The goal of automatic speech recognition (ASR) is to map a spoken utterance, i.e. an acoustic speech signal, to an orthographic representation.
The lecture provides an introduction to signal processing methods based on acoustic and articulatory phonetic insights. The focus will be on Hidden-Markov-Models (HMMs) and associated algorithms. In detail, algorithms for parameter estimation and decoding will be presented, as well as for signal processing. The rich modeling space will be discussed with a range of standard variants.
* Schukat-Talamazzini, E.-G.: Automatische Spracherkennung, Vieweg, Wiesbaden, 1995.
* Huang, X., Acero, A., Hon, H-W.: Spoken Language Processing: A Guide to Theory, Algorithm, and System Development, Prentice Hall, Upper Saddle River, NJ, 2001.
* Clark & Yallop: Introduction to Phonetics and Phonology, 2007. url: tocs.ulb.tu-darmstadt.de/178080047.pdf
Frequency | Weekday | Time | Format / Place | Period |
---|
Module | Course | Requirements | |
---|---|---|---|
39-M-Inf-SSV Sprachsignalverarbeitung | Anwendungsorientierte Sprachverarbeitung | Student information | |
Spracherkennung | Graded examination
|
Student information |
The binding module descriptions contain further information, including specifications on the "types of assignments" students need to complete. In cases where a module description mentions more than one kind of assignment, the respective member of the teaching staff will decide which task(s) they assign the students.
Degree programme/academic programme | Validity | Variant | Subdivision | Status | Semester | LP | |
---|---|---|---|---|---|---|---|
Linguistik: Kommunikation, Kognition und Sprachtechnologie / Master | (Enrollment until WiSe 19/20) | 39-Inf-MaLinMSV | 4 |
A corresponding course offer for this course already exists in the e-learning system. Teaching staff can store materials relating to teaching courses there: