Location:
Search - speech segment
Search list
Description: 語音識別音框分割,c++ source code-Speech Recognition sound box partition, c++ Source code
Platform: |
Size: 20480 |
Author: 張政偉 |
Hits:
Description: calculates the active level of a speech segment according to ITU-T recommendation P.56.
Platform: |
Size: 3072 |
Author: qingpg518 |
Hits:
Description: 在语音识别系统中，端点检测的目的是要区分语音段和非语音段 ,它在自动语音识别中起着关键作用-In speech recognition systems, the purpose of endpoint detection is to distinguish between voice and non-voice segment, which in automatic speech recognition plays a key role
Platform: |
Size: 1024 |
Author: 小英 |
Hits:
Description: gaze tracking system in matlab-used to move a wheelchair for physically challenged people
Platform: |
Size: 760832 |
Author: pkp |
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: This project describes the work done on the development of an audio segmentation and classification system. Many existing works on audio classification deal with the problem of classifying known homogeneous audio segments. In this work, audio recordings are divided into acoustically similar regions and classified into basic audio types such as speech, music or silence. Audio features used in this project include Mel Frequency Cepstral Coefficients (MFCC), Zero Crossing Rate and Short Term Energy (STE). These features were extracted from audio files that were stored in a WAV format. Possible use of features, which are extracted directly from MPEG audio files, is also considered. Statistical based methods are used to segment and classify audio signals using these features. The classification methods used include the General Mixture Model (GMM) and the k- Nearest Neighbour (k-NN) algorithms. It is shown that the system implemented achieves an accuracy rate of more than 95 for discrete audio classification.-This project describes the work done on the development of an audio segmentation and classification system. Many existing works on audio classification deal with the problem of classifying known homogeneous audio segments. In this work, audio recordings are divided into acoustically similar regions and classified into basic audio types such as speech, music or silence. Audio features used in this project include Mel Frequency Cepstral Coefficients (MFCC), Zero Crossing Rate and Short Term Energy (STE). These features were extracted from audio files that were stored in a WAV format. Possible use of features, which are extracted directly from MPEG audio files, is also considered. Statistical based methods are used to segment and classify audio signals using these features. The classification methods used include the General Mixture Model (GMM) and the k- Nearest Neighbour (k-NN) algorithms. It is shown that the system implemented achieves an accuracy rate of more than 95 for discrete audio classification.
Platform: |
Size: 653312 |
Author: kvga |
Hits:
Description: 用于提取一段语音中单独的每个字词，matlab下编写，经检测很好用。注意不是检测一段语音中的一个字词，而是所有的。-to detect every word in a speech segment. made in matlab. mind you , it s meant to detect every word, not only the first word
Platform: |
Size: 3072 |
Author: 沈雨祥 |
Hits:
Description: 根据国际电信联盟标准P.56对语音信号的作用电平进行计算。-calculates the active level of a speech segment according to ITU-T recommendation P.56
Platform: |
Size: 5120 |
Author: xiaohang |
Hits:
Description: filter for denoising noisy speech (corrupted by white noise). Kalman
filtering of noisy speech usually have two steps:
Estimating the AR parameters of speech segment
Platform: |
Size: 13312 |
Author: omkumar |
Hits:
Description: 语音分段检测算法，用于语音增强的分段算法。-Speech segment detection algorithm, the segmentation algorithm for speech enhancement.
Platform: |
Size: 322560 |
Author: jzhou |
Hits:
Description: 语音特征信号识别是语音识别研究领域中的一个重要方面,一般采用模式匹配的原理解
决。语音识别的运算过程为:首先,待识别语音转化为电信号后输入识别系统,经过预处理后用数学方法提取语音特征信号,提取出的语音特征信号可以看成该段语音的模式。然后将该段语音模型同已知参考模式相比较,获得最佳匹配的参考模式为该段语音的识别结果.-Speech characteristic signal recognition is an important aspect in the field of speech recognition research, generally USES pattern matching the original understanding
Definitely. Operation process of speech recognition are as follows: first, after waiting for voice recognition into electrical signal input and recognition system, after pretreatment
Mathematical method was used to extract speech signal, and extracts the phonetic characteristics of signals can be as the segment of speech patterns. And then the
Audio model compared to a known reference model, get the best match the reference pattern for this speech recognition results.
Platform: |
Size: 375808 |
Author: 吴军 |
Hits:
Description: 语音特征信号识别是语音识别研究领域中的一个重要方面,一般采用模式匹配的原理解
决。语音识别的运算过程为:首先,待识别语音转化为电信号后输入识别系统,经过预处理后用数学方法提取语音特征信号,提取出的语音特征信号可以看成该段语音的模式。然后将该段语音模型同已知参考模式相比较,获得最佳匹配的参考模式为该段语音的识别结果-Recognition is the speech characteristic signal in the field of speech recognition is an important aspect, the general principle of pattern matching solution. Voice recognition operation process as follows: First, to be converted to electrical signals identifying the input speech recognition system, after pretreatment using mathematical methods to extract the speech characteristic signal, the speech characteristic signal extracted can be seen that the pattern of voice. Then the paragraph speech model with a known reference pattern compared to the best matching reference pattern of speech recognition results for the segment
Platform: |
Size: 489472 |
Author: 吴军 |
Hits:
Description: top the acquisition and displays the recognized digit. Beside the length of speech segment it is possible to change also the sampling frequency.
Platform: |
Size: 4096 |
Author: Alich |
Hits:
Description: On the companion website, you will find in the directory Chap exercises/chapter3 a
workspace ex3M1.mat. Load this workspace and plot the speech waveform labeled speech1 10k.
This speech segment was taken a vowel sound that is approximately periodic, 25 ms in duration,
and sampled at 10000 samples/s.-On the companion website, you will find in the directory Chap exercises/chapter3 a
workspace ex3M1.mat. Load this workspace and plot the speech waveform labeled speech1 10k.
This speech segment was taken a vowel sound that is approximately periodic, 25 ms in duration,
and sampled at 10000 samples/s.
Platform: |
Size: 1024 |
Author: asdamha |
Hits:
Description: 可以直接用于MATLAB中的.txt语音片段，浊音片段-Can be directly used for.Txt speech segments MATLAB, voiced segment
Platform: |
Size: 5120 |
Author: 李冉 |
Hits:
Description: This paper proposes a new variant of the least square autoregressive (LSAR) method for speech reconstruction, which can estimate
via least squares a segment of missing samples by applying the linear
prediction (LP) model of speech. First, we show that the use of a single
high-order linear predictor can provide better results than the classic
LSAR techniques based on short- and long-term predictors without the
need of a pitch detector. However, this high-order predictor may reduce
the reconstruction performance due to estimation errors, especially in the
case of short pitch periods, and non-stationarity. In order to overcome
these problems, we propose the use of a sparse linear predictor which
resembles the classical speech model, based on short- and long-term correlations, where many LP coefficients are zero. The experimental results
show the superiority of the proposed approach in both signal to noise
ratio and perceptual performance.
Platform: |
Size: 54272 |
Author: pashaa
|
Hits:
Description: The speech signal for the particular isolated word can be viewed as the one generated using the sequential generating probabilistic model known as hidden Markov
model (HMM). Consider there are n states in the HMM. The particular isolated
speech signal is divided into finite number of frames. Every frame of the speech
signal is assumed to be generated from any one of the n states. Each state is modeled as the multivariate Gaussian density function with the specified mean vector
and the covariance matrix. Let the speech segment for the particular isolated word
is represented as vector S. The vector S is divided into finite number of frames
(say M). The i th frame is represented as Si . Every frame is generated by any of the n
states with the specified probability computed using the corresponding multivariate
Gaussian density model.
Platform: |
Size: 787456 |
Author: Khan17
|
Hits:
Description: 根据短时傅里叶变换原理，计算并显示该语音段的短时幅度谱和功率谱；根据语谱图显示原理，编程实现该语音段语谱图的计算和显示，并尽量多地分析出语谱图包含的语音特征信息,用MATLAB提供的倒谱计算函数，显示该语音段的复倒谱和倒谱(According to the principle of short-term Fourier transform, the short range spectrum and power spectrum of the speech segment are calculated and displayed. According to the principle of spectrogram display language, programming implementation period of the speech spectrum diagram calculation and display, and as often as possible language phonetic characteristics of spectra contain information provided by the MATLAB cepstrum calculation function, according to the voice of the complex cepstrum and cepstrum)
Platform: |
Size: 282624 |
Author: 这些成分
|
Hits:
Description: 熵值越大则每个符号包含的平均信息量越大。有研究发现，在有噪声的语音信号中，语音信号的熵和噪声信号的熵存在着较大的差异，对噪声信号来说在整个频带内分布相对平坦，熵值小，语音信号集中在某些特定频段内，熵值大。因此利用这个差异可以区分噪音段和语音段。(The greater the entropy is, the greater the average information of each symbol is. It is found that, in noisy speech signals, the entropy of speech signals and the entropy of noise signals are quite different. For noisy signals, the distribution is relatively flat in the whole frequency band, and the entropy value is small. The speech signal is concentrated in some specific frequency bands, and the entropy value is large. So the difference can be used to distinguish the noise segment and the speech segment.)
Platform: |
Size: 1024 |
Author: p雄 |
Hits:
Description: 语音信号的时域、频域与倒谱域分析。
1.分析一帧清音和浊音的自相关函数和倒谱系数
2.用Matlab画出该段语音的时域波形、短时能量、短时平均幅度、短时过零率、短时过电平率
3.选择一帧无声、清音和浊音的语音，用Matlab画出它们的对数幅度谱(Time domain, frequency domain and cepstrum domain analysis of speech signals.
1. Analyze the autocorrelation function and cepstrum coefficient of unvoiced and voiced sounds
2. Use Matlab to plot the time domain waveform of the speech segment, short-term energy, short-term average amplitude, short-term zero-crossing rate, and short-term overshoot ratio.
3. Select an unvoiced, unvoiced, and voiced sound and use Matlab to plot its logarithmic amplitude spectrum)
Platform: |
Size: 146432 |
Author: jacek |
Hits: