arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1709.07552cs.SDeess.AS
收藏

语音合成技术与挑战

Techniques and Challenges in Speech Synthesis

The University of Newcastle, Australia(澳大利亚纽卡斯尔大学)

David Ferris

摘要:

本项目的目的是开发和实现一个英语文本到语音合成系统。这包括对人类语音产生机制的研究,对语音合成技术的回顾,以及对用于评估合成语音有效性的测试的分析。确定双音合成系统是本项目范围内最有效的选择。设计了一种从提示语音中自动识别和提取双音素的方法,允许说话人在不到40分钟的时间内创建双音素数据库。CMUdict用于确定已知单词的发音。设计并实现了一个用于平滑双音子记录之间的过渡的系统。CMUdict然后被用来训练最大似然预测系统,以确定未知的英语字母词的正确发音。然后,设计了一个词性标注器来查找句子中单词的词汇类。设计了一种随时间改变所产生语音的音高、时长和音量的方法,该方法是TD-PSOLA算法和一种称为清音语音时长移位的新方法的组合。这最大限度地减少了在改变音调或持续时间时语音的失真,同时通过在时域中操作来最大限度地提高计算效率。这种方法被用来在单词中的元音上添加正确的词汇重音。开发了一个文本标记化系统来处理任意文本输入,允许数字输入标记的发音和使用适当的标点停顿。讨论了进一步提高句子级语音自然度的方法。最后,该系统进行了测试,其清晰度和自然的听众。

英文摘要:

The aim of this project was to develop and implement an English language Text-to-Speech synthesis system. This involved a study of mechanisms of human speech production, a review of techniques in speech synthesis, and analysis of tests used to evaluate the effectiveness of synthesized speech. It was determined that a diphone synthesis system was the most effective choice for the scope of this project. A method of automatically identifying and extracting diphones from prompted speech was designed, allowing for the creation of a diphone database by a speaker in less than 40 minutes. CMUdict was used to determine the pronunciation of known words. A system for smoothing the transitions between diphone recordings was designed and implemented. CMUdict was then used to train a maximum-likelihood prediction system to determine the correct pronunciation of unknown English language alphabetic words. Then, a Part Of Speech tagger was designed to find the lexical class of words within a sentence. A method of altering the pitch, duration, and volume of the produced voice over time was designed, being a combination of the TD-PSOLA algorithm and a novel approach referred to as Unvoiced Speech Duration Shifting. This minimises distortion of the voice when shifting the pitch or duration, while maximising computational efficiency by operating in the time domain. This approach was used to add correct lexical stress to vowels within words. A text tokenisation system was developed to handle arbitrary text input, allowing pronunciation of numerical input tokens and use of appropriate pauses for punctuation. Methods for further improving sentence level speech naturalness were discussed. Finally, the system was tested with listeners for its intelligibility and naturalness.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑