Location:
Search - speech features
Search list
Description: An Evaluation of Visual Speech Features for the Tasks of Speech and Speaker Recognition.-An Evaluation of Visual Speech Features az r Tasks of the Speech and Speaker Recognition.
Platform: |
Size: 102080 |
Author: rw |
Hits:
Description: 计算所汉语词法分析系统ICTCLAS.分词正确率高达97.58%(973专家组评测)，未登录词识别召回率均高于90%，其中中国人名的识别召回率接近98%处理速度为31.5Kbytes/s。ICTCLAS的特色还在于：可以根据需要输出多个高概率结果，有多种输出格式，支持北大词性标注集，973专家组给出的词性标注集合。-Calculate the Chinese Lexical Analysis System ICTCLAS. Segmentation correct rate of 97.58 percent (973 Expert Group on Evaluation), the recall rate of identification of unknown words were higher than 90 percent, of which China s name to identify the recall rate of nearly 98 percent processing speed for 31.5Kbytes/s. Also features ICTCLAS is: can output a number of high probability that there are a variety of output formats, to support the North-of-speech tagging sets, 973 expert group is given a collection of-speech tagging.
Platform: |
Size: 3140608 |
Author: 站长 |
Hits:
Description: 语音识别（Speech Recognition）是让机器通过识别和理解过程把语音信号转变为相应的文本或命令的技术。在课题中，通过采用DTW（Dynamic time warping, 动态时间伸缩）算法，对实现孤立词的识别进行了初步探讨和研究，实现了在MATLAB软件环境下孤立词语的语音识别，并针对DTW的主要特点及不足做出了总结。-Speech Recognition (Speech Recognition) machines is through recognition and understanding of a process which put the voice signal into the corresponding text or command technology. The issue, through the use DTW (Dynamic time warping, dynamic time telescopic) algorithm to achieve an isolated word recognition conducted a preliminary exploration and study, the realization of the MATLAB software environment isolated words of Speech Recognition and DTW against the main features and deficiencies make summarized.
Platform: |
Size: 116736 |
Author: 序号 |
Hits:
Description: 本程序是基于模板匹配的语音识别技术。提取语音的特征，并建立模板库。可以将语音识别技术应用于机器人。-this program is based on template matching speech recognition technology. Extraction of voice features, and the establishment of Template Library. Voice recognition can be used in robot technology.
Platform: |
Size: 84992 |
Author: |
Hits:
Description: An Evaluation of Visual Speech Features for the Tasks of Speech and Speaker Recognition.-An Evaluation of Visual Speech Features az r Tasks of the Speech and Speaker Recognition.
Platform: |
Size: 101376 |
Author: rw |
Hits:
Description: matlab 源码,基于小波变换的语音信息隐藏的实现,对原始语音信息和水印信息都经过三层小波分解处理后,将水印信息的低频信号嵌入原始语音信号的部分高频信号部分实现隐藏.源代码不仅给出隐藏过程,并且给出的在随机噪声,重采样,信息压缩情况下的抗攻击特性.源代码清晰有注释-matlab source code, based on wavelet transform voice messages hidden realize, the original voice information and watermark information after a three-treatment, after wavelet decomposition, the watermark information embedded in the low-frequency signals of the original speech signal realize some hidden part of high-frequency signals. source code is given not only to hide the process, and given in random noise, resampling, compression of information in case of anti-attack features. source code has a clear Notes
Platform: |
Size: 1024 |
Author: 桑圣洁 |
Hits:
Description: 语音识别系统Sphinx的训练模型工具程序，可以通过该训练工具抽取语音特征、训练语言模型等。-Sphinx speech recognition system training process modeling tools, the training tool can extract the speech features, such as language model training.
Platform: |
Size: 8194048 |
Author: 闫永明 |
Hits:
Description: 一个自然语言处理的Java开源工具包。LingPipe目前已有很丰富的功能，包括主题分类（Top Classification）、命名实体识别（Named Entity Recognition）、词性标注（Part-of Speech Tagging）、句题检测（Sentence Detection）、查询拼写检查（Query Spell Checking）、兴趣短语检测（Interseting Phrase Detection）、聚类（Clustering）、字符语言建模（Character Language Modeling）、医学文献下载/解析/索引（MEDLINE Download, Parsing and Indexing）、数据库文本挖掘（Database Text Mining）、中文分词（Chinese Word Segmentation）、情感分析（Sentiment Analysis）、语言辨别（Language Identification）等API。-A natural language processing of the Java open-source toolkit. LingPipe currently have a lot of useful features, including Subject Classification (Top Classification), Named Entity Recognition (Named Entity Recognition), part of speech tagging (Part-of Speech Tagging), sentence detection problem (Sentence Detection), spell-checking query (Query Spell Checking), interest in the phrase detection (Interseting Phrase Detection), Cluster (Clustering), Character Modeling Language (Character Language Modeling), medical literature to download/analysis/index (MEDLINE Download, Parsing and Indexing), text mining database (Database Text Mining), Chinese word segmentation (Chinese Word Segmentation), emotional analysis (Sentiment Analysis), language identification (Language Identification), such as API.
Platform: |
Size: 4669440 |
Author: 张国栋 |
Hits:
Description: The philosophy of the book is to present various pattern recognition tasks in
a unified way, including image analysis, speech processing, and communication applications. Despite their differences, these areas do share common features and their study can only benefit from a unified approach.-The philosophy of the book is to present various pattern recognition tasks in
a unified way, including image analysis, speech processing, and communication applications. Despite their differences, these areas do share common features and their study can only benefit from a unified approach.
Platform: |
Size: 10775552 |
Author: Andrey |
Hits:
Description: 基于Mel倒谱特征和RBF网络的孤立词语音识别方法-Mel-based cepstral features and RBF networks isolated word speech recognition method
Platform: |
Size: 239616 |
Author: yuanjiaxing |
Hits:
Description: Template based Speech Recognition using spectral features and DTW, very clear code in MATLAB
Platform: |
Size: 9216 |
Author: Cutie Babe |
Hits:
Description: 关于语音处理的英文书籍，其中特征提取部分（MFCC）讲解的很好很详细-The performance of speech recognition systems receiving speech that has been transmitted over mobile channels can be
significantly degraded when compared to using an unmodified signal. The degradations are as a result of both the low
bit rate speech coding and channel transmission errors. A Distributed Speech Recognition (DSR) system overcomes
these problems by eliminating the speech channel and instead using an error protected data channel to send a
parameterized representation of the speech, which is suitable for recognition. The processing is distributed between the
terminal and the network. The terminal performs the feature parameter extraction, or the front-end of the speech
recognition system. These features are transmitted over a data channel to a remote "back-end" recognizer. The end result
is that the transmission channel does not affect the recognition system performance and channel invariability is achieved.
Platform: |
Size: 101376 |
Author: gqy |
Hits:
Description: 小波变换加VQ语音识别程序。用小波变换来提高语音特征的性能，从而提高VQ算法的识别率-Wavelet transform plus VQ speech recognition program. Using wavelet transform to improve the performance of speech features to enhance the recognition rate of VQ algorithms
Platform: |
Size: 8192 |
Author: 黄邦奉 |
Hits:
Description: BP神经网络 数据分类 语音特征信号分类-BP neural network classification of data signal classification speech features
Platform: |
Size: 375808 |
Author: guanyouyuan |
Hits:
Description: 运用matlab仿真实现语音增强和噪声消除的功能-Matlab simulation using voice enhancement and noise reduction features
Platform: |
Size: 5120 |
Author: ywj7891 |
Hits:
Description: program for gmm distribution calculation of speech features
Platform: |
Size: 2048 |
Author: entekhab |
Hits:
Description: his a simple method for silence removal and segmentation of audio streams that contain speech. The method is based in two simple audio features (signal energy and spectral centroid). As long as the feature sequences are extracted, as thresholding approach is applied on those sequence, in order to detect the speech segment-his is a simple method for silence removal and segmentation of audio streams that contain speech. The method is based in two simple audio features (signal energy and spectral centroid). As long as the feature sequences are extracted, as thresholding approach is applied on those sequence, in order to detect the speech segment
Platform: |
Size: 980992 |
Author: petr |
Hits:
Description: EXTRACTING speech features using LPC
Platform: |
Size: 1024 |
Author: reda |
Hits:
Description: 基于CRF的中文机构名识别系统。使用北京大学1998年的人民日报语料库作为训练语料。除常用的特征模板，已经词性特征外，使用词语的最后一个字作为特征，提高了机构名识别的准确率, 调用了CRF++程序包训练模型。-CRF-based name recognition system of Chinese institutions. People' s Daily, Peking University in 1998 with corpus as training data. In addition to the characteristics of commonly used templates, has been part of speech features, the last word to use words as features and improve the organization name recognition accuracy, call the CRF++ package training model.
Platform: |
Size: 26624 |
Author: paul |
Hits:
Description: 通过凌阳16位单片机实现语音电子钟的功能的程序。-By Sunplus 16-bit MCU clock features the voice of electronic procedures.
Platform: |
Size: 307200 |
Author: 郭晓艺 |
Hits: