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 2003.02837eess.AScs.LGcs.SDstat.ML
收藏

基于语料库的单元选择文本转语音中的统计上下文相关单元边界校正

Statistical Context-Dependent Units Boundary Correction for Corpus-based Unit-Selection Text-to-Speech

Università di Pisa(比萨大学);Istituto di Scienze e Tecnologie della Cognizione, Consiglio Nazionale di Ricerca(国家研究委员会认知科学与技术研究所);University of Sheffield(谢菲尔德大学)

Claudio Zito, Fabio Tesser, Mauro Nicolao, Piero Cosi

摘要:

在这项研究中,我们提出了一种创新的说话人自适应技术,以提高应用于单元选择文本转语音(TTS)系统的分割的准确性。与传统的说话人自适应技术,试图提高分割的准确性,使用声学模型,更强大的扬声器的特点,面对,我们的目标是只使用上下文相关的特性外推与语言分析技术。简而言之,我们使用的直观的想法,上下文相关的信息是紧密相关的声波波形。我们提出了一个统计模型,预测校正值,以减少由一个国家的最先进的隐马尔可夫模型(HMM)的语音分割产生的系统误差。我们的方法包括两个阶段:(1)识别上下文相关的语音单元类(例如,识别元音作为单音节词的核心的类);(2)建立一个回归模型,该模型将ASR在单个说话人语料库分割过程中产生的平均误差值与每个类相关联。该方法的成功评估通过比较校正的边界的单位和国家的最先进的HHM分割对参考对齐,这应该是最佳的解决方案。总之,我们的工作提供了第一次分析的模型敏感的扬声器相关的特性,强大的缺陷和嘈杂的信息,和一个非常简单的实现,可以用作替代更昂贵的扬声器自适应系统或众多的手动校正会话。

英文摘要:

In this study, we present an innovative technique for speaker adaptation in order to improve the accuracy of segmentation with application to unit-selection Text-To-Speech (TTS) systems. Unlike conventional techniques for speaker adaptation, which attempt to improve the accuracy of the segmentation using acoustic models that are more robust in the face of the speaker's characteristics, we aim to use only context dependent characteristics extrapolated with linguistic analysis techniques. In simple terms, we use the intuitive idea that context dependent information is tightly correlated with the related acoustic waveform. We propose a statistical model, which predicts correcting values to reduce the systematic error produced by a state-of-the-art Hidden Markov Model (HMM) based speech segmentation. Our approach consists of two phases: (1) identifying context-dependent phonetic unit classes (for instance, the class which identifies vowels as being the nucleus of monosyllabic words); and (2) building a regression model that associates the mean error value made by the ASR during the segmentation of a single speaker corpus to each class. The success of the approach is evaluated by comparing the corrected boundaries of units and the state-of-the-art HHM segmentation against a reference alignment, which is supposed to be the optimal solution. In conclusion, our work supplies a first analysis of a model sensitive to speaker-dependent characteristics, robust to defective and noisy information, and a very simple implementation which could be utilized as an alternative to either more expensive speaker-adaptation systems or of numerous manual correction sessions.

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。

↑