Back
Course 2 of 4: Applied Artificial Intelligence – Speech Recognition Systems
This course is part of the Advanced and Applied AI on Microsoft Azure QLMExpertFastTrack
Applied Artificial Intelligence: Speech Recognition Systems
Understand Automatic Speech Recognition (ASR) systems using Python and AI technology.
Duration
– 3 weeks
– Weekly study: 5 hours
Course 2 of 4
Find out more
Accreditation
Available
More info
Explore AI-Powered Technology
This course is part of the Advanced and Applied AI on Microsoft Azure QLMExpertFastTrack, designed to enhance your AI and machine learning skills and prepare you for relevant Microsoft microcredentials.
Learn the essential components of modern Automatic Speech Recognition (ASR) systems. You will then apply this knowledge by building your own speech recognition system using Python, a powerful language in AI and data science.
Delve into Automatic Speech Recognition
When a person speaks, their voice creates time-varying patterns of sounds and pressure waves that travel through the air.
In this course, you will learn how these sounds are captured by sensors, converted into a sequence of numbers, and transformed into a textual representation by an ASR system.
Explore the components and underlying theory of speech recognition.
Build Your Own Speech Recognition System
Discover the various models and challenges in designing Speech Recognition Systems as you construct your own. This hands-on approach will help you understand speech decoding components and techniques like Advanced Acoustic Modelling.
In each lab session, you will build a different functioning block of the system. By the end of the course, you will have created a speech recognition system almost entirely with Python code, a versatile tool for data science.
What Topics Will You Cover?
– Fundamental Theory of Speech Recognition
– Background and Theory of Speech Recognition
– Models and Problems in Designing Speech Recognition Systems
– Deep Neural Network Acoustic Models
– Vocabulary and Techniques in Language Modelling
– Components of Speech Decoding
– Advanced Acoustic Modelling Techniques
Prove You're Job Ready
Showcase your new, job-relevant skills with an industry-specific digital certificate, plus one for every course within your QLMExpertFastTrack.
– Stay up-to-date with the latest in your field.
– Complete each course and pass assessments.
– Receive certificates validated by the educating organisation.
– Impress employers with learning outcomes for your CV.
– Achieve your career aspirations.
Accreditation
Microsoft: This course is accredited by Microsoft.
Learning on This Course
Engage with fellow learners, share ideas, and participate in active discussions in the comments throughout the course.
What Will You Achieve?
By the end of the course, you will be able to:
– Understand the fundamentals of Speech Recognition
– Apply basic signal processing for Speech Recognition
– Perform acoustic modelling and labelling
– Use common algorithms for Language Modelling
– Decode acoustic features into speech
Who Is the Course For?
This course is aimed at anyone with a background in data analysis and experience in creating machine learning models. It is beneficial for:
– Data Analysts
– Machine Learning Engineers
– Deep Learning Engineers
– Other professionals involved in AI-based technology development
Course Development
QLM has partnered with leading global technology companies to deliver cutting-edge digital skills training for the modern workplace.
Course 2 of 4