论文标题
基于自动韵律注释的低资源蒙古语音综合
Low-Resource Mongolian Speech Synthesis Based on Automatic Prosody Annotation
论文作者
论文摘要
尽管VIT等基于深度学习的文本到语音（TTS）模型表现出了很好的结果，但它们通常需要一组相当大的高质量<文本，音频>对训练，这是昂贵的。到目前为止，世界上大多数语言仍然缺乏开发TTS系统所需的培训数据。本文提出了针对低资源蒙古语音综合面临的两个问题的两种改进方法：a）鉴于缺乏高质量的<文本，音频>对数据，因此很难将映射问题从语言特征到声学特征进行建模。使用预训练的VIT模型和转移学习方法进行改进。 b）考虑到标记不太标记的信息的问题，本文建议使用自动韵律注释方法标记文本的韵律信息和相应的语音，从而提高低资源蒙古语的自然性和清晰度。通过实证研究，本文提出的方法的N-MOS为4.195，I-MOS为4.228。
While deep learning-based text-to-speech (TTS) models such as VITS have shown excellent results, they typically require a sizable set of high-quality <text, audio> pairs to train, which is expensive to collect. So far, most languages in the world still lack the training data needed to develop TTS systems. This paper proposes two improvement methods for the two problems faced by low-resource Mongolian speech synthesis: a) In view of the lack of high-quality <text, audio> pairs of data, it is difficult to model the mapping problem from linguistic features to acoustic features. Improvements are made using pre-trained VITS model and transfer learning methods. b) In view of the problem of less labeled information, this paper proposes to use an automatic prosodic annotation method to label the prosodic information of text and corresponding speech, thereby improving the naturalness and intelligibility of low-resource Mongolian language. Through empirical research, the N-MOS of the method proposed in this paper is 4.195, and the I-MOS is 4.228.
