Automatic Sentence Selection from Speech Corpora Including Diverse Speech for Improved HMM-TTS Synthesis Quality
Automatic Sentence Selection from Speech Corpora Including Diverse Speech for Improved HMM-TTS Synthesis Quality
复制标题
从包括多种语音在内的语音语料库中自动选择句子，以提高 HMM-TTS 合成质量
DOI：
--
复制
发表时间：
2011
期刊：
影响因子：
--
通讯作者：
S. Buchholz
中科院分区：
文献类型：
--
作者：
N. Braunschweiler;S. Buchholz
使用公共可用的有声读物的HMM-TTS提出了新的挑战。本文探讨有声读物中的言语差异问题。其目的是识别可能对HMM-TTS质量产生负面影响的不同语音。手动删除不同的语音被发现产生更好的合成质量，尽管减半的训练语料库。为了处理大量的数据，提出了一种自动方法。该方法使用一小部分基于声学和文本的特征。一系列的听力测试表明，手动选择是最受欢迎的，而自动选择显示出显着的偏好超过了整个训练集。索引术语：语音合成，HMM-TTS，语料库创建，多样化语音，说话风格，有声读物
Using publicly available audiobooks for HMM-TTS poses new challenges. This paper addresses the issue of diverse speech in audiobooks. The aim is to identify diverse speech likely to have a negative effect on HMM-TTS quality. Manual removal of diverse speech was found to yield better synthesis quality despite halving the training corpus. To handle large amounts of data an automatic approach is proposed. The approach uses a small set of acoustic and text based features. A series of listening tests showed that the manual selection is most preferred, while the automatic selection showed significant preference over the full training set. Index Terms: speech synthesis, HMM-TTS, corpus creation, diverse speech, speaking styles, audiobooks