DeepMine-Multi-TTS: A Persian Speech Corpus for Multi-Speaker Text-to-Speech

Author:

Adibian Majid1,Zeinali Hossein1,Barmaki Soroush1

Affiliation:

1. Amirkabir University of Technology

Abstract

Abstract

Speech synthesis has made significant progress in recent years thanks to deep neural networks (DNNs). However, one of the challenges of DNN-based models is the requirement for large and diverse data, which limits their applicability to many languages and domains. To date, no multi-speaker text-to-speech (TTS) dataset has been available in Persian, which hinders the development of these models for this language. In this paper, we present a novel dataset for multi-speaker TTS in Persian, which consists of 120 hours of high-quality speech from 67 speakers. We use this dataset to train two synthesizers and a vocoder and evaluate the quality of the synthesized speech. The results show that the naturalness of the generated samples, measured by the mean opinion score (MOS) criterion, is 3.94 and 4.12 for two trained multi-speaker synthesizers, which indicates that the dataset is suitable for training multi-speaker TTS models and can facilitate future research in this area for Persian.

Publisher

Springer Science and Business Media LLC

Reference41 articles.

1. Ramsay, Gordon J (2019) Mechanical Speech Synthesis in Early Talking Automata. Acoustics Today 15(2): 11--19

2. Khan, Rubeena A and Chitode, Janardan Shrawan (2016) Concatenative speech synthesis: A Review. International Journal of Computer Applications 136(3): 1--6 Citeseer

3. Ren, Yi and Ruan, Yangjun and Tan, Xu and Qin, Tao and Zhao, Sheng and Zhao, Zhou and Liu, Tie-Yan (2019) Fastspeech: Fast, robust and controllable text to speech. Neural Information Processing Systems

4. Ren, Yi and Hu, Chenxu and Tan, Xu and Qin, Tao and Zhao, Sheng and Zhao, Zhou and Liu, Tie-Yan (2021) Fastspeech 2: Fast and high-quality end-to-end text to speech. International Conference on Learning Representations

5. {\L}a{\'n}cucki, Adrian (2021) Fastpitch: Parallel text-to-speech with pitch prediction. IEEE, 6588--6592, ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3