Description: 语音识别中的两种特征提取方法lpcc和mfcc，还有一个是文本无关的识别算法dtw，另外还有一个是预处理消噪部分的。共享一下，这些都是我调试过的，好用。-Speech Recognition two feature extraction methods and mfcc lpcc. There is a text-independent recognition algorithm dtw, in addition to a pretreatment is part of the noise source. Sharing that those are off the debugging and ease of use. Platform: |
Size: 1741 |
Author:杨洁 |
Hits:
Description:
语音识别模块的性能指标：
高识别率：在一定的硬件环境下，平均准确率可达97％；
端点检测：在识别过程，具备端点检测功能；
实时识别：具有唤醒功能；
环境噪音：一定范围之内，仍可保证高识别率-speech recognition module performance indicators : high recognition rate : some of the hardware environment, average accuracy rate of up to 97%; Endpoint Detection : the identification process, with endpoint detection; Real-time Recognition : The wake-up function; Environmental noise : within a certain range, can ensure high recognition rate Platform: |
Size: 1625250 |
Author:唐永锋 |
Hits:
Description: 语音端点检测是语音识别中至关重要的技术。无论军用还是民用，语音端点检测都有着广泛的应用。在低信噪比的环境中进行精确的端点检测比较困难，尤其是在无声段或者发音前后-voice activity detection is critical speech recognition technologies. Whether military or civilian, voice endpoint detection have broad application. Low signal-to-noise ratio in the environment for accurate endpoint detection more difficult, especially in or pronunciation of the silent before and after Platform: |
Size: 531719 |
Author:李一 |
Hits:
Description: ETSI发布的用于研究分布式语音识别的前端降噪代码-ETSI issued for the study of Distributed Speech Recognition front Noise Code Platform: |
Size: 1170824 |
Author:杜俊 |
Hits:
Description: ETSI发布的用于研究分布式语音识别的前端降噪算法-ETSI issued for the study of Distributed Speech Recognition front Noise Reduction Algorithm Platform: |
Size: 1496520 |
Author:杜俊 |
Hits:
Description: ETSI发布的用于研究分布式语音识别的前端降噪算法-ETSI issued for the study of Distributed Speech Recognition front Noise Reduction Algorithm Platform: |
Size: 1496555 |
Author:杜俊 |
Hits:
Description: ETSI发布的用于研究分布式语音识别的前端降噪算法-ETSI issued for the study of Distributed Speech Recognition front Noise Reduction Algorithm Platform: |
Size: 1496064 |
Author:杜俊 |
Hits:
Description: ETSI发布的用于研究分布式语音识别的前端降噪算法-ETSI issued for the study of Distributed Speech Recognition front Noise Reduction Algorithm Platform: |
Size: 1496064 |
Author:杜俊 |
Hits:
Description: 语音识别中的两种特征提取方法lpcc和mfcc，还有一个是文本无关的识别算法dtw，另外还有一个是预处理消噪部分的。共享一下，这些都是我调试过的，好用。-Speech Recognition two feature extraction methods and mfcc lpcc. There is a text-independent recognition algorithm dtw, in addition to a pretreatment is part of the noise source. Sharing that those are off the debugging and ease of use. Platform: |
Size: 1024 |
Author:杨洁 |
Hits:
Description:
语音识别模块的性能指标：
高识别率：在一定的硬件环境下，平均准确率可达97％；
端点检测：在识别过程，具备端点检测功能；
实时识别：具有唤醒功能；
环境噪音：一定范围之内，仍可保证高识别率-speech recognition module performance indicators : high recognition rate : some of the hardware environment, average accuracy rate of up to 97%; Endpoint Detection : the identification process, with endpoint detection; Real-time Recognition : The wake-up function; Environmental noise : within a certain range, can ensure high recognition rate Platform: |
Size: 1934336 |
Author:唐永锋 |
Hits:
Description: 语音端点检测是语音识别中至关重要的技术。无论军用还是民用，语音端点检测都有着广泛的应用。在低信噪比的环境中进行精确的端点检测比较困难，尤其是在无声段或者发音前后-voice activity detection is critical speech recognition technologies. Whether military or civilian, voice endpoint detection have broad application. Low signal-to-noise ratio in the environment for accurate endpoint detection more difficult, especially in or pronunciation of the silent before and after Platform: |
Size: 531456 |
Author:李一 |
Hits:
Description: LMS滤波器示例程序，在TURBOC中运行
这是一个简单的可图形显示的C程序
输入信号是一个被噪声污染了的sin信号。 */
/* 运行后，屏幕的上方是输入信号，下方是经过LMS滤波后的输出信号
-LMS filter sample programs, run in TurboC This is a simple graphical display can process the C input signal is a noise contaminated signal sin.*//* Running, the top of the screen is the input signal, the bottom is the result after the LMS filter output signal Platform: |
Size: 4096 |
Author:蜗牛 |
Hits:
Description: 波形和频谱双显示
记录讲话直接进入MATLAB
手动分割讲话波形-创建标签文件
波形编辑-切割，复制或粘贴
共振峰分析-显示共振轨道的F1 ， F2和F3
基音分析
过滤工具-语音信号滤波器截止频率
比较工具-比较两个波形的频谱距离使用几种措施
增加噪声-Dual time-waveform and spectrogram displays
Records speech directly into MATLAB NEW
Displays time-aligned phonetic transcriptions [e.g., TIMIT s .phn files]- see example Figure above
Manual segmentation of speech waveforms- creates label files which can be used to train speech recognition systems
Waveform editing- cutting, copying or pasting speech segments
Formant analysis- displays formant tracks of F1, F2 and F3
Pitch analysis
Filter tool- filters speech signal at cutoff frequencies specified by the user
Comparison tool- compares two waveforms using several spectral distance measures
Speech degradation- adds noise to the speech signal at an SNR specified by the us Platform: |
Size: 1180672 |
Author:wsw |
Hits:
Description: 噪声环境下的说话人识别技术研究，论文。供研究语音识别的人员参考，学习。-Noise environments Speaker Recognition Technology, Thesis. Research on speech recognition for staff members to learn. Platform: |
Size: 11094016 |
Author:hyguo |
Hits:
Description: duction techniques proposed in the art are expressed as a spectral
gain depending on the a priori SNR. In the well-known decision-
directed approach, the a priori SNR depends on the speech spec-
trum estimation in the previous frame. As a consequence the gain
function matches the previous frame rather than the current one
which degrades the noise reduction performance. We propose a
new method called Two-Step Noise Reduction (TSNR) technique
which solves this problem while maintaining the benefi ts of the
decision-directed approach. This method is analyzed and results
in voice communication and speech recognition context are given.-noise estimate Platform: |
Size: 194560 |
Author:leon |
Hits:
Description: 基于抗噪语音识别的计算机声控系统的实现，将抗噪语音识系统运行于windows上实现windows操作系统的一些简单命令-Anti-noise speech recognition based on voice-activated computer system implementation, the anti-noise voice-identification system is running on windows operating system windows to achieve a few simple commands Platform: |
Size: 738304 |
Author: |
Hits:
Description: 论文首先介绍了传统的语音特征参数MFCC，它是基于人耳听觉
特性设计的一种特征参数，在静音环境下能得到较高的识别率，但在
信噪比较低时识别率急剧下降，不利于实用化。本文通过对MFCC算
法的分析和研究，发现其中的FFT和DCT在整个时频空间使用固定的
。分析窗，这不符合语音信号特性，而小波变换具有多分辨率特性，更
符合人耳的听觉特性。因此，本文将小波变换和MFCC算法相结合，
提出了三种新的语音识别特-Speech recognition has wide use in the field of communication and so
on·Speech feature parameter extraction is an important part of the speech
recognition system．The performance of the feature parameter haftuences
the system’S performance directly．And the environmental noise is a kev
factor of restricting the performance of the feature parameter．This paper，s
research object is extracting the speech feature parameter under the noise
environment·Then it analyzes the auditory model of human，deeply
analyzes and researches the traditional speech feature parameter MFCC，
and proposes three improved MFCC parameters based on theⅥ，avelet
transformation and the auditory characteristic ofhuman．Besides，the paper
also gives all improved method about the feature parameter ZCPA． Platform: |
Size: 2001920 |
Author:周卓然 |
Hits:
Description: 介绍Laguerre滤波器在抗噪语音识别特征提取中的应用，很详细-Introduced the application of the Laguerre filter in Noisy Speech Recognition feature extraction, in detail Platform: |
Size: 266240 |
Author:cooldog |
Hits:
Description: A robust speech recognit ion system based on discriminative learning of environmental features is
proposed for recognit ion of environmental features in high noise background, and a g radient descent algo
rithm was adopted for parameters opt imization. Ex periments w ere carried out at different levels of back
g round noise for SNR, basic accuracy, noise- resistance and system environment adaptability. T he experi
mental result s show that the system has good recog nition performance in high noisy environments. The sys
tem can meet different needs of applicat ion. Platform: |
Size: 167936 |
Author:yanyeguo |
Hits:
Search - speech recognition noise