Description: 语音识别源代码，可以基于它实实现声音控制装置。
-Speech recognition source code, can be based on a real implementation of sound control device. Platform: |
Size: 3414016 |
Author:mx |
Hits:
Description: 针对语音识别中语音数据库 设计，在音节 音素 声韵母等单元建模之前，需要考虑某些音节或音素或声韵母出现的频率，该程序可以很方便统计某些音节或音素或声韵母出现的频率，也可以在此基础上修改下代码，实现某些音节或音素出现在某个位置的频率，有利于语音识别 语音合成的数据工作。-Database designed for speech recognition in voice, syllables and phonemes sound vowels unit modeling before, need to consider the frequency of certain syllables or phonemes or sound vowels, the program can be very convenient statistical frequency of certain syllables or phonemes or sound vowels On this basis, can also modify the next code, some syllables or phonemes appear in the frequency of a location, is conducive to the speech recognition speech synthesis data. Platform: |
Size: 1287168 |
Author:bill |
Hits:
Description: 在语音识别和语音合成的数据准备阶段，针对音节的 声韵母拆分，写了一套自动拆分音节，输入一个拼音文件，可以输出一个声韵母文件。每一音节都被拆分为对应的声韵母。-Data preparation phase in speech recognition and speech synthesis for a split syllable initials and finals, wrote an automatic split syllables, enter a phonetic file, you can output a sound finals file. Each syllable are split into corresponding sound vowels. Platform: |
Size: 1441792 |
Author:bill |
Hits:
Description: 一款基于鸟叫声识别的通用鸟类识别软件LilyBirdSongIdentification 1.0。 鸟类或者其他野生动物对于我们的环境进而我们的生活有着非常大的影响。在很多情况下，对于其种类的识别我们可以通过它们发出的声音来分辨。它们所发出的声音在许多方面对我们的文化也有重要的影响。在很多时候鸟鸣是许多作曲家，音乐家和作家一个重要的灵感来源。我们也时常可以在城市听到甚至它们的叫声，大多数人都能够通过叫声分辨识别较常见的品种。 本软件能够通过自动识别鸟的叫声来识别鸟的种类。当然它也可以用于其他物种的识别：如基于野生动物发出的叫声识别其类型等。同时这款软件也可以略作修改识别说话人（话者识别、说话人识别、声纹识别）等，但仅限为有限集（2，000人以内）的说话人识别。这样一款软件有着非常广泛的应用前景：（1）它能够帮助鸟类或者野生动物观察者、物种学者进一步确定动物的信息；（2）它能够在无人区或者深山区通过传感器自动监测鸟类或者其他野生动物的种类数目以及迁移情况；（3）它可对机场附近的鸟类或者野生动物确定类型从而进行不同手段的驱散，进而确保机场安全；（4）同时这款软件如果做说话人识别，可以用做门禁等方便。-A bird identification software based on the birdcall identify generic LilyBirdSongIdentification 1.0. Birds or other wildlife for our environment and thus has a very big impact on our lives. In many cases, for the identification of a type we can by their sounds to distinguish. The sound in many ways also have an important impact on our culture. The birds often is an important source of inspiration for many composers, musicians and writers. We also often hear their voices even in the city, most people are able to identify the more common varieties distinguished by barking. This software is able to automatically identify bird sounds to identify the types of birds. Of course, it can also be used for the identification of other species: cries emitted by wild animals to identify its type. This software can be slightly modified to identify the speaker (speaker recognition, speaker recognition, voiceprint identification), but only for a limited set (2,000 or less) speaker recognition. Such a Platform: |
Size: 10962944 |
Author:Shi |
Hits:
Description: 声音识别源代码，这是实验室在做项目时用到的一部分源代码，用来进行声音控制的。-Voice recognition source code, which is part of the source code used by the laboratory doing the project, used for sound control. Platform: |
Size: 11720704 |
Author:李卫东 |
Hits:
Description: 从麦克风获取声音，调用微软的语音识别功能，然后实现录音。-Get sound from a microphone, calling Microsoft' s voice recognition feature, and then realized the sound recording. Platform: |
Size: 717824 |
Author:赵敏 |
Hits:
Description: 这个是语音识别的例子上面展示的是声音的方向，下面是语音识别的结果，有Red，Green，Blue三个单词，当站在Kinect前面说某个单词时，如果识别正确，横线会显示相应的颜色。试了一下，还是挺灵敏的-This is a voice recognition example shown above, the direction of the sound, the following is the speech recognition result, Red, Green, Blue three words, when standing in front of Kinect say a word, if the identification is correct, dashes will be displayed corresponding color. Tried it, or very sensitive Platform: |
Size: 99328 |
Author:丁蕾 |
Hits:
Description: 实现功能
1) 在用户界面设置录音时长并实时录音
2) 调节放音幅度、播放原声并进行时域、频域绘图
3) 对收集的声音进行倒放处理并播放
4) 对收集声音进行回声处理并播放，比对时域波形
5) 对收集声音进行回响处理并播放，比对时域波形
6) 对经过回声处理的声音进行回音消除并比对时域波形
7) 采用自适应滤波器消除采集声音中的环境噪音
8) 设计相应的滤波器组成均衡器对收集的声音进行处理并播放
9) 男女声识别
10) 设计参数可调的滤波器对采集的声音进行处理
-1) in the user interface to set the recording length and real-time recording
2) to adjust sound, played acoustic amplitude and time domain, frequency domain mapping
3) to upend the collection of sound and play
4) to collect sound echo processing and playback, than in the time domain waveform
5) to collect sound echoes, processing and playback, than in the time domain waveform
6) to echo and treated with echo s voice than in the time domain waveform
7) using adaptive filter to eliminate ambient noise in acquisition voice
8) to design the corresponding filter to process the voice of equalizer to collect and display
9) NanNvSheng recognition
10) tunable filter design parameters for voice processing
Platform: |
Size: 22076416 |
Author:Tony |
Hits:
Description: 基于LabVIEW的声音识别程序，通过对声音的分析做到识别声音来源分析与匹配-LabVIEW-based voice recognition program, through the voice analysis done to identify the source of sound analysis and matching Platform: |
Size: 222208 |
Author:邱明 |
Hits:
Description: 基于Android 平台开发的这个英语学习游戏软件，主要实现的功能包括通过对单词认知获得积分的游戏功能、选择不同难度关卡、关卡解锁、游戏背景音乐、游戏音效、提供游戏帮助等功能。-Based on the Android platform developed by the English learning game software, the main features include word recognition score points by game features, choose different difficulty levels, levels unlock game background music, game sound, Games Help other functions. Platform: |
Size: 5579776 |
Author:Alex Feng |
Hits:
Description: This folder gives information about false part recognition and noise removal in ultra sound images Platform: |
Size: 701440 |
Author:padmapriya |
Hits:
Description: 此代码完成歌曲库哼唱识别,并能够将哼唱转化为其它乐器的声音回放-This code complete song library humming recognition, and can be converted into other instruments humming sound playback Platform: |
Size: 3072 |
Author:杨少凡 |
Hits:
Description: 基于自建数据库的音乐识别及检索软件 ；
利用Matlab开发软件, 通过抓取录入歌曲的音高(pitch tracking)绘出声音的频率变化并进行降噪和润滑（smoothing）处理
与数据库中歌曲的频率变化图比对，计算出相似度top10的歌曲并显示。
-Based on self-built of music recognition and retrieval software developed using Matlab software, change the pitch of a song by crawling entry (pitch tracking) plots the frequency of the sound and noise reduction and lubrication (smoothing) processing
Frequency changes in the diagram songs than calculate the similarity top10 songs and displayed. Platform: |
Size: 44032 |
Author:wangyuntuo |
Hits:
Description: 语音识别技术(Auto Speech Recognize，ASR)，是让机器能够“听懂”人类的语言，然后将语音转化成文字。此处分享的云知声语音识别sdk，下载后可以直接使用-Voice recognition technology (Auto Speech Recognize, ASR), is to let the machine can understand human language, and then the voice into text. Share cloud here knows the sound of speech recognition sdk, can be used directly after downloading Platform: |
Size: 1608704 |
Author:sheraint |
Hits:
Description: 属于机器学习的范畴，通过输入训练样本，通过分类或线性回归得到标签的假设性函数-The Gesture Recognition Toolkit (GRT) is a cross-platform, open-source, C++ machine learning library that has been specifically designed for real-time gesture recognition.
In addition to a comprehensive C++ API, the GRT now also includes an easy-to-use graphical user interface (GUI) which enables user s to stream real-time data into the GUI via the Open Sound Control network protocol. Using the GUI you can:
(1) Setup and configure a gesture recognition pipeline that can be used for classification, regression, or timeseries analysis.
(2) Stream real-time data into the GUI via Open Sound Control (OSC) another application (such as Processing, Max, Pure Data, Openframeworks, etc.).
(3) Record, label, save and load your training data.
(4) Train a model for classification or regression.
(5) Test the generalization abilities of the model (using another test dataset or cross validation).
(6) Perform real-time prediction on new data streamed into the GUI via OSC.
(7) Stre Platform: |
Size: 21445632 |
Author:王哲 |
Hits:
Description: dsp语音识别程序，居于DSP芯片设计而实现的代码，先录入声音，代码分析提取出其特征存储，之后便可以识别录入的声音-DSP speech recognition program, in the DSP chip design and implementation of the code, the first voice input, code analysis to extract features of storage, then can identify the input sound
DSP speech recognition program, living in the DSP chip design and implementation of the code, the first input sound, code analysis to extract the characteristics of the storage, then you can identify the sound input
DSP speech recognition program, living in the DSP chip design and implementation of the code, the first input sound, code analysis to extract the characteristics of the storage, then you can identify the sound input
Platform: |
Size: 2890752 |
Author:赵 |
Hits:
Description: 源码描述
这是一款比较经典的连连看游戏源码，规则比较简单，将相同的两张牌用三根以内的直线连在一起就可以消除，
全部消除完成即为胜利。整个源码还算完整，所有的图片和音效文件都在Images和Sounds目录下面并且游戏启动
时会有相应的加载动画，并且点击相同的图像以后还会有一个爆炸消除的效果，感兴趣的朋友可以下载试玩下哦。
二、玩法介绍
该源码主要通过鼠标点击图标，在规定的时间内消除所有的图标就可以过关。
三、游戏特点
本源码实现了随机重排和背景以及点击音效。总共有初级、中级和高级三个难度可以设置，
不同的等级主要是背景不同，高级模式下有三层背景能够对玩家图像识别进行干扰。
四、注意事项
1、开发环境为Visual Studio 2010，无数据库，使用.net 2.0开发。
2、该源码比较适合新手学习交流使用。-Source description
This is a more classic game source code, the rules are relatively simple, the same two cards with three or less can be eliminated in a straight line,
Complete elimination of the completion of the victory. The entire source code is complete, all the pictures and sound files are in the Images and Sounds directory and the game starts
There will be a corresponding loading animation, and click on the same image will have a blast to eliminate the effect, interested friends can download the demo.
Two, play the introduction
The source is mainly through the mouse click on the icon, in the specified time to eliminate all the icons can pass.
Three, game features
The source code to achieve a random rearrangement and background and click sound. A total of primary, intermediate and advanced three difficulty can be set,
Different levels are different, and there are three layers of background in advanced mode can interfere with the image recognition.
Four, note
1, the deve Platform: |
Size: 1000448 |
Author:xxpudn96 |
Hits:
Description: 基于分形理论的心音信号特征分析与分类识别研究-Analysis of characteristics of heart sound signals based on fractal theory and classification recognition research
Platform: |
Size: 1024 |
Author:温嘉杰 |
Hits:
Search - sound recognition