Improve Top ASR Hypothesis with Re-correction by Reinforcement Learning
碩士 === 國立中央大學 === 資訊工程學系 === 107 === In real situations, utterances are transcribed by ASR(Automatic Speech Recognition) systems, which usually propose multiple candidate transcriptions(hypothesis). Most of the time, the first hypothesis is the best and most commonly used. But the first hypothesis o...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/zde779 |