Coursera Spring Sale
40% Off Coursera Plus Annual!
Grab it
Explore the evolution of speech recognition technology in this comprehensive lecture from the JSALT Summer School, delivered by Petr Schwarz from Brno University of Technology. Trace the development of speech recognizers from traditional componental HMM/GMM architectures to modern sequence-to-sequence end-to-end trained neural network architectures. Learn from an expert with over 20 years of speech recognition research experience who developed commercial speech recognition technology for Phonexia and contributed to the Kaldi toolkit. Gain insights into the historical progression and technical foundations that shaped current speech recognition systems, presented by a researcher who has worked on numerous national, EU, and US research projects and participated in international technology evaluation campaigns organized by NIST. Discover how speech recognition technology has transformed from statistical models to deep learning approaches, with practical perspectives from someone who has bridged academic research and commercial applications in voice biometry, speech transcription, keyword spotting, and language identification.
