Multilingual Representations for Low-Resource Speech Processing

Overview

Limited-Time Offer: Up to 75% Off Coursera Plus!

7000+ certificate courses from Google, Microsoft, IBM, and many more.

This course focuses on teaching multilingual representations for low-resource speech processing. The learning outcomes include understanding how multilingual speech representations can reduce the amount of data needed to train a speech recognition system in a new language. The course covers topics such as the importance of low-resource speech processing, the use of multilingual features, different neural network architectures, and various use cases. The intended audience for this course is individuals interested in speech recognition, natural language processing, and machine learning.

Syllabus

Intro
Why Care About Low-Resource Speech Processing?
How Much Transcribed Audio Do We Need?
Why Do We Need All That Training Data?
Multilingual Features
The IARPA Babel Program
Babel Languages
Limited resources
What is keyword search, and why focus on it?
How do we measure keyword search performance?
Properties of term-weighted value
Take-Home Messages
Three Ways of Looking at Speech
Deep Neural Network
A Stacked DNN Architecture
Convolutional Neural Network
Considered 2 CNN Architectures
Recurrent Neural Network
Bidirectional LSTM Architecture
Three Use Cases
More Expressive Architectures Make a Big Difference
Fixed Features Allow for Rapid Development
Our partners
Babel resources