Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Explore the fundamentals of automatic speech recognition in this comprehensive lecture delivered by Brian Kingsbury in 2009 at the Center for Language & Speech Processing (CLSP) at Johns Hopkins University. Delve into the core concepts, techniques, and challenges of converting spoken language into written text. Learn about acoustic modeling, language modeling, and decoding algorithms that form the backbone of speech recognition systems. Gain insights into the historical development of ASR technology and its applications in various domains. Discover how machine learning and statistical methods are applied to improve recognition accuracy and robustness. Examine the challenges posed by different accents, background noise, and speaker variability. Understand the evaluation metrics used to assess the performance of speech recognition systems. This 1-hour and 21-minute talk provides a solid foundation for researchers, students, and professionals interested in the field of automatic speech recognition.
