Back to all courses

Speech recognition

Individual course

Max amount of FITech students: 20

Persons without a valid study right at a Finnish university or university of applied sciences have preference to this course.

Course contents

  • Preprocessing and feature extraction for speech phoneme models
  • Decoding
  • Lexicon and language models
  • Recognition and retrieval of continuous speech

After completing the course you will have become familiar with speech recognition methods and applications. Additionally, you will have learned to understand the structure of a typical speech recognition system and to know how to construct one in practice.

Teaching schedule

  • Lectures in Otaniemi (voluntary): Wednesdays 10:15 – 12:00 and Thursdays 10:15 – 12:00. If you are unable to attend the classes, you can ask the material from the teacher.

Completion methods

Homework assignments and group work. Compulsory group work presentation and final report. No exam.

More information on Aalto University’s course page.

You can get a digital badge after completing this course.

Responsible teacher

Aalto University
Mikko Kurimo

Further information about the studies

Aalto University
Tiina Porthén

Contact person for applications

FITech Network University
Fanny Qvickström, Student services specialist
Application period has ended
Application period has ended
Topics:
AI and machine learning,
Computer engineering
Course code:
ELEC-E5510
Study credits:
5 ECTS
Price:
0 €
Course level:
Teaching period:
25.10.–29.11.2023
Application start date:
01.06.2023
Application deadline:
Application period has ended
Host university:
Aalto University
Who can apply:
Adult learner,
Degree student
Teaching method:
Blended
Place of contact learning:
Espoo
Teaching language:
English
General prerequisites:
Basic engineering mathematics and probability consept.
Interested in this course? Subscribe and get updates about the course directly to your email. You can cancel subscription any time you want.

This course is included in the following theme