Dictionary evaluation and optimization for sparse coding based speech processing

Dictionary evaluation and optimization for sparse coding based speech processing
复制标题

基于稀疏编码的语音处理的字典评估和优化

DOI:
10.1016/j.ins.2015.03.010
复制
发表时间:
2015-07
影响因子:
8.1
通讯作者:
Han, Jiqing
Han, Jiqing
中科院分区:
计算机科学1区
文献类型:
--
作者:
He, Yongjun;Chen, Deyun;Sun, Guanglu;Han, Jiqing

文献摘要

参考文献

被引文献

相似文献

近年来,稀疏编码在语音处理中引起了广泛的关注。稀疏编码作为一种很有前途的技术,在语音分析、表示、压缩、去噪和分离等方面有着广泛的应用。为了精确和稀疏地表示信号,包含基本信号的良好字典是优选的,并且已经提出了许多方法来学习这样的字典。然而,目前还缺乏一种合理的评价方法来判断一部词典是否足够好。为了解决这个问题,我们定义了一组字典评估的措施。这些措施不仅解决了信号表示的稀疏性和重构误差,而且考虑了去噪和分离性能。我们展示了如何用这些度量来评价词典,并进一步提出了两种通过改进相关度量来优化词典的方法。第一种方法通过去除不重要的原子来提高稀疏编码的效率;第二种方法通过去除有害原子来提高字典的去噪性能。实验结果表明,该方法可以提供合理的评价,所提出的优化方法可以进一步改善给定的字典。
Recently, sparse coding has attracted considerable attention in speech processing. As a promising technique, sparse coding can be widely used for analysis, representation, compression, denoising and separation of speech. To represent signals accurately and sparsely, a good dictionary which contains elemental signals is preferred and many methods have been proposed to learn such a dictionary. However, there is a lack of reasonable evaluation methods to judge whether a dictionary is good enough. To solve this problem, we define a group of measures for dictionary evaluation. These measures not only address sparseness and reconstruction error of signal representation, but also consider denoising and separating performance. We show how to evaluate dictionaries with these measures, and further propose two methods to optimize dictionaries by improving relative measures. The first method improves the efficiency of sparse coding by removing unimportant atoms; the second one improves denoising performance of dictionaries by removing harmful atoms. Experimental results show that the measures can provide reasonable evaluations and the proposed methods for optimization can further improve given dictionaries.
DOI: 10.1017/cbo9780511794308
发表时间: 2012
期刊: --
影响因子: --
作者:
Gitta Kutyniok
通讯作者: Gitta Kutyniok
DOI: 10.1109/icassp.2012.6288956
发表时间: 2012-03
期刊: 2012 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
影响因子: --
作者:
Yongjun He;Jiqing Han;Shiwen Deng;Tieran Zheng;Guibin Zheng
通讯作者: Yongjun He;Jiqing Han;Shiwen Deng;Tieran Zheng;Guibin Zheng
DOI: 10.1109/lsp.2013.2285218
发表时间: 2013-10
影响因子: 3.9
作者:
M. Sadeghi;M. Babaie-zadeh;C. Jutten
通讯作者: M. Sadeghi;M. Babaie-zadeh;C. Jutten
DOI: --
发表时间: --
期刊: --
影响因子: --
作者:
Jort Florent Gemmeke;Hugo Van Hamme;B. Cranen;L. Boves
通讯作者: Jort Florent Gemmeke;Hugo Van Hamme;B. Cranen;L. Boves
DOI: 10.1016/b978-0-12-466606-1.x5000-4
发表时间: 1998
期刊: --
影响因子: --
作者:
S. Mallat
通讯作者: S. Mallat