Neural Networks for Speech Recognition - From Basic Structures to Piled Higher and Deeper Architectures
Center for Language & Speech Processing(CLSP), JHU via YouTube
AI, Data Science & Cloud Certificates from Google, IBM & Meta
2,000+ Free Courses with Certificates: Coding, AI, SQL, and More
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore the evolution and application of neural networks in speech recognition technology through this comprehensive lecture that covers fundamental architectures and advanced "piled" structures. Learn about the basic building blocks of neural networks used for speech processing, understand how these systems have developed over time, and discover sophisticated layered approaches that enhance recognition accuracy. Examine the theoretical foundations behind neural network design for speech applications, analyze different structural configurations, and gain insights into the practical implementation challenges and solutions in speech recognition systems. Delve into the progression from simple neural network models to more complex, stacked architectures that improve performance in real-world speech processing tasks.
Syllabus
2013 09 20 Nelson Morgan - Neural Networks for Speech Recognition: From Basic Structures to Piled...
Taught by
Center for Language & Speech Processing(CLSP), JHU