VVZ API is not affiliated with ETH Zurich. Data might be outdated or incorrect. Please view the official ETHZ Vorlesungsverzeichnis for binding information.
Speech Processing II
Sprachverarbeitung II
Last Updated: 2026-02-05 14:55:36
Objective
More detailed knowledge about selected concepts and approaches to the problems of speech synthesis (transcription) and automatic speech recognition.
Content
Fundamentals of representation and application of linguistic knowledge: Introduction of the theory of formal languages, the Chomsky hierarchy, word analysis, finite state machines, parsing. Speech synthesis: Natural language analysis (for words and sentences), lexicon, grammar for natural language; generation of the abstract representation of pronunciation (phone sequence, accents, phrases). Additionally, the ETH text-to-speech system SVOX is discussed. Speech recognition: Speech signals are highly variable and must therefore be described by statistical means. Additionally, all available knowledge (about language, task, etc.) should be incorporated into the recognition process. The statistical approach to speech recognition (using Hidden Markov models) and efficient ways of incorporating additional knowledge are considered
Resources
Lecture Notes
yes
General Information
- Language
- German
- Frequency
- Yearly recurring
Examination
- Type
- session examination
- Mode
- oral 30 minutes
Course Components
| Type | Title | Time & Place | Hours |
|---|---|---|---|
| lecture with exercise | Sprachverarbeitung II |
|
4 h weekly |