Tasha Nagamine

I am a Ph.D. student at Columbia University working with Professor Nima Mesgarani. My research interests include the neural processing of speech and language, and potential applications to speech processing systems through biologically-inspired deep neural network models.

Education

Columbia University

Ph.D. candidate in Electrical Engineering (2015-present)

M.S. in Electrical Engineering (2014-2015)

Brown University

B.S. in Physics (2009-2013)

Publications

Tasha Nagamine, Zhuo Chen, and Nima Mesgarani, "Adaptation of neural networks constrained by prior statistics of node co-activations," in Proc. Interspeech, San Francisco, September 2016.

Tasha Nagamine, Michael L. Seltzer, and Nima Mesgarani, "On the Role Nonlinear Transformations in Deep Neural Network Acoustic Models," in Proc. Interspeech, San Francisco, September 2016.

Okko Rasanen, Tasha Nagamine, and Nima Mesgarani, "Analyzing Distributional Learning of Phonemic Categories in Unsupervised Deep Neural Networks," in 38th Annual Meeting of the Cognitive Science Society, Philadelphia, August 2016.

Tasha Nagamine, Michael L. Seltzer, and Nima Mesgarani, "Exploring How Deep Neural Networks Form Phonemic Categories," in Proc. Interspeech, Dresden, September 2015.

Poster Presentations

Tasha Nagamine, Michael L. Seltzer, and Nima Mesgarani. “On the Formation of Phoneme Categories in Neural Network Models,” poster presented at Computational and Systems Neuroscience (COSYNE), Salt Lake City, Utah, 2016.

Tasha Nagamine, Michael L. Seltzer, and Nima Mesgarani. “On the Formation of Phoneme Categories in DNN Acoustic Models,” poster presented at Speech and Audio in the Northeast (SANE), New York, New York, 2015.