Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis

Exploiting Morphological and Phonological Features to Improve Prosodic Phrasing for Mongolian Speech Synthesis
复制标题

利用形态和语音特征来改进蒙古语语音合成的韵律短语

DOI:
10.1109/taslp.2020.3040523
复制
发表时间:
2021
期刊:
IEEE/ACM Transactions on Audio Speech and Language Processing
影响因子:
--
通讯作者:
Haizhou Li
Haizhou Li
中科院分区:
其他
文献类型:
--
作者:
Rui Liu;Berrak Sisman;Feilong Bao;Jichen Yang;Guanglai Gao;Haizhou Li

文献摘要

参考文献

被引文献

相似文献

韵律短语是影响文语合成自然度和可懂度的重要因素。研究表明,当有大量文本和语音语料库可用时,深度学习技术可以改善韵律措辞。然而,对于低资源语言,如蒙古语,韵律短语仍然是一个挑战,出于各种原因。首先,适合系统训练的数据库有限。第二,在韵律短语建模中,没有使用能够提供韵律信息的词语组成知识。为了解决这些问题,在这篇文章中,我们提出了一种结合自注意神经分类器的特征增强方法。我们增加输入文本的形态和语音分解的话,以提高文本编码器。我们研究了使用自注意分类器,它利用一个句子的全局上下文,作为一个解码器的短语中断预测。客观和主观评价都验证了所提出的短语中断预测框架的有效性,该框架在蒙古文语音合成系统中持续提高语音质量。
Prosodic phrasing is an important factor that affects naturalness and intelligibility in text-to-speech synthesis. Studies show that deep learning techniques improve prosodic phrasing when large text and speech corpus are available. However, for low-resource languages, such as Mongolian, prosodic phrasing remains a challenge for various reasons. First, the database suitable for system training is limited. Second, word composition knowledge that is prosody-informing has not been used in prosodic phrase modeling. To address these problems, in this article, we propose a feature augmentation method in conjunction with a self-attention neural classifier. We augment input text with morphological and phonological decompositions of words to enhance the text encoder. We study the use of self-attention classifier, that makes use of global context of a sentence, as a decoder for phrase break prediction. Both objective and subjective evaluations validate the effectiveness of the proposed phrase break prediction framework, that consistently improves voice quality in a Mongolian text-to-speech synthesis system.
DOI: --
发表时间: 2011
期刊: --
影响因子: --
作者:
通讯作者: --
DOI: 10.1609/aaai.v33i01.33016706
发表时间: 2018-09
期刊: --
影响因子: --
作者:
Naihan Li;Shujie Liu;Yanqing Liu;Sheng Zhao;Ming Liu-
通讯作者: Naihan Li;Shujie Liu;Yanqing Liu;Sheng Zhao;Ming Liu-
DOI: 10.21437/interspeech.2020-2014
发表时间: 2020-05
期刊: The International Journal of Plant, Animal and Environmental Sciences
影响因子: --
作者:
Kun Zhou;Berrak Sisman;Mingyang Zhang;Haizhou Li
通讯作者: Kun Zhou;Berrak Sisman;Mingyang Zhang;Haizhou Li
DOI: 10.21437/odyssey.2020-33
发表时间: 2020-02
期刊: --
影响因子: --
作者:
Kun Zhou;Berrak Sisman;Haizhou Li
通讯作者: Kun Zhou;Berrak Sisman;Haizhou Li
DOI: 10.1109/icassp.2019.8682770
发表时间: 2019-05
期刊: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
Chunhui Lu;Pengyuan Zhang;Yonghong Yan
通讯作者: Chunhui Lu;Pengyuan Zhang;Yonghong Yan