| 王媛媛,王新宇,张明阳,周锋,赵力.基于平均模型和误差削减网络的语音转换系统*[J].,2023,42(3):620-626 |
| 基于平均模型和误差削减网络的语音转换系统* |
| A voice conversion system based on average model and error reduction network |
| 投稿时间：2022-02-16 修订日期：2023-05-05 |
| 中文摘要: |
| 现阶段用于语音转换的深度学习方法多是通过使用大量的训练数据来生成高质量的语音。本文提出了一种基于平均模型和误差削减网络的语音转换框架,可用于有限数量的训练数据。首先,基于CBHG网络的平均模型使用排除源说话人和目标说话人的多说话人语音数据进行训练；然后,在有限数量的目标语音数据下对平均模型执行自适应训练；最后,提出一种误差削减网络,可以进一步改善转换后语音的质量。实验表明,所提出的语音转换框架可以灵活地处理有限的训练数据,并且在客观和主观评估方面均优于传统框架。 |
| 英文摘要: |
| So far, many of the deep learning approaches for voice conversion produce good quality speech by using a large amount of training data. This paper presents an average model and error reduction network-based voice conversion framework that can work with a limited amount of training data. We propose to implement a CBHG based average model that is trained with data from many speakers excluding source and target speakers; then, we propose to perform adaptation with a limited amount of target data; Last, we propose an error reduction network that can improve the voice conversion quality even further. The experiments show that the proposed voice conversion framework is flexible to work with limited training data and outperforms the traditional frameworks in both objective and subjective evaluations. |
| DOI：10.11684/j.issn.1000-310X.2023.03.021 |
| 中文关键词: 语音转换，CBHG，平均模型，误差削减网络 |
| 英文关键词: voice conversion, CBHG, average model, error reduction network |
| 基金项目:国家自然科学基金项目(61673108，62076215)；江苏省高等学校自然科学研究重大项目 (19KJA110002) |
|
| 摘要点击次数: 427 |
| 全文下载次数: 533 |
|
查看全文
查看/发表评论 下载PDF阅读器 |
| 关闭 |
