Open AccessBetter Communication Tool for Specially Disabled
Author(s) -
Gogineni Saikiran*,
Anjusha Pimpalshende,
Porika Dhanrajnath
Publication year - 2019
Publication title -
international journal of recent technology and engineering
Language(s) - English
Resource type - Journals
ISSN - 2277-3878
DOI - 10.35940/ijrte.d7439.118419
Subject(s) - computer science , pruning , convolutional neural network , scalability , metric (unit) , focus (optics) , artificial intelligence , sign (mathematics) , artificial neural network , sign language , machine learning , mathematics , engineering , mathematical analysis , linguistics , operations management , physics , philosophy , optics , database , agronomy , biology
Sign language is widely used when a dumb communicates. However, non-sign-language people find it difficult in interpreting them. So, we had come up with a system that enables speech impaired to speak with an artificial voice in public communities using Artificial intelligence techniques. we propose a hybrid-weighted metric known as weighted pruning in deep convolutional neural networks. In this work, we report experiments of weighted pruning. we show that using a weighted pruning strategy we can achieve significant speed up in Faster RCNN object detection model by discarding 50% of filters. In this paper we show evidences to our claim by reporting mean Average Precision of weighted pruned CNN is slightly higher than existing pruning techniques. The former part of the paper focus on moulding convolutional neural networks in terms of their speed and scalability for deploying them on mobiles, embedded and further small gadgets. The latter part of the paper describes novel approaches in letting dumb speak as fast as normal person in public, without time lapse using natural language algorithms and recommendations.