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
   phonetic classification 的翻译结果: 查询用时:0.007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
 

phonetic classification
相关语句
  “phonetic classification”译为未确定词的双语例句
     A voice activity detection algorithm based on phonetic classification
     一种基于声学分类的语音激活检测算法
短句来源
     729B. This algorithm classifies the speech signal into noise,voiced and unvoiced sounds by using the phonetic classification. The simulation result proves its validity and robustness.
     该算法结合了声学分类 ,对噪声、清音和浊音加以区分 ,最后给出了仿真结果 ,证明其稳健性和有效性
短句来源
     Experimental results show that phonetic classification based on the triphone can greatly improve system performance. The proposed method reduces the error rate by 28% compared with a baseline system. 
     实验表明:基于语音学分类的三音子单元对识别性能有明显的改善,系统的首选误识率相对基线系统降低了28%。
短句来源
  相似匹配句对
     On Classification of
     ω_(2,2g/(3+2))~2的分类
短句来源
     ·classification.
     ①对地震层析成像方法进行分类.
短句来源
     A Study on Phonetic Transcription Classification of The Annotation of Classics
     《经典释文》音切类目研究的基本结论
短句来源
     Classification of Mandarin Consonants based on Acoustic-phonetic Knowledges
     一种基于语音学知识的汉语辅音分类方法
短句来源
     On the Phonetic Mode
     语音模式试说
短句来源
查询“phonetic classification”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。
  phonetic classification
In addition, we report improved audio-visual phonetic classification over the use of a single-stage image transform visual front end.
      
The phonetic classification was performed on the phone set listed in Table 1.
      
High-performance phonetic classification algorithms are developed based on discrete-time Wavelet decomposition and the Teager energy operator.
      
Finally, our wavelet based feature extraction system is described and its performance on a simple phonetic classification problem given.
      
Another phonetic classification, based on both acoustic and articulatory features is more natural than broad phonetic classes.
      


Based on an analysis of the characteristics of Mandarin digits,the zero-crossing rate,energy,pitch and the first two formant frequencies are chosen as the features in the speakerindependent,isolated Mandarin digit recognition system. The recognition accuracy of about96.6%is achieved in the experiments,The system is different from most similar ones inthat it recognizes Mandarin digits by a decision tree rather than the pattern matchingmethod.The decision tree first classifies the Mandarin digits into two types,the...

Based on an analysis of the characteristics of Mandarin digits,the zero-crossing rate,energy,pitch and the first two formant frequencies are chosen as the features in the speakerindependent,isolated Mandarin digit recognition system. The recognition accuracy of about96.6%is achieved in the experiments,The system is different from most similar ones inthat it recognizes Mandarin digits by a decision tree rather than the pattern matchingmethod.The decision tree first classifies the Mandarin digits into two types,the voiced consonant type (0,1,2,5,6, 8) and the unvoiced one(3,4,7, 9)and then it gives the recognition result by the first two formant frequencies and the pitches. It is shown in the experi-ments that the decision tree method derived from the phonetic classification is very effectivefor the recognition of Mandarin digits.

通过分析汉语语音及非特定人语音特点,选择过零率、能量、基音周期和前两个共振峰作为语音特征,用音素分类的方法构造判决树,在此基础上,给出了一个非特定人普通话孤立数字音(0~9)识别系统,识别率大约为96.6%。

Variable-rate speech coding, a new speech coding method, is dealt with in this paper.Voice activity detection (VAD) is a key part in variable-rate speech coding and it can affect the quality of synthesis speech signal.This paper proposes a VAD algorithm for triple-rate speech coding based on ITU-T standard G.729B. This algorithm classifies the speech signal into noise,voiced and unvoiced sounds by using the phonetic classification. The simulation result proves its validity and robustness.

文章涉及了语音编码中最新的一种编码方式——变速率语音编码。语音激活检测 (VAD)算法是其中的关键部分 ,直接影响语音质量和试听效果。文章通过分析国际电信联盟的 G.72 9B标准 ,提出了一种适用于三速率语音编码方式的VA D算法。该算法结合了声学分类 ,对噪声、清音和浊音加以区分 ,最后给出了仿真结果 ,证明其稳健性和有效性

This paper proposes a new technique to construct triphones for Mandarin to improve the performance of automatic speech recognition systems. The technique is based on the monosyllabic characteristic structure of Mandarin. As opposed to traditional parametersharing techniques, which are based on datadriven clustering, this method is purely based on phonetics. Phonetics is applied to classify various contexts between syllables to realize parametersharing between different triphone units. A training algorithm...

This paper proposes a new technique to construct triphones for Mandarin to improve the performance of automatic speech recognition systems. The technique is based on the monosyllabic characteristic structure of Mandarin. As opposed to traditional parametersharing techniques, which are based on datadriven clustering, this method is purely based on phonetics. Phonetics is applied to classify various contexts between syllables to realize parametersharing between different triphone units. A training algorithm is presented with a search network for recognition. Experimental results show that phonetic classification based on the triphone can greatly improve system performance. The proposed method reduces the error rate by 28% compared with a baseline system.

为提高语音识别系统的性能,针对汉语语音的单音节结构的特点,提出了建立三音子识别单元的方法。这种方法完全利用语音学知识对上下文进行分类从而实现参数共享,而不同于传统的数据驱动的聚类共享。提出并实现了采用三音子单元的识别系统的训练算法和识别搜索算法。实验表明:基于语音学分类的三音子单元对识别性能有明显的改善,系统的首选误识率相对基线系统降低了28%。

 
<< 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phonetic classification的内容
在知识搜索中查有关phonetic classification的内容
在数字搜索中查有关phonetic classification的内容
在概念知识元中查有关phonetic classification的内容
在学术趋势中查有关phonetic classification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