电子学报 ›› 2016, Vol. 44 ›› Issue (9): 2203-2210.DOI: 10.3969/j.issn.0372-2112.2016.09.027

• 学术论文 • 上一篇    下一篇

基于局部最小二乘支持向量机的音频频带扩展方法

白海钏, 鲍长春, 刘鑫   

  1. 北京工业大学电子信息与控制工程学院, 北京 100124
  • 收稿日期:2014-10-10 修回日期:2014-11-05 出版日期:2016-09-25
    • 通讯作者:
    • 刘鑫
    • 作者简介:
    • 白海钏 女,1986年出生,河北邯郸人,北京工业大学硕士研究生.主要研究方向为音频信号处理.E-mail:baihaichuan@emails.bjut.edu.cn;鲍长春 男,1965年出生,内蒙古赤峰人,博士,北京工业大学教授、博士生导师,IEEE高级会员,国际语音通信学会(ISCA)会员,亚太信号与信息处理学会(APSIPA)会员,中国电子学会理事,中国声学学会理事,信号处理专业委员会委员.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:
    • 国家自然科学基金项目 (No.61072089,No.61471014)

Audio Bandwidth Extension Method Based on Local Least Square Support Vector Machine

BAI Hai-chuan, BAO Chang-chun, LIU Xin   

  1. School of Electronic Information and Control Engineering, Beijing University of Technology, Beijing 100124, China
  • Received:2014-10-10 Revised:2014-11-05 Online:2016-09-25 Published:2016-09-25
    • Supported by:
    • National Natural Science Foundation of China (No.61072089, No.61471014)

摘要:

在网络传输过程中宽带音频会由于高频信息的缺失导致音频质量下降,因此,本文提出了一种基于局部最小二乘支持向量机的宽带向超宽带音频频带扩展方法.根据音频频域序列的非线性特性,本文采用相空间重构和局部最小二乘支持向量机对音频信号的高频频谱细节进行预测,并结合高斯混合模型对高频子带能量进行估计,最后经过高频频谱包络调整,所提方法能够有效地恢复7kHz~14kHz频率范围内的高频成分.主客观测试结果表明,该方法改善了宽带音频的听觉质量,其性能优于参考音频频带扩展方法.

关键词: 音频编码, 频带扩展, 高斯混合模型, 局部最小二乘支持向量机

Abstract:

The auditory quality of wideband audio is generally degraded due to the lack of the high-frequency in network transmission,so this paper presents a kind of audio bandwidth extension method from wideband to super wideband based on local least square support vector machine.In the light of the nonlinearity of audio spectrum,the high-frequency fine spectrum of audio signals is predicted by using phase space reconstruction and local least square support vector machine.Combining with the estimation of high-frequency sub-band energy based on Gaussian mixture model,the proposed method can effectively recover the high-frequency components in the frequency range 7kHz~14kHz through the envelope adjustment of high-frequency spectrum at last.Subjective and objective testing results indicate that the proposed method improves the auditory quality of wideband audio and outperforms the reference methods of audio bandwidth extension.

Key words: audio coding, bandwidth extension, Gaussian mixture model, local least square support vector machine

中图分类号: