Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52009| Title: | 使用向量量化技術來達成語音轉換 Using Vector Quantization To Achieve Voice Conversion |
| Authors: | Da-Yi Wu 吳達懿 |
| Advisor: | 呂育道(Yuh-Dauh Lyuu) |
| Co-Advisor: | 李宏毅(Hung-yi Lee) |
| Keyword: | 語音轉換,向量量化,深度學習, voice conversion,vector quantization,deep learning, |
| Publication Year : | 2020 |
| Degree: | 碩士 |
| Abstract: | 本論文提出了一套基於向量量化的深度語者轉換模型。 與此同時，本文對此方法與其他現存的方法做了多種客觀、主觀的評估。結果顯示，本文所提出的方法在流利度以及語者相似度上都比現存的方法優秀。 This thesis proposes a vector quantization-based voice conversion approach. The objective and the subjective evaluations show that the proposed method performs better than other existing approaches in both audio naturalness and speaker similarity |
| URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/52009 |
| DOI: | 10.6342/NTU202002653 |
| Fulltext Rights: | 有償授權 |
| Appears in Collections: | 資訊工程學系 |
Files in This Item:
| File | Size | Format | |
|---|---|---|---|
| U0001-0708202016441000.pdf Restricted Access | 2.23 MB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.