Temple University Goals : 1.Down sample 20 khz TIDigits data to 16 khz. 2. Use Down sample data run regression test and Compare results posted in Sphinx-4.

Slides:



Advertisements
Similar presentations
Samsung Smart TV is a web-based application running on an application engine installed on digital TVs connected to the Internet.
Advertisements

1 CS 446 – Tutorial 6 Frid. Nov. 6 th, 2009 Implementation Tutorial.
Computer Software 3 Section A Software Basics CHAPTER PARSONS/OJA
WebGoat & WebScarab “What is computer security for $1000 Alex?”
LECTURE 7 SEP 27, 2010 Building computational pipelines.
Top Level System Block Diagram BSS Block Diagram Abstract In today's expanding business environment, conference call technology has become an integral.
GIS Topics and Applications
Algorithmic State Machines
Copyright © 2006 by The McGraw-Hill Companies, Inc. All rights reserved. McGraw-Hill Technology Education Copyright © 2006 by The McGraw-Hill Companies,
Creating a Console Application with Visual Studio
By Davis Hsu. Why is it important to have the Emergency Document automatically updated? The Emergency Document provides the important documentation on.
CHAPTER 4: INTRODUCTION TO COMPUTER ORGANIZATION AND PROGRAMMING DESIGN Lec. Ghader Kurdi.
OpenTS for Windows Compute Cluster Server. Overview  Introduction  OpenTS (academic) for Windows CCS  T-converter  T-microkernel  OpenTS installer.
Temple University Speech Recognition using Sphinx 4 (Ti Digits test) Jaykrishna shukla,Amir Harati,Mubin Amehed,& cara Santin Department of Electrical.
Topics Introduction Hardware and Software How Computers Store Data
Job Aids video storyboard Matt Boardman, Chiao-Ling Lu.
Lab 11 Department of Computer Science and Information Engineering National Taiwan University Lab11 - Porting 2014/12/9/ 26 1.
CprE 588 Embedded Computer Systems Prof. Joseph Zambreno Department of Electrical and Computer Engineering Iowa State University Lecture #7 – System-Level.
Creating Speaking Web Pages: The Text-to-Speech Integrated Development Environment (TTS-IDE) David C. Gibbs Department of Mathematics and Computing University.
Copyright © 2012 Pearson Education, Inc. Publishing as Pearson Addison-Wesley C H A P T E R 1 Introduction to Computers and Programming.
FYP Final Presentation: Distributed Audio Mixing Daire O'Neill, Final Year Electronic Engineering Project Supervisor: Dr Peter Corcoran Co-Supervisor:
Temple University QUALITY ASSESSMENT OF SEARCH TERMS IN SPOKEN TERM DETECTION Amir Harati and Joseph Picone, PhD Department of Electrical and Computer.
1 Building the CarryDrop Simulation in JBuilderX By Deddy Koesrindartoto 08/16/2004.
Seungchan Lee Intelligent Electronic Systems Human and Systems Engineering Department of Electrical and Computer Engineering Software Release and Support.
IT 456 Seminar 5 Dr Jeffrey A Robinson. Overview of Course Week 1 – Introduction Week 2 – Installation of SQL and management Tools Week 3 - Creating and.
CMAQ Runtime Performance as Affected by Number of Processors and NFS Writes Patricia A. Bresnahan, a * Ahmed Ibrahim b, Jesse Bash a and David Miller a.
Wake-up Word Detector Douglas Rauscher ECE5525 April 30, 2008.
* Third party brands and names are the property of their respective owners. Performance Tuning Linux* Applications LinuxWorld Conference & Expo Gary Carleton.
Temple University Training Acoustic model using Sphinx Train Jaykrishna shukla,Mubin Amehed& cara Santin Department of Electrical and Computer Engineering.
Installing CompuCell3D from source. Why you might want to install from source? 1.There are no binaries for your platform (e.g. gentoo linux) 2.You want.
Temple University Training Acoustic Models Using SphinxTrain Jaykrishna Shukla, Mubin Amehed, and Cara Santin Department of Electrical and Computer Engineering.
Round-Robin Discrimination Model for Reranking ASR Hypotheses Takanobu Oba, Takaaki Hori, Atsushi Nakamura INTERSPEECH 2010 Min-Hsuan Lai Department of.
Kickstart Installation
Guide to Linux Installation and Administration, 2e1 Chapter 11 Using Advanced Administration Techniques.
Release Progress Report Daniel May Intelligent Electronic Systems Human and Systems Engineering Department of Electrical and Computer Engineering min XMLABNF.
Component 4: Introduction to Information and Computer Science Unit 5: Overview of Programming Languages, Including Basic Programming Concepts Lecture 2.
OCR GCSE Computing © Hodder Education 2013 Slide 1 OCR GCSE Computing Python programming 1: Introduction.
Agenda Overview 2.What is SharePoint? 3.NCDOT Websites 4.Roles 5.Search 6.SharePoint Interface.
PROPOSAL : The Use of Voice Command in Operating Personal Computer By : COLLEGE OF ART & SCIENCE UNIVERSITI UTARA MALAYSIA STIW5023 ADVANCED PROGRAMMING.
This is a personal evaluation that was carried out after the completion of my project one and two. The next slide shows the summary of the key points.
Getting Started with SIDL using the ANL SIDL Environment (ASE) ANL SIDL Team MCS Division, ANL April 2003 The ANL SIDL compilers are based on the Scientific.
Basic structure of sphinx 4
Renesas Technology America Inc. 1 SKP8CMINI Tutorial 2 Creating A New Project Using HEW.
IT System Administration Lesson 3 Dr Jeffrey A Robinson.
® IBM Software Group © 2006 IBM Corporation Rational Asset Manager v7.2 Using Scripting Tutorial for using command line and scripting using Ant Tasks Carlos.
ALPHABET RECOGNITION USING SPHINX-4 BY TUSHAR PATEL.
Software testing techniques Software testing techniques REGRESSION TESTING Presentation on the seminar Kaunas University of Technology.
Software. Introduction n A computer can’t do anything without a program of instructions. n A program is a set of instructions a computer carries out.
Simple Project on Digit Recognition By: Class: Faculty: Manish Ravlani Speech Recognition Dr. Kepuska.
An Introduction to Programming with C++1 Beginning the Problem- Solving Process Tutorial 2.
Software Engineering Algorithms, Compilers, & Lifecycle.
A S P. Outline  The introduction of ASP  Why we choose ASP  How ASP works  Basic syntax rule of ASP  ASP’S object model  Limitations of ASP  Summary.
REGRESSION TESTING Audrius Čėsna IFM-0/2. Regression testing is any type of software testing that seeks to uncover new errors, or regressions, in existing.
Bootstrap Tutorial Overview Objective Learn how to use the bootstrap for configuring the system. Requirements Installed Version of.
Solvency II Tripartite template V2 and V3 Presentation of the conversion tools proposed by FundsXML France.
SNS Integrated Control System ORACLE –JERI DB Generation April 27, 2004 Coles Sibley Jeff Patton.
With. Project Overview  Introduction to Factory Automation Numerical Control  Build an autonomous robotic solution  Testing an autonomous robot build.
Topic 2: Hardware and Software
Development Environment
Chapter Topics The Basics of a C++ Program Data Types
Obtaining the Required Tools
Topics Introduction Hardware and Software How Computers Store Data
ECE Computer Engineering Design Project
Matlab Training Session 4: Control, Flow and Functions
Basic Elements of C++.
Digital Speech Processing
Basic Elements of C++ Chapter 2.
ECE Computer Engineering Design Project
Topics Introduction Hardware and Software How Computers Store Data
ICT Gaming Lesson 2.
Presentation transcript:

Temple University Goals : 1.Down sample 20 khz TIDigits data to 16 khz. 2. Use Down sample data run regression test and Compare results posted in Sphinx-4 website 3. Based on the results, make decisions (issue with microprocessor, floating point etc.) By Jaykrishna shukla, Mubin Ahmed and Cara Santin

Temple University Learned : 1.Cygwin not effective to run Sox 2. effective to run linux command line interface to build application 3.Easy to install

Temple University Training Acoustic model using Sphinx Train URL:

Temple University Introduction to Training Q1.What is acoustic model ? A1. model used by a speech recognizer for decoding language spoken by a person and modeling numerically how the language sounds when spoken in a form that can be stored on a computer. Q2. what is training A2. process that wants to converge on a solution yielding the most likely sequence of vectors for a given acoustic unit. Q3. why is training required? A3. In order to generate a set of acoustic model for any audio data, one needs to follow a particular set of steps which is named as training, hence to generate acoustic model, training is required.

Temple University The Flow chart for the Training Procedure Training acoustic model using SphinxTrain 1.0 overview

Temple University SphinxTrain 1.0 & auto generation The new version of sphinx train has a build all option, that generates all the required files that were shown in the flow chart from previous slide. However, in order to do object specific function, one needs to modify the config file according to the purpose of the task.

Temple University This week’s accomplishment The two major goals that I achieved this week were: Finished the complete training process for the an4 demo. Worked on generating the feature model for the TI Digit short test data. Sample output of a training process (it took more than 20 min to compile this code)

Temple University Generating the feature vectors There two main step in generating the feature vector: 1. Generate the.Fileids file (it is just the path list of all the data file) 2. Modify the Make_feats (perl script) to in order to read the correct data in and change the default settings that the SphinxTrain comes with.

Temple University Conclusion and Future The main problem in feature generation is that the Make_feats file has default settings for the an4 tutorial, hence to getting it working we have to change the configuration for both the make_feats file and the SphinxTrain connfig file (because the config file determines what goes in to the make_feats file. Follow the below Example )

Temple University Training Acoustic model using Sphinx Train Jaykrishna shukla,Mubin Amehed& cara Santin Department of Electrical and Computer Engineering Temple University URL:

Temple University: Slide 10 Introduction to Training Q1.What is acoustic model ? A1. model used by a speech recognizer for decoding language spoken by a person and modeling numerically how the language sounds when spoken in a form that can be stored on a computer. Q2. what is training A2. process that wants to converge on a solution yielding the most likely sequence of vectors for a given acoustic unit. Q3. why is training required? A3. In order to generate a set of acoustic model for any audio data, one needs to follow a particular set of steps which is named as training, hence to generate acoustic model, training is required.

Temple University: Slide 11 The Flow chart for the Training Procedure Training acoustic model using SphinxTrain 1.0 overview

Temple University: Slide 12 SphinxTrain 1.0 & auto generation The new version of sphinx train has a build all option, that generates all the required files that were shown in the flow chart from previous slide. However, in order to do object specific function, one needs to modify the config file according to the purpose of the task.

Temple University: Slide 13 This week’s accomplishment The two major goals that I achieved this week were: Finished the complete training process for the an4 demo. Worked on generating the feature model for the TI Digit short test data. Sample output of a training process (it took more than 20 min to compile this code)

Temple University: Slide 14 Generating the feature vectors There two main step in generating the feature vector: 1. Generate the.Fileids file (it is just the path list of all the data file) 2. Modify the Make_feats (perl script) to in order to read the correct data in and change the default settings that the SphinxTrain comes with.

Temple University: Slide 15 Conclusion and Future The main problem in feature generation is that the Make_feats file has default settings for the an4 tutorial, hence to getting it working we have to change the configuration for both the make_feats file and the SphinxTrain connfig file (because the config file determines what goes in to the make_feats file. Follow the below Example )