Cross-language Voice Conversion Evaluation Using Bilingual Databases
Cross-language Voice Conversion Evaluation Using Bilingual Databases
复制标题
使用双语数据库进行跨语言语音转换评估
DOI：
--
复制
发表时间：
2002
期刊：
影响因子：
--
通讯作者：
N. Campbell
中科院分区：
文献类型：
--
作者：
Miki Mashimo;T. Toda;Hiromichi Kawanami;K. Shikano;N. Campbell
本文描述了测试扩展技术的实验，该技术用于将一个说话者的声音转换为像另一个说话者的声音，以包括跨语言的话语，例如口语翻译或语言训练应用所需的。特别是，它解决了系统性能的评估问题，并比较客观的测试，使用感知动机的声学措施，与声音质量和扬声器相似性的感知测试。该方法使用日语和英语语音数据库从2名女性和2名男性双语扬声器的训练系统的基础上高斯混合模型（GMM）和高质量的声码器。结果表明，使用跨语言模型进行训练也可以在源和目标说话人的声音之间产生紧密的声学匹配。感知测试显示，在单语言和跨语言数据对上训练的映射函数的性能几乎没有显著差异。
This paper describes experiments that test an extension of techniques for converting the voice of one speaker to sound like that of another speaker, to include cross-language utterances, such as would be required for spoken language translation or language training applications. In particular, it addresses the issue of evaluation of system performance, and compares objective tests using a perceptually-motivated acoustic measure, with perceptual tests of voice quality and speaker resemblance. The proposed method uses Japanese and English speech databases from 2 female and 2 male bilingual speakers for training in a system based on a Gaussian mixture model (GMM) and a high quality vocoder. Results indicate that training with cross-language models also produces close acoustic matches between source and target speakers’ voices. Perceptual tests revealed little significant difference in the performance of mapping functions trained on single-language and cross-language data pairs.