A Preliminary Study on Deep Neural Network-based Voice Conversion
碩士 === 國立臺北科技大學 === 電子工程系 === 106 === The purpose of this paper is to strengthen the conversion of sounds and convert the voice of the source speaker voice into a high-similar target speaker voice. In the paper, the speech conversion of parallel corpus is transformed into the traditional DNN model a...
Main Authors: | Ya-Bo Chai, 蔡亞伯 |
---|---|
Other Authors: | 廖元甫 |
Format: | Others |
Language: | zh-TW |
Published: |
2018
|
Online Access: | http://ndltd.ncl.edu.tw/handle/g2eddf |
Similar Items
-
Multimodal Voice Conversion Under Adverse Environment Using a Deep Convolutional Neural Network
by: Jian Zhou, et al.
Published: (2019-01-01) -
Study of Deep Learning-Based Voice Conversion Systemfor Dysarthria Speech
by: Hsiu-Wei Yeh, et al.
Published: (2018) -
A Preliminary Study on ALS Patient-Oriented Voice Conversion System
by: HUANG, BAI-HONG, et al.
Published: (2019) -
A Preliminary Study on Deep Neural Network-based License Plate Recognition
by: SU, SHIH-SN, et al.
Published: (2019) -
Adversarial Attack and Defense on Deep Neural Network-Based Voice Processing Systems: An Overview
by: Xiaojiao Chen, et al.
Published: (2021-09-01)