click

ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2020
Deep learning based approaches have greatly improved the performance of spoken keyword spotting (KWS). However, KWS of different languages should have their own corresponding modeling units to optimize the performance. In this paper, we propose an end-to-end Mandarin KWS system using Convolutional Recurrent Neural Network with the Connectionist ...
Haikang Yan, Qianhua He, Wei Xie
openaire +1 more source

Medical Handwritten Prescription Recognition Using CRNN

2019 International Conference on Computer, Information and Telecommunication Systems (CITS), 2019
Reading a doctor’s handwritten prescription is a challenge that most patients and some pharmacists face; an issue that, in some cases, lead to negative consequences due to wrong deciphering of the prescription. Part of the reason why doctor’s prescriptions are so difficult to decipher is that doctors make use of Latin abbreviations and medical ...
Roger Achkar +4 more
openaire +1 more source

deep learning
convolutional recurrent neural network
text recognition

fos: computer and information sciences
audio and speech processing eess.as
computer science - sound

sound cs.sd
medicine
cnn