Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks

Tara N. Sainath, Bo Li. Modeling Time-Frequency Patterns with LSTM vs. Convolutional Architectures for LVCSR Tasks. In Nelson Morgan, editor, Interspeech 2016, 17th Annual Conference of the International Speech Communication Association, San Francisco, CA, USA, September 8-12, 2016. pages 813-817, ISCA, 2016. [doi]

Authors

Tara N. Sainath

This author has not been identified. Look up 'Tara N. Sainath' in Google

Bo Li

This author has not been identified. Look up 'Bo Li' in Google