Coursera Flash Sale
40% Off Coursera Plus for 3 Months!
Grab it
Learn the fundamentals and advanced concepts of Automatic Speech Recognition (ASR) through this comprehensive 2 hour and 46 minute lecture from the JSALT 2024 Summer School hosted by the Center for Language & Speech Processing at Johns Hopkins University. Explore the core principles behind converting spoken language into text, including signal processing techniques, acoustic modeling, language modeling, and decoding algorithms. Dive into modern deep learning approaches for ASR, examining neural network architectures such as recurrent neural networks, transformers, and end-to-end models. Understand the challenges in speech recognition including handling different accents, background noise, and speaker variability. Gain insights into evaluation metrics, dataset preparation, and practical implementation considerations for building robust ASR systems. Discover current research trends and future directions in the field, including multilingual ASR, low-resource language processing, and real-time speech recognition applications.
