Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore advanced techniques in robust speech recognition through this 4-hour tutorial presentation from JSALT 2025's seventh day afternoon session. Learn from Lukáš Burget and Alex Polok as they delve into sophisticated methods for building speech recognition systems that maintain high performance under challenging conditions such as noise, accents, and varying acoustic environments. Discover state-of-the-art approaches to handling robustness challenges in automatic speech recognition, including domain adaptation techniques, noise-robust feature extraction, and advanced neural network architectures designed to improve recognition accuracy across diverse speaking conditions and environments.
