I am an applied scientist at Amazon AGI (Alexa). I work on application of foundation models to improve language understanding and automatic speech recognition, in cloud and edge models. I am broadly interested in applying machine learning methods for natural language processing, particularly in generative and understanding tasks.
I completed my masters at Ohio State University & Cornell University. Before that, I was an undergraduate at Birla Intitute of Technology and Science, Pilani.
Saumya Y Sahai, Jing Liu, Thejaswi Muniyappa, Kanthashree M. Sathyendra et al. “Dual-attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition.” IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP 2023)}
Saumya Y Sahai, Oana Balalau and Roxana Horincar. “Breaking Down the Invisible Wall of Informal Fallacies in Online Discussions.” Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics (ACL 2021)
Dravyansh Sharma, Saumya Y Sahai, Neha Chaudhari, Antoine Bruguier. “Improved pronunciation prediction accuracy using morphology.” The ACL Special Interest Group on Computational Morphology and Phonology (ACL 2021)
Saumya Y Sahai, Dravyansh Sharma. “Predicting and Explaining French Grammatical Gender.” The ACL Special Interest Group on Typology (NAACL 2021) (* denotes equal contribution)
Saumya Y Sahai, Saket Gurukar, Wasiur R. KhudaBukhsh, Srinivasan Parthasarathy and Grzegorz A. Rempala. “A Machine Learning Model for Nowcasting Epidemic Incidence.” Journal of Mathematical Biosciences (2021)
Bortik Bandyopadhyay, Pranav Maneriker, Vedang Patel, Saumya Y Sahai, Ping Zhang, and Srinivasan Parthasarathy. “DrugDBEmbed: Semantic Queries on Relational Database using Supervised Column Encodings.” arXiv preprint arXiv:2007.02384 (2020).