Sequence-to-Sequence Asr Optimization Via Reinforcement Learning
Sequence-to-Sequence Asr Optimization Via Reinforcement Learning
Despite the success of sequence-to-sequence approaches in automatic speech recognition (ASR) systems, the models still suffer from several problems, mainly due to the mismatch between the training and inference conditions. In the sequence-to-sequence architecture, the model is trained to predict the grapheme of the current time-step given the input of …