IEEE paper and Patent Review

-
IEEE Paper :
DSP Implementation of Voice Recognition Using Time Warping Algorithm
Department of Electronics Engineering, NED University of Engineering & Technology, Karachi
Date of Conference - 27 Aug 2005
Date added to IEEE Xplore - 12 Nov 2007.
Review:
The paper tells about voice recognition algorithm using Time Warping. Voice recognition is a process of an automatic system to identify the speech. Paper tells about voice recognition using Cepstral analysis & DTW of set of five words. The developed models provide tools to record, filter and analyze different voice signals and compare them with output sample. Voice signal analysis is done using various operations like pre-emphasis, normalizing, windowing, cepstrum analysis and recognition of the input word. Recognition block uses dynamic time warping algorithm. The software used for implementation are MATLAB, Simulink, Softscope (Data Acquisition Toolbox ). Hardware used is C67x consisting of three main parts: CPU, Peripherals, Memory. The output showed that the Cepstrum analysis and time warping algorithm gives 68% accurate results.    

Patent :
David Lee Basore and William Stuart Meisel, Voice activated device and method for providing access to remote data.
Patent No. : US5752232
Publication Date : May 12, 1998.

Review:
A voice activated device which uses speaker independent voice recognition is able to receive phonetic spellings required for recognition from a remote location. The phonetic spellings and the additional data are communicated to activated device from remote location and stored in the device. A user can then give voice commands which are intercepted by the device voice command’s local processing takes place. The information may be communicated to the user by means of voice or via other media. The DSP processor used for implementation uses ADC.

 Learning Experience :
We were looking for the DSP application for Speech signal. So, we searched for different speech signal applications from IEEE paper conference website and we searched for patents on freepatentsonline.com . We used matlab to obtain the required waveform for the process. For the first time in my life I referred patents. The team worked hard to get output because there were some problems to obtain required output.  

Comments

  1. utkarsha@tilakMay 15, 2018 at 7:19 AM

    This can be used as voice passwords in mobile phones.

    ReplyDelete
    Replies
    1. UnknownMay 15, 2018 at 9:40 PM

      Not only mobile phones it can be used anywhere where there is need of password access.

      Delete
  2. UnknownMay 15, 2018 at 7:19 AM

    Good Work !! Correlation can also be used for this.

    ReplyDelete
    Replies
    1. UnknownMay 15, 2018 at 9:40 PM

      Yes we used correlation property at the end for this application.

      Delete
  3. MayurLankhande2510May 15, 2018 at 7:30 AM

    The DSP processors are widely used in applications like this. They use very simple programming for the such applications.

    ReplyDelete
    Replies
    1. UnknownMay 15, 2018 at 9:42 PM

      DSP Processors are also used in applications like Image processing, RADAR etc.

      Delete
  4. tilakmunshiMay 15, 2018 at 9:56 AM

    Voice Recognition can be used in various applications, mainly in authentication as well as in home saftey features.Will read your report for sure.

    ReplyDelete
    Replies
    1. UnknownMay 15, 2018 at 9:44 PM

      The report briefly talks about use of simple algorithm like Correlation for voice recognition.

      Delete
  5. Omkar SawantMay 15, 2018 at 9:56 AM

    Very Informative the usage of time warping technique in voice based password systems is explained.

    ReplyDelete
    Replies
    1. UnknownMay 15, 2018 at 9:45 PM

      You can also read the IEEE paper for more information.

      Delete

Post a Comment

Popular posts from this blog

Overlap Add Method and Overlap Save Method

-
This was 4th experiment. In this experiment we perform filtering of Long Data Sequences using OAM and OSM. To perform a c program was written and executed and output was found as desired. Overlap Add Method        In this method input signal x(n) is decomposed into no. of L point sequences using formula N=L+M-1, where M is length of h(n) and N is assumed to be Radix2 value. Then we find linear convolution between every decomposed signal and h(n) using FFT algorithm. The Inverse FFT is then performed on all output signals and the outputs are added to get final result. Overlap Save Method       In this method input signal x(n) is again decomposed into L point sequences using formula N>=L+M-1, where M is length of h(n) and N is assumed to be Radix2 value. Here every decomposed signal is begins with (N-L) last values of previous signal. Then we find linear convolution between every decomposed signal and h(n) using FFT algorithm. The Inverse FFT is...
Read more

DSPP Course Review

-
On the lecture of the DSP subject I was absent because of the internship so I won't be able give the first day or first week review of the course. From next week I started attending lectures and my first lecture was on DFT algorithm. DSP subject was the continuation the 'Signals and System' subject which was also taught by Talele sir so we knew some basic concepts of signals, filters already. From 1st module, we found how DFT is obtained using DTFT from sampling and by DFT formulas. But after completion of DFT module we found that the number of computations in DFT were too large. so we were introduced to FFT algorithm as 2nd module which was faster in performance. But there were some disadvantages of FFT so we went for OAM and OSM. 3rd module was on Filter design, we designed IIR filters by IIM and BLT method and FIR filters by Windowing and frequency sampling method. 4th module was on quantization  of filter parameters. In which we learned about Input, output, coefficie...
Read more

DSP Processor

-
The aim of this experiment was to perform various operations on DSP Processor. We used TMS320F2855 processor to perform those tasks. We used Code Composer Studio to program to processor. We performed Arithmetic operations like Addition, Subtraction, Multiplication and logical Operations like AND, OR, NOT.The change in the register values was observed. 
Read more