All courses
AI path Β· course 21 of 54
Speech Recognition & Synthesis
Intermediate Β· 5 lessons Β· 0 complete
Learn how spoken audio becomes text and how text becomes spoken audio, from raw sound waves and spectrograms through modern neural speech models. This is part 2 of the NLP & Language Systems track, and it assumes you already understand basic NLP concepts like tokenization and embeddings from the first course. Built for learners who want a grounded, mechanics-first understanding of speech recognition and text-to-speech, not just a list of product names.
