14 citations · 24 across the 3 of their papers we have counts for
3 papers
cs.CL2017
No Need for a Lexicon? Evaluating the Value of the Pronunciation Lexica in End-to-End Models
Tara N. Sainath, Rohit Prabhavalkar, Shankar Kumar +9
For decades, context-dependent phonemes have been the dominant sub-word unit for conventional acoustic modeling systems. This status quo has begun to be challenged recently by end-…
eess.AS2017★ 10 cited
Multi-Dialect Speech Recognition With A Single Sequence-To-Sequence Model
Bo Li, Tara N. Sainath, Khe Chai Sim +6
Sequence-to-sequence models provide a simple and elegant solution for building speech recognition systems by folding separate components of a typical system, namely acoustic (AM),…
cs.LG2017★ 14 cited
Projection Based Weight Normalization for Deep Neural Networks
Lei Huang, Xianglong Liu, Bo Lang +1
Optimizing deep neural networks (DNNs) often suffers from the ill-conditioned problem. We observe that the scaling-based weight space symmetry property in rectified nonlinear netwo…