CASIA OpenIR  > 模式识别国家重点实验室  > 语音交互
Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement
Liu, Bin1; Tao, Jianhua1; Wen, Zhengqi1; Mo, Fuyuan2; Bin Liu
2016-02-01
发表期刊JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
卷号82期号:2页码:141-150
文章类型Article
摘要This paper presents a speech enhancement approach based on analysis-synthesis framework. An improved multi-band summary correlogram (MBSC) algorithm is proposed for pitch estimation and voiced/unvoiced (V/UV) detection. The proposed pitch detection algorithm achieves a lower pitch detection error compared with the reference algorithm. The denoising autoencoder (DAE) is applied to enhance the line spectrum frequencies (LSFs). The reconstruction loss could be decreased compare with the swallow model. The proposed approach is evaluated using the perceptual evaluation of speech quality (PESQ) and the experimental results show that the proposed approach improves the performance of speech enhancement compared with the conventional speech enhancement approach. In addition, it could be applied to parametric speech coding even at low bit rate and low signal-noise ratio (SNR) environments.
关键词Analysis-synthesis Framework Multi-band Summary Correlogram Denoising Autoencoder Speech Enhancement Speech Coding
WOS标题词Science & Technology ; Technology
DOI10.1007/s11265-015-1025-1
关键词[WOS]SPECTRAL AMPLITUDE ESTIMATOR ; ERROR ; NOISE ; ALGORITHM ; PRIORS
收录类别SCI
语种英语
项目资助者National High-Tech Research and Development Program of China(863 Program)(2015AA016305) ; National Natural Science Foundation of China (NSFC)(61425017 ; Major Program for the National Social Science Fund of China(13ZD 189) ; Integration and application of basic science data in Chinese information processing field(XXH12504-1-11) ; 61403386 ; 61305003 ; 61332017 ; 61375027 ; 61273288 ; 61233009 ; 61203258)
WOS研究方向Computer Science ; Engineering
WOS类目Computer Science, Information Systems ; Engineering, Electrical & Electronic
WOS记录号WOS:000371299700002
引用统计
被引频次:2[WOS]   [WOS记录]     [WOS相关记录]
文献类型期刊论文
条目标识符http://ir.ia.ac.cn/handle/173211/11357
专题模式识别国家重点实验室_语音交互
通讯作者Bin Liu
作者单位1.Chinese Acad Sci, Inst Automat, Natl Lab Pattern Recognit, Beijing 100190, Peoples R China
2.Chinese Acad Sci, Inst Acoust, Beijing 100190, Peoples R China
推荐引用方式
GB/T 7714
Liu, Bin,Tao, Jianhua,Wen, Zhengqi,et al. Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement[J]. JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,2016,82(2):141-150.
APA Liu, Bin,Tao, Jianhua,Wen, Zhengqi,Mo, Fuyuan,&Bin Liu.(2016).Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement.JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY,82(2),141-150.
MLA Liu, Bin,et al."Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement".JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY 82.2(2016):141-150.
条目包含的文件 下载所有文件
文件名称/大小 文献类型 版本类型 开放类型 使用许可
Speech Enhancement B(695KB)期刊论文作者接受稿开放获取CC BY-NC-SA浏览 下载
个性服务
推荐该条目
保存到收藏夹
查看访问统计
导出为Endnote文件
谷歌学术
谷歌学术中相似的文章
[Liu, Bin]的文章
[Tao, Jianhua]的文章
[Wen, Zhengqi]的文章
百度学术
百度学术中相似的文章
[Liu, Bin]的文章
[Tao, Jianhua]的文章
[Wen, Zhengqi]的文章
必应学术
必应学术中相似的文章
[Liu, Bin]的文章
[Tao, Jianhua]的文章
[Wen, Zhengqi]的文章
相关权益政策
暂无数据
收藏/分享
文件名: Speech Enhancement Based on Analysis-Synthesis Framework with Improved Parameter Domain Enhancement.pdf
格式: Adobe PDF
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。