Scribd Logo
Upload

Welcome to Scribd!

  • 2K views

    Thesis Chapter I - ACM Format

    Uploaded by

    Ryan Podiotan Adlao Sapitanan
    This document discusses a research project that aims to implement a speech recognition system using Hidden Markov Models and the Viterbi algorithm to control the movement of a robotic arm. The objectives are to 1) establish an analysis of implementing speech recognition using these techniques and 2) apply the speech recognition system to control a robotic arm. Specifically, the research will examine how the Viterbi algorithm works with Hidden Markov Models for speech recognition, how Hidden Markov Models are used in the recognition process, and how recognized speech commands can be used to communicate with and control a robotic arm. The scope is limited to short speech sounds and a simple robotic arm vocabulary and movement set.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOCX, PDF, TXT or read online from Scribd

    Thesis Chapter I - ACM Format

    Uploaded by

    Ryan Podiotan Adlao Sapitanan
    2K views1 page
    This document discusses a research project that aims to implement a speech recognition system using Hidden Markov Models and the Viterbi algorithm to control the movement of a robotic arm. The objectives are to 1) establish an analysis of implementing speech recognition using these techniques and 2) apply the speech recognition system to control a robotic arm. Specifically, the research will examine how the Viterbi algorithm works with Hidden Markov Models for speech recognition, how Hidden Markov Models are used in the recognition process, and how recognized speech commands can be used to communicate with and control a robotic arm. The scope is limited to short speech sounds and a simple robotic arm vocabulary and movement set.

    Original Description:

    This is the chapter 1 of Computer Science Thesis Proposal Project.

    Copyright

    © Attribution Non-Commercial (BY-NC)

    Available Formats

    DOCX, PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    This document discusses a research project that aims to implement a speech recognition system using Hidden Markov Models and the Viterbi algorithm to control the movement of a robotic arm. The objectives are to 1) establish an analysis of implementing speech recognition using these techniques and 2) apply the speech recognition system to control a robotic arm. Specifically, the research will examine how the Viterbi algorithm works with Hidden Markov Models for speech recognition, how Hidden Markov Models are used in the recognition process, and how recognized speech commands can be used to communicate with and control a robotic arm. The scope is limited to short speech sounds and a simple robotic arm vocabulary and movement set.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    2K views1 page

    Thesis Chapter I - ACM Format

    Uploaded by

    Ryan Podiotan Adlao Sapitanan
    This document discusses a research project that aims to implement a speech recognition system using Hidden Markov Models and the Viterbi algorithm to control the movement of a robotic arm. The objectives are to 1) establish an analysis of implementing speech recognition using these techniques and 2) apply the speech recognition system to control a robotic arm. Specifically, the research will examine how the Viterbi algorithm works with Hidden Markov Models for speech recognition, how Hidden Markov Models are used in the recognition process, and how recognized speech commands can be used to communicate with and control a robotic arm. The scope is limited to short speech sounds and a simple robotic arm vocabulary and movement set.

    Copyright:

    Attribution Non-Commercial (BY-NC)
    Download as DOCX, PDF, TXT or read online from Scribd
    Download as docx, pdf, or txt
    of 1

    A Viterbi Algorithm Implementation For Speech Recognition Using Hidden Markov Model Applied to Robotic Arm Movement

    Mikeel Nuel Langomez Mark Ferdinand Sanchez Ryan Sapitanan

    1. INTRODUCTION 1.1 Project Context


    For so many years, research in the area of speech recognition has been characterized by the steady accumulation of small incremental improvements. A lot of techniques models and algorithms has been postulated and formulated and then integrated and re-combined to experiment which works well on a specific application. One of the research areas is to improve robustness of speech recognition performance against any condition that causes degradation in performance not just robustness against noise. Since it is too expensive to have humans transcribe such huge amount of speech, it would be better enough to focus the research on developing new methods of machine learning that can effectively utilize large quantities of unlabeled data. HMM-based approach (Hidden Markov Model) along with the Viterbi algorithm which can be used in the area of speech decoding is just another combination technique that enables such feat. It is in this perspective, the researchers would like to contribute even in its humble contribution while experimenting a way to control mechanical devices and further shed supplementary light while exploring this computing technology.

    disciplines such as robotics, ergonomics, or even special education. This research is intended to explore the extending possibilities of the HMM-based computing technology and experiment to find ways for optimization.

    1.3 Objectives
    The general objectives of the study are: [1] to establish formalism, abstraction or analysis of the implementation of speech recognition; and [2] to apply the speech recognition system to a device that controls the movement of robotic arm. Specifically, this research will be done to answer the following items: 1. How Viterbi Algorithm works with the Hidden Markov Model? 2. How the Hidden Markov Model plays the main role in the speech recognition process? 3. How the speech sound signal analysis and pattern matching process works in identifying specific commands for control? 4. How to communicate the speech recognition system to a robotic arm device to serve as movement control? 5. What is the efficiency of the combination computing technique as applied to robotic arm movement control?

    1.2 Purpose & Description


    Speech recognition is basically a pattern recognition dedicated to detect speech, or in other words, to identify language words from sound signal achieved as input from the environment. Pattern matching makes a comparison among source reference patterns previously stocked on the system and scores the likelihood of this reference patterns against the input set. The speech will be converted into sequence of commands. The sequence observation is evaluated using Hidden Markov Model, which, as the acoustic reference pattern, plays the main role in the recognition process. The Viterbi Algorithm is used to compute the Hidden Markov Model likelihood score. The commands generated from the speech recognition setup will be fed in to the robotic arm setup for movement control. Speech recognition covers a variety of uses which include controlling certain devices through voice commands. Controlling a robotic arm simply puts the researchers in an opportunity for improvement of the technique as applied to other research

    1.4 Scope & Limitations


    The research will focus on relatively short speech sounds with a relatively simple vocabulary and grammar just to implement with the robotic arm movement. This is to show how the algorithm and model really works with this setup. The robotic arm will only allow limited arm movement as with the device to include swinging for example. The researchers will use the Hidden Markov Model toolkit (HTK) developed by the Cambridge University which is intended for HMM-based research. The toolkit is used to build the Hidden Markov Model. The researchers will then conduct efficiency evaluation of the computing technique as applied to a robotic arm movement control.

    You might also like