漢語之端到端語音合成研究;Mandarin End-To-End Text-To-Speech Research

NCUIR > College of Electrical Engineering & Computer Science > Executive Master of Computer Science and Information Engineering > Electronic Thesis & Dissertation > Item 987654321/81960

Please use this identifier to cite or link to this item: http://ir.lib.ncu.edu.tw/handle/987654321/81960

Title:	漢語之端到端語音合成研究;Mandarin End-To-End Text-To-Speech Research
Authors:	王紹全;WANG, SHAO-CHUAN
Contributors:	資訊工程學系在職專班
Keywords:	端到端;語音合成;深度學習;End-To-End;speech synthesis;deep learning
Date:	2019-09-25
Issue Date:	2020-01-07 15:10:34 (UTC+8)
Publisher:	國立中央大學
Abstract:	語音合成即指將文本合成語音的技術，在過去一個語音合成系統通常分多個階段處理，並涉及了語音學、聲學等相關領域知識，因此造就了高的技術門檻，由於近年來硬體技術的提升，以往基於神經網絡架構的深度學習方法在近期廣為研究者使用，本論文亦將深度學習技術應用到文字轉語音(TTS)系統上，利用端到端語音合成架構，透過訓練用語音訓練出單一神經網路模型，捨棄傳統由時間模型、聲學特徵等多個模型生成語音的架構，只使用一個端到端模型，輸入文字即可生成目標語音。目前常見的端到端語音合成研究以英語語系為主，然而，只要找到文字和語音的對應關係，我們也可將其應用在其他非英語語系合成，本論文利用漢語拼音方案的字母音標取代中文注音，以此取代中文文字作為訓練的資料，以實現中文的語音合成，未來也希望能以此概念將端到端語音合成推廣到其他非英文語系的使用。;Speech synthesis refers to the technique of synthesizing text into speech,In the past a speech synthesis system usually has multiple stages of processing, and it also related to phonetics, acoustics or other related domain knowledge, which creates high technical threshold. Due to the advancement of hardware technology in recent years, the deep learning methods based on neural network architecture have been widely used by researchers recently. This paper also applies deep learning technology to text-to-speech. (TTS) system , by using End-To-End speech synthesis architecture, training a single neural network model through audio training data, and abandoning the traditional architecture of generating speech from multiple models such as time models and acoustic features, use only an end-to-end model to enter the text to generate the target speech . Current End-To-End speech synthesis research is mainly in English, however, as long as we find the correspondence between text and speech, we can also apply it to other non-English language synthesis. This thesis replaces Chinese phonetic transcription with the phonetic symbols from Scheme of the Chinese Phonetic Alphabet, which replaces Chinese characters as training materials to achieve Chinese speech synthesis. And I hope that this concept can be used to implement other non-English languages end-to-end speech synthesis too.
Appears in Collections:	[Executive Master of Computer Science and Information Engineering] Electronic Thesis & Dissertation

Files in This Item:

File	Description	Size	Format
index.html		0Kb	HTML	334	View/Open

社群 sharing

Loading...