Today

1
CA461 Speech Processing 1

• Welcome
• Today
• Admin
• Module Overview
• A taste of things to come

2
Admin

• Lectures
• John McKenna, john_at_computing.dcu.ie Office 2.47,
  Tel. [phone]
• Tuesday 1pm, C114
• Thursday 2pm, Q119
• Labs
• Tuesday 3-5pm, L2.08

3
Admin

• CA4 students welcome from all streams
• CL4 core module
• CLX welcome too
• Please come see me if you have doubts about
  prerequisite knowledge
• Prerequisites
• Some maths
• probability, linear algebra (matrices)
• Ability to program
• Open mind

4
Admin

• Assessment
• Continuous Assessment 60
• Assignment 1 40 or Assignment 2 50
• APC 10 (Not a distance education module)
• End of module exam 40
• Books, etc
• See Module Descriptor for list
• No book purchase necessary
• Recommended
• Gold Morgan, or Holmes Holmes
• Headset required
• Composite (with microphone) recommended
• Sharing feasible

5
Module Overview

• Module Aims
• To present the characteristics of speech
• To discuss automatic speech recognition systems
• Indicative Syllabus
• Speech Production, Representations and
  Terminology
• Introduction to Waveforms, Spectrograms,
  Fundamental Frequency Formants
• Overview of ASR (Automatic Speech Recognition)
• Hidden Markov Models (HMMs) and Trellis
  Algorithms
• Speech Parametrisation for ASR
• HMM Training and Recognition
• Other issues and applications

6
Module Overview

• Learning Outcomes
• An understanding of speech production and speech
  waveforms
• Familiarity with current models of speech
  production and analysis
• Competence at implementing speech recognition
  algorithms
• Ability to program MATLAB scripts
• Ability to use HTK (Hidden Markov Model Toolkit)
  for speech recognition design
• A good knowledge of the principles and problems
  involved in the design, implementation and
  evaluation of speech recognition systems

7
Module Overview

• Achieving the aims of the module will involve the
  following
• Communication skills
• Group Work skills
• Organisational skills
• Personal skills
• Problem solving skills
• Programming skills
• Information Technology skills
• Cross-disciplinary partnerships
• Skills transfer
• Module mailing list
• Discussion forum No code!!!

8
What about Speech Processing 2?

• Focus on
• Speech Analysis
• Digital Signal Processing of Speech
• Speech Synthesis
• Prerequisites
• Speech Processing 1 or
• possibly DSP 1
• Semester 1
• You can choose both DSP1 and SP1

9
A Taste of Things to Come

• Todays Lab
• Recording
• Analysis
• Synthesis
• Experiment
• Now
• Demos
• Next
• Speech Production Review