Speech recognition
Course will address preprocessing and feature extraction for speech phoneme models, decoding, lexicon and language models, and recognition and retrieval of continuous speech.
Schedule:
–
Teaching time:
Daytime
Topic:
Information and communications technology
Form of learning:
Online
On-campus
Provider:
Aalto University, FITech
Level:
Advanced
Credits:
5 By Aalto University (ECTS)
Fee:
€ 0.00
Application period:
1.6.2023
– 17.10.2023
Target group and prerequisites
Basic engineering mathematics and probability concept.Course description
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): on Wednesdays at 10:15–12:00 and Thursdays at 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.