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
   feature compensation 的翻译结果: 查询用时:0.006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
 

feature compensation
相关语句
  特征补偿
     The Application of Feature Compensation Method Based on Probability Model in Speech Recognition
     基于概率模型的特征补偿算法在语音识别中的应用
短句来源
     Feature Compensation Method Based on Probability Model and Spectrum Difference
     基于概率模型和倒谱差分的特征补偿算法
短句来源
     A Feature Compensation Method Based Probability Model
     一种基于概率模型的特征补偿算法
短句来源
     In this paper, we evaluate the performance of MFCC,RASTA-PLP,PAC and MVDR four speech features for ASR in noisy environment. Their results are compared with those of speech enhancement and Probability Model-based feature compensation.
     比较了MFCC、RASTA-PLP、MVDR和PAC四种特征参数的性能,并和语音降噪方法及基于概率模型的特征补偿算法在噪声环境下的语音识别结果进行了对比。
     A common technique for robust speech recognition is feature compensation.
     特征补偿是一种常用的鲁棒性识别技术。
短句来源
更多       
  “feature compensation”译为未确定词的双语例句
     Robust Speaker Identification Based on Weighted Feature Compensation
     基于加权特征值补偿的说话人识别
短句来源
     A weighted feature compensation method for noisy speaker recognition is proposed, which aims at removing the additional term introduced by noise in the feature domain.
     本论文提出一种加权特征值补偿算法,把由噪声引起的使带噪语音信号特征值与纯净语音特征值发生偏差的部分去除,从而使进入识别器的特征值接近纯净语音的特征值。
短句来源
     The paper introduces a new feature compensation method which will induct the relativity of the prediction of spectrum based probability model in detail.
     在概率模型中,给出了引入倒谱预测值的动态相关性来进行特征补偿的方法。
短句来源
  相似匹配句对
     Compensation
     补偿
短句来源
     Feature:
     本文特色:
短句来源
     Motion Estimation and Compensation Based on Feature Points
     基于图像特征点的运动估计和补偿
短句来源
     A Feature Compensation Method Based Probability Model
     一种基于概率模型的特征补偿算法
短句来源
     On the Administrative Compensation
     论行政补偿
短句来源
查询“feature compensation”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。
  feature compensation
Utterance SNR estimation The SNRs employed in the feature compensation algorithm are signal-to-noise ratio of the whole utterance.
      
The smaller the distances, the more accurate the feature compensation algorithm is.
      
The combination of feature compensation and weighted Viterbi Decoding algorithms can achieve further improvements of about 7%.
      
On average, the feature compensation algorithms obtains 35% word error reduction compared with the baseline and 15% over MLLR algorithm.
      
In Sections 2 and 3, formulations of feature compensation based on SNR polynomial regression and weighted Viterbi decoding are provided, respectively.
      
更多          


The background noise leads a mismatch between the training environment and testing environment, and degrades the performance of speaker identification system. A weighted feature compensation method for noisy speaker recognition is proposed, which aims at removing the additional term introduced by noise in the feature domain. The SNR of noisy speech is used to weight the feature in the compensation. The experiment results indicate that the proposed method can significantly improve the...

The background noise leads a mismatch between the training environment and testing environment, and degrades the performance of speaker identification system. A weighted feature compensation method for noisy speaker recognition is proposed, which aims at removing the additional term introduced by noise in the feature domain. The SNR of noisy speech is used to weight the feature in the compensation. The experiment results indicate that the proposed method can significantly improve the speaker identification accuracy.

背景噪声的存在,使得说话人识别系统的训练环境和测试环境发生失配,导致系统性能发生急剧下降。本论文提出一种加权特征值补偿算法,把由噪声引起的使带噪语音信号特征值与纯净语音特征值发生偏差的部分去除,从而使进入识别器的特征值接近纯净语音的特征值。在特征值补偿过程中引入了信噪比加权的方法。实验表明,这种方法能够有效的提高说话人识别系统的性能。

The article introduces a new feature compensation method which based p robability model in detail. The Minimum Mean Squared Error (MMSE) estimator for the speech feature parameters in spectrum-domain based the prior probability dis tribution is to enhance the correctness of speech recognition. The algorithm is tested in different noise and Signal Noise Ratio (SNR). Subjective measure testi fies that this method can increase the correctness of continuous speech recognit ion.

本文提出了一种基于概率模型的特征补偿算法。该方法基于语音和噪声的先验概率密度,在倒谱域对语音特征参数进行最小均方误差预测(MMSE),提高识别精度。实验结果表明,本文方法能有效提高噪声环境下的中文连续语音识别的正确率。

The paper introduces a new feature compensation method which will induct the relativity of the prediction of spectrum based probability model in detail. The method evaluates the parameters of the joint distribution using the expectation maximization (EM) algorithm. The minimum mean squared error (MMSE) estimator for the speech feature parameters in spectrum-domain based the prior probability distribution is to enhance the correctness of speech recognition. The algorithm is tested in different noise...

The paper introduces a new feature compensation method which will induct the relativity of the prediction of spectrum based probability model in detail. The method evaluates the parameters of the joint distribution using the expectation maximization (EM) algorithm. The minimum mean squared error (MMSE) estimator for the speech feature parameters in spectrum-domain based the prior probability distribution is to enhance the correctness of speech recognition. The algorithm is tested in different noise and signal noise ratio (SNR). Subjective measure testifies that this method can increase the correctness of continuous speech recognition.

在概率模型中,给出了引入倒谱预测值的动态相关性来进行特征补偿的方法。该方法采用期望最大化(EM)算法来估计联合分布参数,基于语音和噪声的先验概率密度,在倒谱域中对语音特征参数进行最小均方误差预测(MMSE),以提高语音识别精度。不同噪声环境和不同信噪比下的实验结果表明,该方法能有效地提高噪声环境下的中文连续语音识别的正确率。

 
<< 更多相关文摘    
图标索引 相关查询

 


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