Universität Wien
Achtung! Das Lehrangebot ist noch nicht vollständig und wird bis Semesterbeginn laufend ergänzt.

340212 VU Speech Technologies (2023S)

6.00 ECTS (3.00 SWS), SPL 34 - Translationswissenschaft
Prüfungsimmanente Lehrveranstaltung

An/Abmeldung

Hinweis: Ihr Anmeldezeitpunkt innerhalb der Frist hat keine Auswirkungen auf die Platzvergabe (kein "first come, first served").

Details

max. 40 Teilnehmer*innen
Sprache: Englisch

Lehrende

Termine (iCal) - nächster Termin ist mit N markiert

  • Dienstag 07.03. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 21.03. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 28.03. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 18.04. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 02.05. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 16.05. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 23.05. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 06.06. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG
  • Dienstag 13.06. 16:45 - 20:00 Hybride Lehre
    Hörsaal 6 Franz-Klein-Gasse 1 EG

Information

Ziele, Inhalte und Methode der Lehrveranstaltung

Our goal is to provide the students with a comprehensive understanding of the field of speech technolo-gies, which has undergone significant innovation in recent years. Speech technologies enable computers to process and interact with human speech and have a wide range of applications in areas such as lin-guistics, translation, natural language processing, and human-computer interaction. The course will cov-er the basics of automatic speech recognition (ASR) systems, the use of neural networks in speech tech-nologies, the principles of dialogue systems, and practical skills for building and deploying ASR and speech-to-speech systems.
Through a mix of lectures, demonstrations, and hands-on exercises, the course will introduce the students to the fundamental concepts and techniques of speech technologies and will encourage them to apply their knowledge to real-world problems and projects with the help of the acquired knowledge in class. Guest lectures from experts in different fields will provide the students with diverse perspectives on the applications and implications of speech technologies as well as future career opportunities.
The course will not only provide the students with the skills and knowledge needed to work with speech technologies but will also foster critical thinking and creative problem-solving skills, which are essential in this rapidly evolving field. As such, we think, that it is a fundamental course for students interested in pursuing careers in speech technologies, linguistics, translation, or related fields.

Art der Leistungskontrolle und erlaubte Hilfsmittel

Participation,
input presentations
programming / written assignments

Mindestanforderungen und Beurteilungsmaßstab

regular participation, positive completion of all partial performances

Prüfungsstoff

Literatur

- Jurafsky, Dan / Martin, James H. (7.1.2023): Speech and Language Processing. 3rd ed. draft: https://web.stanford.edu/~jurafsky/slp3/ .
- Rabiner, Lawrence / Juang, Biing-Hwang (1993): Fundamentals of Speech Recognition. PTR Prentice Hall.
- Nielsen, Michael (2019): Neural Networks and Deep Learning: http://neuralnetworksanddeeplearning.com/ .

Zuordnung im Vorlesungsverzeichnis

Letzte Änderung: Do 11.05.2023 11:28