Website
Module guide

Modul CS5260-KP04, CS5260SJ14

Speech and Audio Signal Processing (SprachAu14)

Duration:


1 Semester
Turnus of offer:


every second semester
Credit points:


4
Course of studies, specific field and terms:
  • Master CLS 2023 (optional subject), Elective, Arbitrary semester
  • Master Robotics and Autonomous Systems 2019 (optional subject), Elective, Arbitrary semester
  • Master MES 2020 (optional subject), medical engineering science, Arbitrary semester
  • Master Media Informatics 2020 (optional subject), computer science, Arbitrary semester
  • Master Medical Informatics 2019 (optional subject), Medical Data Science / Artificial Intelligence, 1st or 2nd semester
  • Master MES 2014 (optional subject), medical engineering science, Arbitrary semester
  • Master CLS 2010 (optional suject), computer science, Arbitrary semester
  • Master Medical Informatics 2014 (optional subject), computer science, 1st or 2nd semester
  • Master Media Informatics 2014 (optional subject), computer science, Arbitrary semester
Classes and lectures:
  • Speech and Audio Signal Processing (exercise, 1 SWS)
  • Speech and Audio Signal Processing (lecture, 2 SWS)
Workload:
  • 20 Hours exam preparation
  • 45 Hours in-classroom work
  • 55 Hours private studies
Contents of teaching:
  • Speech production and human hearing
  • Physical models of the auditory System
  • Dynamic compression
  • Spectral analysis: Spectrum and cepstrum
  • Spectral perception and masking
  • Vocal tract models
  • Linear prediction
  • Coding in time and frequency domains
  • Speech synthesis
  • Noise reduction and echo compensation
  • Source localization and spatial reproduction
  • Basics of automatic speech recognition
Qualification-goals/Competencies:
  • Students are able to describe the basics of human speech production and the corresponding mathematical models.
  • They are able to describe the process of human auditory perception and the corresponding signal processing tools for mimicing auditory perception.
  • They are able to present basic knowledge of statistical speech modeling and automatic speech recognition.
  • They can describe and use signal processing methods for source separation and room-acoustic measurements.
Grading through:
  • Written or oral exam as announced by the examiner
Responsible for this module:
  • Prof. Dr.-Ing. Markus Kallinger
Teachers:
  • Prof. Dr.-Ing. Markus Kallinger
Literature:
  • L. Rabiner, B.-H. Juang: Fundamentals of Speech Recognition - Upper Saddle River: Prentice Hall 1993
  • J. O. Heller, J. L. Hansen, J. G. Proakis: Discrete-Time Processing of Speech Signals - IEEE Press
Language:
  • offered only in German
Notes:

Prerequisites for attending the module:
- None

Prerequisites for the exam:
- Successful completion of assignments during the semester.

Modul exam:
- CS5260-L1: Speech and Audio Signal Processing, written or oral exam, 100% of modul grade

Mentioned in SGO MML under CS5260 (without SJ14).

Letzte Änderung:
8.3.2024