2 papers
cs.CL2019
Approximating probabilistic models as weighted finite automata
Ananda Theertha Suresh, Brian Roark, Michael Riley +1
Weighted finite automata (WFA) are often used to represent probabilistic models, such as -gram language models, since they are efficient for recognition tasks in time and space.…
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-…