TTT4185 - Machine Learning and Speech Technology


Examination arrangement

Examination arrangement: Written examination

Evaluation form Weighting Duration Examination aids Grade deviation
Written examination 100/100 4 hours C

Course content

Basic methods for statistical pattern recognition/machine learning. Deep neural networks. Design, training and evaluation of machine learning models. Digital models for production of speech. Human perception of speech and sound. Methods for speech analysis. Automatic speech recognition with emphasis on statistical methods (Hidden Markov Models): statistical methods for acoustic and linguistic modeling; principles for efficient decoding (recognition). Deep neural networks for speech recognition.

Learning outcome

The candidate has
- good understanding of the theoretical principles and practical aspects of using statistical pattern recognition/machine learning
- wide knowledge about speech, speech production and perception
- knowledge about principles and methods for speech analysis
- good knowledge about statistical modeling of speech and language
- good insight in how the basic principles can be employed to construct systems for automatic speech recognition.

The candidate can
- use and/or design software for use in train and evaluate models based on machine learning methods
- use and/or design software for speech analysis and interpret the analysis results
- design simple systems for automatic speech recognition based on statistical pattern recognition
- evaluate the performance of speech recognizers.

General competence:
The candidate can
- the insights in the interplay between basis technology and development of human-computer interfaces
- conduct teamwork and documentation

Learning methods and activities

Lectures, voluntary computer exercises.

Further on evaluation

If there is a re-sit examination, the examination form may be changed from written to oral.

Course materials

Text book will be announced at semester start.

Credit reductions

Course code Reduction From To
SIE2090 7.5


Examination arrangement: Written examination

Term Statuskode Evaluation form Weighting Examination aids Date Time Room *
Autumn ORD Written examination 100/100 C
  • * The location (room) for a written examination is published 3 days before examination date.
If more than one room is listed, you will find your room at Studentweb.