About

Shashi Kumar is a highly skilled Senior Software Engineer with over 5 years of experience in the field. Currently working at Samsung Electronics, he is actively involved in the development of Automatic Speech Recognition (ASR) for far-field speech in home conditions. In addition, he is working on novel speech enhancement methods and speaker-independent acoustic models using Variational Autoencoders (VAEs). Prior to his current role, Shashi worked at Feltso, where he developed an algorithm to analyze review texts using Deep Learning techniques. He successfully tagged aspects being talked about and analyzed their sentiments. He also trained Word2Vec and Doc2Vec on similar text corpus to obtain vectors for words or sentences. His algorithm performed exceptionally well in aspect tagging. Shashi also worked as a Research Intern at Chubu University, where he developed a robust algorithm to detect and classify different types of defects present in Printed Circuit Boards (PCBs). He devised a novel algorithm that achieved state-of-the-art results in non-referential approaches. A research paper discussing the algorithm was accepted at the International Conference on Computer Vision and Image Processing in 2016. Shashi holds a B.Tech in Electronics and Communication Engineering from the Indian Institute of Technology, Guwahati, which he completed in 2017. He is proficient in a range of technical skills, including Software Engineering, Sentiment Analysis, Mobile, Word2Vec, Corpus, Deep Learning, Research Scientist, Computer Vision, and Image Processing. Shashi is a highly motivated and results-driven individual, with a passion for using his technical skills to solve complex problems. He is an excellent team player and has a proven track record of delivering high-quality work within tight deadlines.