Using cross lingual data to improve the performance of DNN-based Mandarin-speech recognition
碩士 === 國立交通大學 === 電信工程研究所 === 104 === Deep neural network (DNN) has been a popular research in automatic speech recognition. In this dissertation, we focus on implementing shared-hidden-layer language DNN acoustic model. The DNNs can be considered as a model that learns a complicated nonlinearity fe...
Main Authors: | , |
---|---|
Other Authors: | |
Format: | Others |
Language: | zh-TW |
Published: |
2016
|
Online Access: | http://ndltd.ncl.edu.tw/handle/20792580221343597206 |