feature of speech
英
美
[网络] 演讲特点
双语例句
- Objective To compare between two methods of speech input, with the aim of providing a reference for further research of phonetic feature of Chinese pathological speech.
目的比较不同语音输入法的异同，为进一步认识汉语病理性语言的音声特征提供参考。 - And then introduces the functions and key technologies of pre-processing 、 feature extraction pattern matching and post-processing of speech recognition. Improved methods have been proposed in view of problems existed in traditional methods.
然后分别介绍了语音识别的预处理、特征参数提取、模式匹配和后处理阶段的功能及其关键技术，并针对传统方法中存在的问题提出了改进方案。 - During simulation experiment, wavelet analysis technique is adopted to extract feature vectors of speech, the results show that SVM and FSVM have both higher correct recognition rate and shorter training time than RBF network.
在仿真实验中，采用小波分析方法提取语音特征向量，识别结果表明，SVM和FSVM比RBF网络具有较好的泛化性能，训练时间也大大缩减。 - This paper uses wavelet theory in noise-robust feature extraction of speech recognition and introduces a feature extraction method based on Gauss wavelet filter. The Gauss wavelet filter with human critical frequency band is obtained by studying human auditory characteristics.
把小波理论应用于抗噪语音识别特征提取，提出了基于高斯小波滤波器的语音识别特征提取方法，通过对人耳听觉特性的研究，按照人耳临界带宽设计了一组高斯小波带通滤波器。 - Then the influence of the weighting of feature vectors, the time duration of speech segments and the various choose of factor α on the performance of a small open-set text-independent speaker identification system is researched by experiments.
在小规模说话人辨认系统的实验研究中，研究了特征矢量的加权、语音段的时长以及α因子的选择对系统性能的影响。 - The problem of syntactic feature of speech is one of the important contents in syntactic study.
词类的句法特征问题是句法研究中的重要内容之一。 - In technology, speech features reflecting the physical and action feature of individuals arc distilled from speech and the identity of the speaker is automatically recognized according to these speech parameters.
从技术上主要是从说话人语音信息中提取反映说话人的生理和行为特征的语音参数，并根据这些语音参数自动识别说话人的身份。 - Searl considers the intentionality as the primary feature of speech act, holding that the illustration of language meaning is inseparable from intentionality.
塞尔认为意向性是言语行为的基本特征，要想阐释语言的意义，必须研究意向性。 - For the length of feature vectors of speech samples is different, direct cutting and Dynamic Time Warping ( DTW) regulation, are put forward to solve the problem.
提出了直接截取和DTW规正两种方法来解决语音样本特征向量长度不一致的问题。 - According to the simulated results, the power spectrum of ARMA model is more accurate than that of AR model, which is more suitable to reflect the feature of speech signal. ( 4) ARMA model is used in CELP.
由仿真可知，ARMA模型比AR模型的功率谱更加准确，更适合描述语音信号的特性。（4）将ARMA应用到CELP算法中。