|
Course Catalog 2012-2013
SGN-4507 Speech Recognition Laboratory, 3 cr |
Additional information
Suitable for postgraduate studies
Person responsible
Tuomas Virtanen
Lessons
Study type | P1 | P2 | P3 | P4 | Summer | Implementations | Lecture times and places |
|
|
|
|
|
|
|
|
Requirements
Completed project work and a report.
Principles and baselines related to teaching and learning
-
Learning outcomes
After completing this course the student will be able to do automatic speech recognition using the Cambridge Hidden Markov Model Toolkit (HTK). The student will be able to independently implement a word-based automatic speech recognition system based on HTK.
Content
Content | Core content | Complementary knowledge | Specialist knowledge |
1. | Implementation of a digit recognizer using HTK (Hidden Markov Model-toolkit). | ||
2. | Using HTK for calculation of feature vectors, language modelling, estimation of the parameters of an acoustic model using training data, evaluation of a speech recognizer. |
Evaluation criteria for the course
Completion of the project work.
Assessment scale:
Evaluation scale passed/failed will be used on the course
Study material
Type | Name | Author | ISBN | URL | Edition, availability, ... | Examination material | Language |
Book | "The HTK Book Version 3.3" | S. Young, G. Evermann, M. Gales, T. Hain, D. Kershaw, G. Moore, J. Odell, D. Ollason, D. Povey, V. Valtchev, P. Woodland | http://htk.eng.cam.ac.uk/docs/docs.shtml | English | |||
Book | HTK Book | English |
Prerequisites
Course | Mandatory/Advisable | Description |
SGN-4106 Speech Recognition | Mandatory |
Additional information about prerequisites
The course SGN-4106 Speech Recognition can be taken at the same time as SGN-4507.
Prerequisite relations (Requires logging in to POP)
Correspondence of content
Course | Corresponds course | Description |
|
|
More precise information per implementation
Implementation | Description | Methods of instruction | Implementation |