基于相似关联度神经网络的音频频带扩展

doi:10.3969/j.issn.0372-2112.2015.04.028

电子学报 ›› 2015, Vol. 43 ›› Issue (4): 816-821.DOI: 10.3969/j.issn.0372-2112.2015.04.028

基于相似关联度神经网络的音频频带扩展

刘鑫, 鲍长春

北京工业大学电子信息与控制工程学院, 北京 100124

收稿日期:2013-10-11 修回日期:2014-02-17 出版日期:2015-04-25
- 作者简介:
- 刘鑫男.1986年9月出生于北京.现为北京工业大学博士研究生.主要研究方向为语音与音频信号处理.E-mail:liuxin0930@emails.bjut.edu.cn;鲍长春 男,1965年6月出生于内蒙古赤峰市,博士,教授,博士生导师,主要研究方向为语音与音频信号处理.E-mail:chchbao@bjut.edu.cn
- 基金资助:
- 国家自然科学基金 (No.61072089)

Audio Bandwidth Extension Method Using Similarity Correlation Degree-Based Neural Network

LIU Xin, BAO Chang-chun

School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China

Received:2013-10-11 Revised:2014-02-17 Online:2015-04-25 Published:2015-04-25
- Supported by:
- National Natural Science Foundation of China (No.61072089)

摘要/Abstract

摘要：

宽带音频带宽的限制会降低其主观质量和自然度.本文提出了一种基于相似关联度神经网络的宽带向超宽带音频频带扩展方法.该方法将宽带音频的精细谱重构成多维相空间,并建立相似关联度神经网络来恢复高频成分的精细谱,同时借助高斯混合模型估计高频谱包络,并以G.722.1编码器为平台实现音频信号的带宽扩展.测试结果表明,本文方法扩展性能优于参考方法,其主观质量接近于G.722.1C超宽带编码器.

关键词: 音频编码, 音频频带扩展, 相似关联度神经网络, 相空间重构, 高斯混合模型

Abstract:

The bandwidth limitation of wideband audio degrades the subjective quality and the naturalness.In this paper,a bandwidth extension of audio signals from wideband to super-wideband was proposed by using a similarity correlation degree-based neural network.Firstly,the fine spectrum of wideband audio was converted to a multi-dimensional phase space.Then,a similarity correlation degree-based neural network was built up to reproduce the high-frequency fine spectrum.In addition,Gaussian mixture model was used to estimate the high-frequency spectral envelope.Finally,the bandwidth was extended to super-wideband by the proposed method in the ITU-T G.722.1 wideband codec.Evaluation results indicate that the proposed method is preferred over the reference methods and achieves a comparable subjective quality with the G.722.1C super-wideband codec.

Key words: audio coding, audio bandwidth extension, similarity correlation degree-based neural network, phase space reconstruction, Gaussian mixture model

中图分类号:

TN912.3

刘鑫, 鲍长春. 基于相似关联度神经网络的音频频带扩展[J]. 电子学报, 2015, 43(4): 816-821.

LIU Xin, BAO Chang-chun . Audio Bandwidth Extension Method Using Similarity Correlation Degree-Based Neural Network[J]. Acta Electronica Sinica, 2015, 43(4): 816-821.

参考文献

[1] P Vary,R Martin.Digital Speech Transmission—Enhancement,Coding and Error Concealment[M].UK:John Wiley & Sons Ltd,2006.
[2] P Ekstrand.Bandwidth extension of audio signals by spectral band replication[A].Proceedings of 1st IEEE Benelux Workshop on Model Based Processing and Coding of Audio[C].New Paltz,NY,USA:IEEE,2002.53-58.
[3] ITU-T Rec G.722.1,Coding at 24 and 32 kbit/s for Hands—free Operation in Systems with Low Frame Loss[S].
[4] E Larsen,R M Aarts.Audio Bandwidth Extension -Application of Psychoacoustics,Signal Processing and Loudspeaker Design[M].UK:John Wiley & Sons Ltd,2004.
[5] F Tobias,G Schuller.Spectral band replication tool for very low delay audio coding applications[A].Proceedings of IEEE Workshop on Applications of Signal Processing to Audio and Acoustics[C].New Paltz,NY,USA:IEEE,2007.199-202.
[6] A H Nour-Eldin,P Kabal.Memory-based approximation of the Gaussian mixture model framework for bandwidth extension of narrowband speech[A].Proceedings of Interspeech[C].Florence,Italy:ISCA,2011.1185-1188.
[7] P Jax,P Vary.Wideband extension of telephone speech using a hidden Markov model[A].Proceedings of IEEE Workshop on Speech Coding[C].Delavan,WI,USA:IEEE,2000.133-135.
[8] H Pulakka,P Alku.Bandwidth extension of telephone speech using a neural network and a filter bank implementation for highband mel spectrum[J].IEEE Transactions on Audio,Speech,and Language Processing,2011,19(7):2170-2183.
[9] ITU-T G.722.1 Annex C,Low complexity coding at 24 and 32 kb/s for hands-free operation in systems with low frame loss annex C 14khz mode at 24,32 and 48 kb/s[S].
[10] F Nagel,S Disch.A harmonic bandwidth extension method for audio codecs[A].Proceedings of IEEE International Conference on Acoustics,Speech and Signal Processing[C].Taipei,Taiwan:IEEE,2009.145-148.
[11] Y Sha,C Bao,M Jia,X Liu.High frequency reconstruction of audio signal based on chaotic prediction theory[A].Proceedings of IEEE International Conference on Acoustics Speech and Signal Processing[C].Dallas,Texas,USA:IEEE,2010.381-384.
[12] X Liu,C Bao,M Jia,Y Sha.Nonlinear bandwidth extension based on nearest-neighbor matching[A].Proceedings of the Second APSIPA Annual Summit and Conference[C].Biopolis,Singapore:APSIPA,2010.169-172.
[13] K Holger.Nonlinear Time Series Analysis,2nd edition[M].New York:Cambridge University Press,2004.
[14] M Small.Applied Nonlinear Time Series Analysis:Applications in Physics,Physiology and Finance[M].Singapore:World Scientific,2005.
[15] N H Packard,J P Crutchfield,J D Farmer,R S Shaw.Geometry from a time series[J].Physical Review Letters,1980,45(9):712-716.
[16] C Rhodes,M Morar.The false nearest neighbors algorithm:an overview[J].Computers & Chemical Engineering,1997,21:S1149-S1154.
[17] Liu Si-feng,Lin Yi.Grey Information—Theory and Practical Applications[M].USA:Springer-Verlag,2006.
[18] X Liu,C Bao,M Jia,Y Sha.A harmonic bandwidth extension based on Gaussian mixture model[A].Proceedings of the 10th International Conference on Signal Processing[C].Beijing,China:IEEE,2010.474-477.
[19] H Pulakka,L Laaksonen,M Vainio,J Pohjalainen,P Alku.Evaluation of an artificial speech bandwidth extension method in three languages[J].IEEE Transactions on Audio,Speech and Language Processing,2008,16(6):1124-1137.

基于相似关联度神经网络的音频频带扩展

Audio Bandwidth Extension Method Using Similarity Correlation Degree-Based Neural Network

PDF

可视化

摘要/Abstract

引用本文

使用本文

参考文献

相关文章 15

编辑推荐

Metrics

[1]	李凯, 张可心. 结构α-熵的加权高斯混合模型的子空间聚类[J]. 电子学报, 2022, 50(3): 718-725.
[2]	石雪, 李玉, 赵泉华. 自适应类别的层次高斯混合模型遥感影像分割[J]. 电子学报, 2020, 48(1): 131-136.
[3]	吴霞, 吴晓军, 史素真, 张其进, 张玉梅. 隐相空间的DUPSO-RPSOVF语音预测模型研究[J]. 电子学报, 2019, 47(9): 1875-1882.
[4]	练秋生, 侯亚伟, 苏月明, 石保顺. 基于高斯混合模型的衍射成像算法[J]. 电子学报, 2018, 46(10): 2347-2350.
[5]	田中大, 张超, 李树江, 王艳红, 沙毅. 基于相空间重构与最小二乘支持向量机的时延预测[J]. 电子学报, 2017, 45(5): 1044-1051.
[6]	栗雨晴, 礼欣, 韩煦, 宋丹丹, 廖乐健. 基于双语词典的微博多类情感分析方法[J]. 电子学报, 2016, 44(9): 2068-2073.
[7]	白海钏, 鲍长春, 刘鑫. 基于局部最小二乘支持向量机的音频频带扩展方法[J]. 电子学报, 2016, 44(9): 2203-2210.
[8]	车滢霞, 俞一彪. 约束条件下的结构化高斯混合模型及非平行语料语音转换[J]. 电子学报, 2016, 44(9): 2282-2288.
[9]	刘鑫, 鲍长春. 基于回声状态网络的音频频带扩展方法[J]. 电子学报, 2016, 44(11): 2758-2766.
[10]	李晓明, 鲍长春, 贾懋. 基于信号规整和稀疏变换的语音与音频分层编码方法[J]. 电子学报, 2015, 43(7): 1286-1293.
[11]	白海钏, 鲍长春, 刘鑫, 李红蕊. 基于灰色Verhulst模型的音频频带扩展方法[J]. 电子学报, 2014, 42(8): 1624-1629.
[12]	何玉文, 鲍长春, 夏丙寅. 基于AR-HMM在线能量调整的语音增强方法[J]. 电子学报, 2014, 42(10): 1991-1997.
[13]	李冬辉, 何鹏林. 基于GMM聚类的空调机组多未知模态辨识方法研究[J]. 电子学报, 2014, 42(10): 2004-2008.
[14]	钟尚平, 徐巧芬, 陈羽中, 何凤英. 一种基于LSB序列局部特征的通用隐写检测方法[J]. 电子学报, 2013, 41(2): 239-247.
[15]	芮瑞, 鲍长春. 基于非线性动力学的乐器分类方法[J]. 电子学报, 2012, 40(7): 1481-1488.