Improving Mandarin LVCSR Using Place and Manner Based Multi-task Learning
碩士 === 國立臺灣大學 === 資訊工程學研究所 === 107 === In large vocabulary continuous speech recognition (LVCSR), it is well known that the recognition performance has been improved by using DNN-HMM instead of GMM-HMM. In this thesis, we use multi-task learning model (MTL-DNN), aiming at simultaneously minimizing t...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2019
|
Online Access: | http://ndltd.ncl.edu.tw/handle/vsq74a |