Multi-band discriminant speech synthesis analysis based on Natural Language Processing

Songjia Liu, Yuancheng Yao, Binyu Liu, Rui Zhu, Jing Ren
{"title":"Multi-band discriminant speech synthesis analysis based on Natural Language Processing","authors":"Songjia Liu, Yuancheng Yao, Binyu Liu, Rui Zhu, Jing Ren","doi":"10.1109/ICSP54964.2022.9778506","DOIUrl":null,"url":null,"abstract":"With the rapid development of neural networks and deep learning, speech synthesis technology has been significantly improved. The end-to-end speech synthesis systems based on deep learning have been able to synthesize speech with naturalness close to the original human pronunciation. However, the existing end-to-end speech synthesis system model is complex, and it is impossible to achieve real-time speech synthesis on devices with low computing power. In this paper, a multi-band discriminative autoregressive speech synthesis model is proposed based on natural language processing. The model uses an encoder-decoder architecture with attention mechanism, which is mainly composed of DSC-GRN modules. Stacking multiple convolutions with different expansion coefficients by gating the residual structure can increase the receptive field so that the encoder and decoder can pay attention to the context information with a longer time span, which can improve the performance of the model. The whole model uses full convolution architecture and can be trained in parallel. Compared with the existing autoregressive model, the number of parameters of the model is greatly reduced. The synthesis speed is improved, and the quality of synthesized speech is ensured.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"265 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"1","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1109/ICSP54964.2022.9778506","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 1

Abstract

With the rapid development of neural networks and deep learning, speech synthesis technology has been significantly improved. The end-to-end speech synthesis systems based on deep learning have been able to synthesize speech with naturalness close to the original human pronunciation. However, the existing end-to-end speech synthesis system model is complex, and it is impossible to achieve real-time speech synthesis on devices with low computing power. In this paper, a multi-band discriminative autoregressive speech synthesis model is proposed based on natural language processing. The model uses an encoder-decoder architecture with attention mechanism, which is mainly composed of DSC-GRN modules. Stacking multiple convolutions with different expansion coefficients by gating the residual structure can increase the receptive field so that the encoder and decoder can pay attention to the context information with a longer time span, which can improve the performance of the model. The whole model uses full convolution architecture and can be trained in parallel. Compared with the existing autoregressive model, the number of parameters of the model is greatly reduced. The synthesis speed is improved, and the quality of synthesized speech is ensured.
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
基于自然语言处理的多波段判别语音合成分析
随着神经网络和深度学习的快速发展,语音合成技术得到了显著的提高。基于深度学习的端到端语音合成系统已经能够合成接近人类原始语音的自然度语音。然而,现有的端到端语音合成系统模型复杂,无法在低计算能力的设备上实现实时语音合成。提出了一种基于自然语言处理的多波段判别自回归语音合成模型。该模型采用具有注意机制的编码器-解码器体系结构,主要由DSC-GRN模块组成。通过对残差结构进行门控,叠加不同展开系数的多个卷积,可以增加接收场,使编码器和解码器能够在更长的时间跨度上关注上下文信息,从而提高模型的性能。整个模型采用全卷积架构,可以并行训练。与现有的自回归模型相比,该模型的参数数量大大减少。提高了合成速度,保证了合成语音的质量。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Research on Retailer Churn Prediction Based on Spatial-Temporal Features Non-sinusoidal harmonic signal detection method for energy meter measurement Deep Intra-Class Similarity Measured Semi-Supervised Learning Adaptive Persymmetric Subspace Detector for Distributed Target Deblurring Reconstruction of Monitoring Video in Smart Grid Based on Depth-wise Separable Convolutional Neural Network
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1