Sequence-to-Sequence Asr Optimization Via Reinforcement Learning.

Andros Tjandra Sakriani Sakti Satoshi Nakamura

Published in: ICASSP (2018)

Keyphrases

reinforcement learning
artificial intelligence
input data
optimization algorithm
long sequences
databases
data mining
genetic algorithm
learning algorithm
search algorithm
optimization problems
global optimization
pseudorandom
hidden state