CS224S: Spoken Language Processing
Stanford's spoken language course, with public lecture slides and readings covering speech recognition, speech synthesis and spoken dialog systems.
About CS224S: Spoken Language Processing
The course introduces spoken language technology with an emphasis on dialog and conversational systems, covering deep learning for automatic speech recognition, speech synthesis, affect detection and dialogue management. The Spring 2025 syllabus links slide PDFs for lectures 1 to 15, on topics such as phonetics, TTS with deep learning, HMM-DNN systems, CTC and end-to-end ASR, and Whisper. Most readings link to free online PDFs, including the Jurafsky and Martin textbook draft. Lecture videos are only available to registered Stanford students.
Who can apply
Proficiency in Python, plus foundations of machine learning and NLP (e.g. CS 124, CS 129, CS 221, CS 224N or CS 229, or equivalent).
How to get it
- Open the Spring 2025 syllabus on the course site.
- Read the slides and linked readings lecture by lecture.
- Try the homework topics listed on the assignments page.
CS224S: Spoken Language Processing — FAQ
Who can apply for CS224S: Spoken Language Processing?+
Proficiency in Python, plus foundations of machine learning and NLP (e.g. CS 124, CS 129, CS 221, CS 224N or CS 229, or equivalent).
How do I get CS224S: Spoken Language Processing?+
1. Open the Spring 2025 syllabus on the course site. 2. Read the slides and linked readings lecture by lecture. 3. Try the homework topics listed on the assignments page.
Is CS224S: Spoken Language Processing free?+
Yes — CS224S: Spoken Language Processing is free to take. Lecture slides online.