About

Ganesh is an experienced and passionate researcher in speech and language technologies, with a strong scientific background in speech production and perception. He has a demonstrated history of working with state-of-the-art Automatic Speech Recognition (ASR), voice biometrics, speech enhancement, and spoofing detection systems. Ganesh is currently working as a Senior Research Scientist at Pindrop, where he is responsible for developing and implementing deep neural network-based systems for speech and language. Ganesh has worked with several organizations in the past, including the University of Groningen and SRI International. At the University of Groningen, he worked on speech production data for second language English data from Dutch speakers and first language English from UK speakers to develop acoustic-to-articulatory speech inversion systems. He also investigated the cross-lingual and cross-accent performance of the speech inversion systems. At SRI International, Ganesh worked on improving low-resource speech recognition on the endangered language - Yoloxchitl Mixtec. He also performed information retrieval using Vector Space Method and Graphical models for Language Model adaptation and benchmarked acoustic features and classifiers for classifying the state of mental health from speech. Ganesh holds a Doctor of Philosophy (PhD) degree in Electrical & Computer Engineering from the University of Maryland, where he also earned his MS degree in the same field. He completed his undergraduate degree, B.E (Hons.), in Electrical and Electronics Engineering from the Birla Institute of Technology and Science, Pilani. Ganesh is proficient in several technologies and tools, including neural networks, information retrieval, natural language processing (NLP), Python, machine learning (ML), TensorFlow, C, Keras, normalization, corpus, language models, and Scikit. With 5.70 years of relevant experience, Ganesh is a dedicated and skilled researcher who is committed to advancing the field of speech and language technologies.