助手标题  
全文文献 工具书 数字 学术定义 翻译助手 学术趋势 更多
查询帮助
意见反馈
   mel filter 的翻译结果: 查询用时:0.25秒
图标索引 在分类学科中查询
所有学科
电信技术
更多类别查询

图标索引 历史查询
 

mel filter
相关语句
  “mel filter”译为未确定词的双语例句
     The first one: based on the hearing system of the human, a new adaptive time frequency parameter considers both auditory and vocal tract character is proposed by studying the Mel filter bank. Simulation results have shown the performance of the algorithm is better than other existing algorithms.
     算法一:从基于人耳的听觉系统出发,对Mel标度滤波器组进行研究,提出了语音信号的一种新的自适应时频参数,该参数既考虑了声道响应,又符合人耳听觉特性,仿真结果表明了它的优越性。
短句来源
     This paper studies wavelet packet transform and analyzes the extraction of MFCC parameters. Comparing partition of frequency-band between MEL filter group and wavelet packet decomposition,we extract a new parameter,DBWPTC,based on wavelet packet transform. The experiment results indicate that the DBWPTC parameter is outperform MFCC.
     论文研究了小波包变换,分析了MFCC参数的提取,比较了MEL滤波器组频带划分和小波包分解的频带划分,提取出了基于小波包变换的特征参数(DBWPTC),实验结果表明通过小波包变换提取的语音特征参数DBWPTC优于通过傅立叶变换提取的特征参数MFCC。
短句来源
  相似匹配句对
     On the Filter
     关于共轭滤波器
短句来源
     melatonin(Mel);
     与IR组相比:RSG组、Mel组大鼠心肌、肾皮质ET一蛋白水平减低,eNOS蛋白水平升高。
短句来源
     Digital Filter
     数字滤波
短句来源
     Application of the Mel-scale Filter-bank for Speech Enhancement and Its Optimization Algorithm
     Mel域滤波在语音增强中的应用及其算法的优化
短句来源
     Finally, the wiener filter is applied directly on Mel-scale filterbank amplitude.
     最后,将维纳滤波器直接应用到Mel域滤波器组幅度上。
短句来源
查询“mel filter”译词为用户自定义的双语例句

    我想查看译文中含有:的双语例句
例句
为了更好的帮助您理解掌握查询词或其译词在地道英语中的实际用法,我们为您准备了出自英文原文的大量英语例句,供您参考。
  mel filter
This type of compensation is related to the logarithm applied on the Mel-filter bank channels in MFCC analysis.
      
Natural logarithm is performed on the outputs of the Mel filter bank.
      


A method of speaker recognition based on sub-band processing and multi-classifier combination is presented. The wideband speech signal is filtered into several sub-bands through Mel filter bank,and feature extraction is individually performed on each sub-band. The resulting sequences of feature vector are modeled and identified on each sub-band,and then the outputs from each separate classifier are fused to produce an overall decision. The experiment results show that the sub-band processing approach...

A method of speaker recognition based on sub-band processing and multi-classifier combination is presented. The wideband speech signal is filtered into several sub-bands through Mel filter bank,and feature extraction is individually performed on each sub-band. The resulting sequences of feature vector are modeled and identified on each sub-band,and then the outputs from each separate classifier are fused to produce an overall decision. The experiment results show that the sub-band processing approach has the best performance when the number of sub-bands is 16,and has a higher robustness for narrow-band noise compared with the method of wideband speech features modeling.

提出了一种基于子带处理多分类器融合的说话人识别方法 .宽带语音信号通过Mel滤波器组转变为多个子带信号 ,对各子带数据独立分析提取相应的特征参数 ,进而对每个子带分别建立识别模型进行判决 ,最后利用分类器融合规则 ,给出总体判决 .研究表明 ,该方法在子带数目选为 16时可以得到最好的识别效果 ,并且在有窄带噪声的情况下 ,子带多分类器融合法比宽带语音数据建模表现出更好的鲁棒性 .

This paper studies wavelet packet transform and analyzes the extraction of MFCC parameters.Comparing partition of frequency-band between MEL filter group and wavelet packet decomposition,we extract a new parameter,DBWPTC,based on wavelet packet transform.The experiment results indicate that the DBWPTC parameter is outperform MFCC.

论文研究了小波包变换,分析了MFCC参数的提取,比较了MEL滤波器组频带划分和小波包分解的频带划分,提取出了基于小波包变换的特征参数(DBWPTC),实验结果表明通过小波包变换提取的语音特征参数DBWPTC优于通过傅立叶变换提取的特征参数MFCC。

 
图标索引 相关查询

 


 
CNKI小工具
在英文学术搜索中查有关mel filter的内容
在知识搜索中查有关mel filter的内容
在数字搜索中查有关mel filter的内容
在概念知识元中查有关mel filter的内容
在学术趋势中查有关mel filter的内容
 
 

CNKI主页设CNKI翻译助手为主页 | 收藏CNKI翻译助手 | 广告服务 | 英文学术搜索
版权图标  2008 CNKI-中国知网
京ICP证040431号 互联网出版许可证 新出网证(京)字008号
北京市公安局海淀分局 备案号:110 1081725
版权图标 2008中国知网(cnki) 中国学术期刊(光盘版)电子杂志社