% Computation of ST-ZCR and STE of a speech signal. % % Functions required: zerocross, sgn, winconv. % % Author: Nabin Sharma % Date: 2009/03/15 [x,Fs] = wavread('so.wav'); % word is: so x = x.'; N = length(x); % signal length n = 0:N-1; ts = n*(1/Fs); % time for signal % define the window wintype = 'rectwin'; winlen = 201; winamp = [0.5,1]*(1/winlen);
標(biāo)簽： 短時(shí)過零率和短時(shí)能量
上傳時(shí)間： 2019-09-23
上傳用戶：minwenji
ephraim1995 子空間降噪經(jīng)典算法
標(biāo)簽： Enhancement Approach Subspace Signal speech for
上傳時(shí)間： 2020-04-29
上傳用戶：LacrimosaMozart
This introduction takes a visionary look at ideal cognitive radios (CRs) that inte- grate advanced software-defined radios (SDR) with CR techniques to arrive at radios that learn to help their user using computer vision, high-performance speech understanding, global positioning system (GPS) navigation, sophisticated adaptive networking, adaptive physical layer radio waveforms, and a wide range of machine learning processes.
標(biāo)簽： Technology Cognitive Radio
上傳時(shí)間： 2020-05-26
上傳用戶：shancjb
This paper presents a Hidden Markov Model (HMM)-based speech enhancement method, aiming at reducing non-stationary noise from speech signals. The system is based on the assumption that the speech and the noise are additive and uncorrelated. Cepstral features are used to extract statistical information from both the speech and the noise. A-priori statistical information is collected from long training sequences into ergodic hidden Markov models. Given the ergodic models for the speech and the noise, a compensated speech-noise model is created by means of parallel model combination, using a log-normal approximation. During the compensation, the mean of every mixture in the speech and noise model is stored. The stored means are then used in the enhancement process to create the most likely speech and noise power spectral distributions using the forward algorithm combined with mixture probability. The distributions are used to generate a Wiener filter for every observation. The paper includes a performance evaluation of the speech enhancer for stationary as well as non-stationary noise environment.
標(biāo)簽： Telecommunications Processing Signal for
上傳時(shí)間： 2020-06-01
上傳用戶：shancjb
Although state of the art in many typical machine learning tasks, deep learning algorithmsareverycostly interms ofenergyconsumption,duetotheirlargeamount of required computations and huge model sizes. Because of this, deep learning applications on battery-constrained wearables have only been possible through wireless connections with a resourceful cloud. This setup has several drawbacks. First, there are privacy concerns. Cloud computing requires users to share their raw data—images, video, locations, speech—with a remote system. Most users are not willing to do this. Second, the cloud-setup requires users to be connected all the time, which is unfeasible given current cellular coverage. Furthermore, real-time applications require low latency connections, which cannot be guaranteed using the current communication infrastructure. Finally, wireless connections are very inefficient—requiringtoo much energyper transferredbit for real-time data transfer on energy-constrained platforms.
標(biāo)簽： Embedded_Deep_Learning Algorithms
上傳時(shí)間： 2020-06-10
上傳用戶：shancjb
speech coder 壓縮標(biāo)準(zhǔn)g728源碼，實(shí)現(xiàn)語(yǔ)音壓縮
上傳時(shí)間： 2020-06-12
上傳用戶：sdasdas123344
INTRODUCTION In the past, adding speech recording and playback capability to a product meant using a digital signal processor or a specialized audio chip. Now, using a simplified Adaptive Differential Pulse Code Modulation(ADPCM) algorithm, these audio capabilities can be added to any PICmicro device. This application note will cover the ADPCM compression and decompression algorithms, performance comparison of all PICmicro devices, and an application using a PIC16C72 micro-controller.DEFINITION OF TERMS step size -value of the step used for quantization of ana-log signals and inverse quantization of a number of steps.quantization -the digital form of an analog input signal is represented by a finite number of steps.adaptive quantization -the step size of a quantizer is dramatically changed with time in order to adapt to a changing input signal.inverse quantizer -a finite number of steps is converted into a digital representation of an analog signal.
上傳時(shí)間： 2022-06-20
上傳用戶：
VIP專區(qū)-嵌入式/單片機(jī)編程源碼精選合集系列（36）資源包含以下內(nèi)容：1. C51 I2C 驅(qū)動(dòng)程序 含頭文件.2. arm芯 ucos 下的開發(fā)框架.3. c8051f***的程序源代碼.4. 新華龍單片機(jī)的flash用法.5. 用C8051F300設(shè)計(jì)鋰離子電池充電器的解決方案.6. c8051f系列單片機(jī) 用過采樣和求均值提高ADC分辨率.7. C6000指令集 是對(duì)C6000指令集的文檔.8. VxWorks 編程手冊(cè) VxWorks 編程手冊(cè).9. proteus 6.7及其破解（絕對(duì)好用）.10. iic總線資料.11. 手機(jī)游戲禮包包 原理圖采用OrCad軟件或PowerPCB軟件打開 好玩的很 快來(lái)試試吧.12. 紅外測(cè)溫計(jì) 紅外線測(cè)溫 自動(dòng)化設(shè)計(jì) 原理圖采用OrCad軟件或PowerPCB軟件打開 很完美.13. 9智能機(jī)器人禮包 智能機(jī)器人 單片機(jī)實(shí)現(xiàn) 功能齊全 運(yùn)動(dòng)流暢.14. 哈哈！終于找到了最新版本的UCGUI！ 增加了不少的功能.15. Nios II是一個(gè)用戶可配置的通用RISC嵌入式處理器,這個(gè)文檔詳細(xì)介紹這個(gè)處理器的用法.16. 這是一個(gè)c語(yǔ)言寫的a/d轉(zhuǎn)換程序。利用i2c總線實(shí)現(xiàn)對(duì)24c02的存和取.17. 學(xué)ＤＳＰ時(shí).18. 漢字液晶子程 液晶屏分為4行*12列漢字.19. 這是一個(gè)c語(yǔ)言描述的8位led顯示的源代碼.20. We demonstrate a method for encoding and decoding the [24,12,8] extended binary Golay code using a s.21. Training embedded apps to process speech may be as easy as finding the right 8-bit micro. Don t let.22. The CC1000 RF transceiver is very easy to interface with a microcontroller. The chip is configured.23. One of the most important issues affecting the implementation of microcontroller software deals wi.24. AVR單片機(jī)開發(fā)中.25. 作基于日立公司superh系列微處理器嵌入式操作系統(tǒng)bootloader源代碼.26. touchsceen_test ├─ main.c C語(yǔ)言主源文件 ├─ AscII6x8.c Ascii字符6x8點(diǎn)陣顯示格式數(shù)據(jù) ├─ lcd.c LCD顯示函數(shù)源文件 ├─.27. iic_test ├─ main.c C語(yǔ)言主源文件 ├─ iic.c IIC總線操作和24C040擦寫函數(shù)源文件 └─ iic.h IIC總線操作和24C040寫定義頭文件.28. Nexperia系統(tǒng)聲音實(shí)現(xiàn)的源碼.29. 89C516RD+的兩個(gè)AD轉(zhuǎn)換程序,89C51是22.1184MHZ,有64KB Flash 256B(DataRAM)+1024B(Ext.RAM)的性價(jià)比很高的MCU.30. 網(wǎng)上收集的VC多線程開發(fā)、嵌入式開發(fā)文檔.31. ucos-2在lpc2100上的移制例子。.32. mcf5307實(shí)驗(yàn)源代碼.33. CPLD對(duì)DUSH的讀寫控制,LINUX下運(yùn)行.解壓即可..34. HART協(xié)議由Rosemount公司開發(fā)且已向每個(gè)使用者開放HART協(xié)議采用標(biāo)準(zhǔn)的Bell 202頻移鍵控信號(hào)以1200波特通信以低電平加載于4mA~20mA模擬信號(hào)上.35. 中文MODBUS協(xié)議（完整版）涵蓋協(xié)議基本內(nèi)容。不用我多說(shuō)了吧！自己看好了。.36. μC_OS-II在Nios上的移植（共同學(xué)習(xí)ucosII）.37. SST28F040讀寫源程序,C語(yǔ)言編寫,方便移植.38. 基于ARM 的PDA拼音輸入法源程序,c語(yǔ)言編寫,方便移植.39. Cypress公司的USB芯片開發(fā)資料.40. at91 sam 系列arm7單片機(jī)程序下工具.
標(biāo)簽： 自動(dòng)變速器
上傳時(shí)間： 2013-06-18
上傳用戶：eeworm
VIP專區(qū)-嵌入式/單片機(jī)編程源碼精選合集系列（161）資源包含以下內(nèi)容：1. 溫度監(jiān)視器.2. 通過按鍵在3位一體的數(shù)碼管上顯示數(shù)字.3. 在IAR 環(huán)境下.4. pruotues仿真教程 pruotues仿真教程 pruotues仿真教程.5. 嵌入式系統(tǒng)設(shè)計(jì)的好書.6. i2c總線的verilog代碼.7. 1、實(shí)驗(yàn)?zāi)康? 掌握編寫一般GUI程序的基本步驟.8. 紅色颶風(fēng)原理圖.9. G代碼生成軟件.10. msp430F437三相電表DEMO(編譯器 IAR 3.42A）.11. 鍵盤程序：基于cpld開發(fā)環(huán)境的4*4鍵盤程序.12. ADS下開發(fā)的A/D轉(zhuǎn)換器AD7892及LCD顯示程序.13. mcs51單片機(jī)鍵盤掃描程序.14. 給出了一種基于$3C2410嵌入式SoC的網(wǎng)絡(luò)視頻會(huì)議終端的實(shí)現(xiàn)方案.15. 在仿真軟件protues7.1上仿真arm7的GUI的代碼和protues的工程文件。是學(xué)習(xí)arm的一個(gè)好東西.16. c51的原理圖啊.17. 溫度傳感器ds18b20的完整程序.18. 中興MG815+CDMA模塊USB轉(zhuǎn)接原理圖及PCB圖（基于CP2102的USB TO RS232轉(zhuǎn)接原理.19. Michael J. Pont 的嵌入式系統(tǒng)編程講座1.20. PIC 的ip 有用的著的拿去看看吧 對(duì)于開發(fā)pci總線會(huì)有很大幫助的.21. AT91RM9260PMC程序,程序和ATMEL9260EK開發(fā)板配套.22. Embedded VC++ 4 Programmer s Guide.23. ylp2410的bootloader源碼.24. McCraw-Hill - Wap A Beginner s Guide Ebook-fly.25. 能夠?qū)崿F(xiàn)步進(jìn)電機(jī)的正轉(zhuǎn)反轉(zhuǎn).26. 很好的資料和大家分享 颶風(fēng)板的原理圖.27. 文章的內(nèi)容是有關(guān)嵌入式編程用到的工具-MAKE的中文手冊(cè)..28. 飛思卡爾智能車攝像頭的完整程序.29. STM32的程序.30. 基于PLC控制交流變頻調(diào)速電梯系統(tǒng)的研究的一篇pdf格式說(shuō)明文檔。.31. This a GUI that manages DSP analysis functions for wav-files (e.g., speech signals). Two functions (.32. 《嵌入式系統(tǒng)設(shè)計(jì)與實(shí)例開發(fā)》王田苗 北航出版社.33. 嵌入式開發(fā)中用于自制JTAG的dll文件.34. 黑色經(jīng)典系列 arm嵌入式系統(tǒng)開發(fā)典型模塊.35. 51系列的軟件包,有i2c驅(qū)動(dòng),各種芯片的介紹.36. 此程序是在AVR單片機(jī)atmega169P處理器的程序.37. 關(guān)于手機(jī)BOOTLADER相關(guān).38. 華中機(jī)床的plc程序.39. 鍵盤的源碼的程序.40. 是北京智心工作室的基于MPC8280設(shè)計(jì)的核心板使用手冊(cè).
標(biāo)簽： 微帶天線
上傳時(shí)間： 2013-06-14
上傳用戶：eeworm
2.5 Neural Turing Machine - 2.1 Model - .DS_Store 10KB 2.4 RNN Sequence-to-Sequence Model - 2.8 One Shot Deep Learning - 2.7 Deep Transfer Learning Lifelong Learning especially for RL - 2.2 Optimization - 1.4 speech Recognition Evolution - 1.2 Deep Belief Network(DBN)(Milestone of Deep Learning Eve) - 1.3 ImageNet Evolution（Deep Learning broke out from here） - 2.3 Unsupervised Learning Deep Generative Model - 2.6 Deep Reinforcement Learning
標(biāo)簽： MoldWizard 使用手冊(cè)
上傳時(shí)間： 2013-05-15
上傳用戶：eeworm
蟲蟲下載站版權(quán)所有 京ICP備2021023401號(hào)-1
