Cost Reduction of Training Mapping Function Based on Multistep Voice Conversion
Cost Reduction of Training Mapping Function Based on Multistep Voice Conversion
复制标题
基于多步语音转换的训练映射函数成本降低
DOI：
10.1109/icassp.2007.367007
复制
发表时间：
2007
期刊：
影响因子：
--
通讯作者：
M. Shozakai
中科院分区：
文献类型：
--
作者：
T. Masuda;M. Shozakai
已经开发了几种基于统计方法的从一个扬声器到另一个扬声器的语音转换方法。在作为这些方法中的典型方法的统计频谱映射方法中，使用频谱特征来确定表示不同说话者之间的相关性的映射函数。该技术的问题在于，需要为每个说话者对训练映射函数。如果发言者人数大幅增加，培训费用必然成为一个严重的问题。本文提出了一种新的语音转换方法，以减少训练成本。该技术易于实现，并且可以直接使用常规技术。实验结果表明，转换后的语音几乎保持了传统的质量，尽管显着的训练成本降低所提出的方法。
Several approaches based on a statistical method for voice conversion from one speaker to another have been developed. In a statistical spectral mapping method which is a typical one in these approaches, a mapping function which represents a correlation between different speakers is determined using spectral features. This technique has the problem that it is necessary to train the mapping function for each speaker pair. The training cost must become a serious issue in case that the number of speakers increases significantly. This paper describes a novel voice conversion method for reducing the training cost. This technique is easily implemented and can use conventional techniques directly. Experimental results demonstrate that the converted speech is almost maintaining the conventional quality despite the significant training cost reduction by the proposed method.