Options
M.Sc.
Gourishetti, Saichand
saichand.gourishetti@idmt.fraunhofer.de
Biographical Information
Mr. Saichand Gourishetti holds a Master’s degree in Computational Science and Engineering with a specialization in Electrical Engineering from the University of Rostock (2019). During his academic tenure, he engaged in a range of machine learning projects, including image recognition, text classification, and sentiment analysis of Twitter data. His master’s thesis focused on optimizing neural networks for real-time keyword detection on resource-constrained devices such as microcontrollers.
Since joining Fraunhofer IDMT in 2020, Mr. Gourishetti has been actively involved in applied research on audio representation learning, neural network optimization, and model compression. His current work centers around industrial media applications, with responsibilities spanning requirements analysis, data acquisition, exploratory data analysis, algorithm development, optimization, and performance evaluation.
He has authored several peer-reviewed conference papers in the areas of acoustic event detection and sound event classification, particularly in the context of industrial sound analysis. In early 2021, he began pursuing a Ph.D., focusing on addressing data scarcity in industrial audio classification through the use of generative audio AI techniques.
Since joining Fraunhofer IDMT in 2020, Mr. Gourishetti has been actively involved in applied research on audio representation learning, neural network optimization, and model compression. His current work centers around industrial media applications, with responsibilities spanning requirements analysis, data acquisition, exploratory data analysis, algorithm development, optimization, and performance evaluation.
He has authored several peer-reviewed conference papers in the areas of acoustic event detection and sound event classification, particularly in the context of industrial sound analysis. In early 2021, he began pursuing a Ph.D., focusing on addressing data scarcity in industrial audio classification through the use of generative audio AI techniques.
Spoken
en
;
de