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: | Chia-Hao Chen, 陳家豪 |
---|---|
Other Authors: | Tsung-Han Tsai |
Format: | Others |
Language: | en_US |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/zde779 |
Similar Items
-
Modeling the ASR Induced Strains and Cracking of Reinforced Concrete Beams
by: Zhang, Li
Published: (2013) -
Experimental investigation of ASR/DEF-induced reinforcing bar fracture
by: Webb, Zachary David
Published: (2012) -
An Investigation on the Impact of ASR Software Feedback on EFL College Students' Pronunciation Learning
by: Kuotai Chen, et al.
Published: (2005) -
ASR in the presocratics and Plato
by: Bargrave-Weaver, Derek
Published: (1956) -
Transfer Learning for Domain and Environment Adaptation in Serbian ASR
by: B. Z. Popović, et al.
Published: (2020-12-01)