Search - 9-1 9-2

Search - 9-1 9-2 - List

[Speech/Voice recognition/combine] telephoneSearch DL : 0: 实现如下的功能：在电话语音识别中需要识别电话号码，这需要识别0到9十个数字，而识别前首先需要训练这十个数字，请编写程序设计一个电话号码表，要求数字组数最少。其中：每一组数字都是八位（例如：62 781 704），0到9十个数字中每两个数字之间至少连接一次（象62781707，其中出现了：6－2、2—7、7－8、8—1、1—7、7—0、0—7七个连接，7－0和0¬ —7是不同的连接），每个数字在开头、结尾至少各出现一次（象62781707其中，6在开头出现一认，7在结尾出现一次）。-achieve the following functions : the telephone speech recognition need to identify the telephone number, This requires identification 0-9 10 figures, and identify training needs first before this 10 figures, please procedures designed to prepare a phone number, requesting at least a group of figures. Of which : Each figure is eight (for example : 62781704) 0-9 10 figures every two digital connections between at least one (like 62781707, which were : connecting 6-2,2-7,7-8,8-1,1-7,7-0,0-7 7 7-0 and 0
Date : 2008-10-13 Size : 6.71kb User : 吴倩茜
[Speech/Voice recognition/combine] 1-4 DL : 1: 为均衡带限信号所引起失真的横向或格型自适应均衡器(其中横向FIR系统长M=11), 系统输入是取值为±1的随机序列，其均值为零；参考信号；信道具有脉冲响应：式中w用来控制信道的幅度失真(w = 2～4，例如，取w = 2.9,3.1,3.3,3.5等),而且信道受到均值为零、方差为 (例如，取，相当于信噪比为30dB)的高斯白噪声的干扰。试比较基于下列五种算法自适应均衡器在不同信道失真、不同噪声干扰下的收敛情况(对应于每一种情况，在同一坐标下画出其学习曲线)：横向/格-梯型结构LMS算法[1-4] 横向/格-梯型结构RLS算法[1-4]
Date : 2008-10-13 Size : 1.15kb User : tang
[Speech/Voice recognition/combine] 10-1snoopy DL : 0: 该程序是非特定人语音识别程序，原来在SPCE500A下运行，能识别并应答16个命令，存储空间为128K字节。 //我们将其进行了修改，使其能在SPCE061A下运行，由于存储空间为32K字，只能识别并应答9个命令。 //在这个例程当中，我们示范了如何使用语音识别引擎对8个已经经过训练的命令进行识别。 //第一个命令 "Snoopy"，可以作为使能命令，也就是说使用者只能在该命令之后发出其他命令。 //例如，用户只有在发出 "Snoopy"命令并且听到响应"Snoopy here"之后才能继续下达其他命令 //如"How are you", "I love you",等等。 //当"Snoopy"命令响应之后，程序将等待8秒钟，如果没有其他命令发出， //系统将跳回到第0组，并且再次等待触发命令"Snoopy"。当用户的命令无法被识别时， //程序将响应为"Execuse me?", "I can t hear you!"或 "Say again!"这时用户可以再一次下达语音命令。-the procedures were non-specific voice recognition procedure, the original run in SPCE500A can identify and Response 16 orders, storage space for 128K bytes.// We had to amending it so that it can run in SPCE061A, storage space for 32K words, recognize only nine responses and orders.// This routine, we have demonstrated how to use voice recognition engine has eight pairs of trained orders for identification.// The first order "Jack Champion", as it can make an order, users can only say in the order issued after other orders.// For example, users only the issue of "Jack Champion" command and response hear "Jack Champion here" can be issued to other orders// as "How are you" and "I love you" and so on.// When "Jack Champion&q
Date : 2025-12-25 Size : 258kb User : 胡珈
[Speech/Voice recognition/combine] telephoneSearch DL : 0: 实现如下的功能：在电话语音识别中需要识别电话号码，这需要识别0到9十个数字，而识别前首先需要训练这十个数字，请编写程序设计一个电话号码表，要求数字组数最少。其中：每一组数字都是八位（例如：62 781 704），0到9十个数字中每两个数字之间至少连接一次（象62781707，其中出现了：6－2、2—7、7－8、8—1、1—7、7—0、0—7七个连接，7－0和0¬ —7是不同的连接），每个数字在开头、结尾至少各出现一次（象62781707其中，6在开头出现一认，7在结尾出现一次）。-achieve the following functions : the telephone speech recognition need to identify the telephone number, This requires identification 0-9 10 figures, and identify training needs first before this 10 figures, please procedures designed to prepare a phone number, requesting at least a group of figures. Of which : Each figure is eight (for example : 62781704) 0-9 10 figures every two digital connections between at least one (like 62781707, which were : connecting 6-2,2-7,7-8,8-1,1-7,7-0,0-7 7 7-0 and 0
Date : 2025-12-25 Size : 6kb User : 吴倩茜
[Speech/Voice recognition/combine] 1-4 DL : 0: 为均衡带限信号所引起失真的横向或格型自适应均衡器(其中横向FIR系统长M=11), 系统输入是取值为±1的随机序列，其均值为零；参考信号；信道具有脉冲响应：式中w用来控制信道的幅度失真(w = 2～4，例如，取w = 2.9,3.1,3.3,3.5等),而且信道受到均值为零、方差为 (例如，取，相当于信噪比为30dB)的高斯白噪声的干扰。试比较基于下列五种算法自适应均衡器在不同信道失真、不同噪声干扰下的收敛情况(对应于每一种情况，在同一坐标下画出其学习曲线)：横向/格-梯型结构LMS算法[1-4] 横向/格-梯型结构RLS算法[1-4]
Date : 2025-12-25 Size : 1kb User : tang
[Speech/Voice recognition/combine] Lucene.Net-1.9.1-004-27Nov06 DL : 0: Lucene.Net-1.9.1-004-27Nov06源码-Lucene.Net-1.9.1-004-27Nov06 source
Date : 2025-12-25 Size : 784kb User : 逍遥
[Speech/Voice recognition/combine] EX5 DL : 0: 在电话语音识别中需要识别电话号码，这需要识别0到9十个数字，而识别前首先需要训练这十个数字。-Telephone Speech Recognition in the identification of necessary phone numbers, which identify the required ten figure 0-9, and the identification of required training before the first figure 10.
Date : 2025-12-25 Size : 1kb User : lan
[Speech/Voice recognition/combine] m_usart DL : 0: PIC单片机模拟串口收发.可设置波特率。8位9位可选-PIC microcontroller analog serial transceiver. You can set the baud rate. 8 9 optional
Date : 2025-12-25 Size : 58kb User : 倪平
[Speech/Voice recognition/combine] mfccandvc DL : 0: 文章介绍的说话人识别系统，采用能够反映人对语音的感知特性的9(:频率倒谱系数（9(: <+(=>(2/?8(’0+): 81(..-/-(20@，9<88）作为特征参数，同时考虑到特征参数各维分量对于不同说话人的区分程度，采用加权的办法进行矢量量化。-This paper introduces the speaker recognition system used to reflect the people s perception of voice characteristics 9 (:-Frequency Cepstral Coefficients (9 (: <+(=>( 2 /? 8 ( 0+): 81 (..-/-( 20 @, 9 "88) as the characteristic parameter, taking into account the characteristic parameters for different components of each dimension of the distinction between the speaker level, using weighted approach to vector Quantization. .
Date : 2025-12-25 Size : 59kb User : 于高
[Speech/Voice recognition/combine] echo-nest-java-api-1[1].2 DL : 0: echonest的音乐分析软件API,可以获取歌曲的各种信息-echonest s music analysis software api
Date : 2025-12-25 Size : 358kb User : 刘玲
[Speech/Voice recognition/combine] Spedaker_Adapting_in_Speech_recognizing DL : 0: ：自适应技术在近年来得到越来越多的重视，其中应用广泛的包括,-.、,//0，该技术利用少量特定人数据就可以调整码本，快速地提升识别性能，它要求原始的码本有很好的说话人无关性。本文介绍了结合 ,//0 自适应的说话人自适应训练（1234536 -74289:3 649<9<=，以下简称1- ）算法，这种方法将每个说话人码本视为说话人无关码本经过线性变换的结果，在此基础上训练的说话人无关码本更有效剔除了说话人相关信息，因此在说话人自适应中时能根据特定数据调整更好地逼近说话人特性，从而有更好的性能表现。-Introduced the term network based maximum likelihood linear regression unsupervised adaptive algorithm, and an improved. According to decode the received word net estimated transformation parameters, the word error rate of net potential is far less than the recognition results, it can make parameter estimation more accurate. A major drawback is that the traditional calculation enormously difficult practical, this paper presents two improved technology: 1 compression using word posterior probability network 2 time information using the word limit state statistic calculation. Experimental determination of the relative error rate than traditional down.
Date : 2025-12-25 Size : 215kb User : 自然快乐
[Speech/Voice recognition/combine] 61_Record DL : 0: 61精简开发板实验范例语音闹钟完全代码很有用值得借鉴！-61 experimental paradigm to streamline the development board voice alarm clock is useful to be learned from the code completely!
Date : 2025-12-25 Size : 88kb User : 钱朝龙
[Speech/Voice recognition/combine] Soudcode DL : 0: 声音验证码，数字0-9，请使用VS2008 SP1或VS2010打开。-Voice verification code, numbers 0-9, use the VS2008 SP1 or VS2010 open.
Date : 2025-12-25 Size : 105kb User : 刘俊岭
[Speech/Voice recognition/combine] 0-9(Speech-Recogenition) DL : 0: 用matlab仿真0到9十个数字的语音识别 1、对语音的WAV文件和LAB文件进行处理，产生十个文件，每个文件对应于一个数字，存贮着该数字的波形文件。（shujuzhengli.m） 2、分别利用上面十个文件训练出十个HMM模板，具体方法是：首先将语音的波形文件分帧，以128个点为一帧，帧移为64，每一帧通过mfcc.m计算出13个系数，随着波形的长度不同，一个语音文件可以计算得到13*N个系数，截取13*15的矩阵（mfcc系数）用作训练数据。一般一个HMM模板用20组mfcc系数训练，得到初始状态分布、状态转移矩阵、高斯正态分布的均值和方差以及混合矩阵，这就是该语音的特征，存贮下来，识别的时候使用。（trainmfcc.m） 3、识别过程：识别的前面部分与训练相似，都是要计算得到mfcc系数，不同在于，识别时，将计算得到的mfcc 参数分别代入训练得到的HMM模板求出概率，比较出最大概率者，则该模板对应的数字就是识别的数字。(shibiesb.m) 4、用大量语音文件做测试，结果正确率为90 以上。-Speech Recogonition: Mumber 0-9
Date : 2025-12-25 Size : 109kb User : Fatso Ding
[Speech/Voice recognition/combine] codes DL : 0: 基于DTW算法的孤立词语音识别，可识别0-9-DTW-based isolated word speech recognition algorithm can recognize 0-9
Date : 2025-12-25 Size : 416kb User : 吉
[Speech/Voice recognition/combine] 4.8k_CELP DL : 0: 语音CELP压缩解压源代码（C语音)- Pronunciation CELP compression decompression source code (C pronunciation) - * 4800 bps CELP Characteristics * * Spectrum Pitch Code Book * ------------- --------------- ----------------- * Update 30 ms 30/4 = 7.5 ms 30/4 = 7.5 ms * ll=240 lp=60 l=60 * * Order 10 256 (max) x 60 512 (max) x 60 * 1 gain 1 gain * * Analysis Open loop Closed loop Closed loop * Correlation Modified MSPE MSPE VQ * 30 ms Hamming VQ, weight=0.8 weight=0.8 * no preemphasis range 20 to 147 shift by 2 * 15 Hz BW exp (w/ fractions) 77 sparsity * * Bits per 34 indep LSP index: 8+6+8+6 index: 9*4 * Frame [3444433333] gain(-1,2): 5*4 gain(+/-): 5*4 * * Bit Rate 1133.3 bps 1600 bps 1866.67 bps * * NOTE: The remaining 200 bps are used as follows: 1 bit per frame * for synchronizatio
Date : 2025-12-25 Size : 107kb User : lcd
[Speech/Voice recognition/combine] yuyin DL : 0: 用DTW算法实现的孤立词语音识别，利用语音的mfcc特征进行识别，可识别0-9十个数。使用时请改相关路径.-DTW with isolated word speech recognition algorithm, using speech recognition mfcc characteristics can be identified 0-9 ten numbers. Please change the relative path when using
Date : 2025-12-25 Size : 6.88mb User : 刘洪君
[Speech/Voice recognition/combine] HMMBasedGestureRecognition-master DL : 1: 基于HMM的0-9是个数字语音识别源程序(HMM based on 0-9 is a digital voice recognition source)
Date : 2025-12-25 Size : 2.64mb User : 2benming
[Speech/Voice recognition/combine] sphinx-0.9.8-win32 DL : 0: Voice recognition in windows java.
Date : 2025-12-25 Size : 1.76mb User : webkahve