Description

About this course

This course is part of the Microsoft Professional Program in Artificial Intelligence.

Developing and understanding Automatic Speech Recognition (ASR) systems is an inter-disciplinary activity, taking expertise in linguistics, computer science, mathematics, and electrical engineering.

When a human speaks a word, they cause their voice to make a time-varying pattern of sounds. These sounds are waves of pressure that propagate through the air. The sounds are captured by a sensor, such as a microphone or microphone array, and turned into a sequence of numbers representing the pressure change over time. The automatic speech recognition system converts this time-pressure signal into a time-frequency-energy signal. It has been trained on a curated set of labeled speech sounds, and labels the sounds it is presented with. These acoustic labels are combined with a model of word pronunciation and a model of word sequences, to create a textual representation of what was said.

Instead of exploring one part of this process deeply, this course is designed to give an overview of the components of a modern ASR system. In each lecture, we describe a component’s purpose and general structure. In each lab, the student creates a functioning block of the system. At the end of the course, we will have built a speech recognition system almost entirely out of Python code.

What you’ll learn

• Fundamentals of Speech Recognition
• Basic Signal Processing for Speech Recognition
• Acoustic Modeling and Labeling
• Common Algorithms for Language Modeling
• Decoding Acoustic Features into Speech

Prerequisites

• Some python experience
• Basic Machine Learning principles
• Knowledge of probability and statistics

Estimate Time : 20-24 hours

Module 1 Background and Fundamental Theory

• Fundamental Theory
• Phonetics
• Performance Metrics
• Other Considerations
• Lab

Module 2 Speech Signal Processing

• Feature Extraction
• Mel Flitering
• Log Compression
• Feature Normalization
• Lab

Module 3 Acoustic Modeling

• Markov Chains
• Problem with Markov Chains
• Hidden Markov Models
• Deep Neural Network Acoustic Models
• Training Feedforward Deep Neural Networks
• Using Sequence Based Objective Function
• Lab

Module 4 Language Modeling

• N Gram Models
• Language Model Evaluation
• Operations on Language Models
• Advance LM Topics
• Lab

Module 5 Speech Decoding

• Weighted Finite State Transducers
• WFSTs and Acceptors
• Graph Composition
• Lab

Module 6 Advance Acoustic Modeling Techniques

• Improved Objective Functions
• Sequential Objective Function
• Connectionsit Temporal Classification
• Sequence Discriminative Objective Functions
• Lab

Adrian Leven
Content Developer
Microsoft Corporation

Adrian Leven is a Content Developer at Microsoft Learning with a focus on Human-Computer Interaction. He received his B.S. In Computer Science from Stanford University.

Additional information

Certificate