FDT3119 Speech and Speaker Recognition 7.5 credits
Automatic Speech Recognition (ASR) is concerned with the problem of transcribing spoken words and phrases into text. The ASR functionality is usually integrated into a larger system that makes it possible for humans to interact with computers using natural language. From a technical point of view, the ASR problem poses a number of challenges, emerging from the need to deal with real life signals produced by different individuals and in different conditions. The solutions are usually based on statistical modeling and machine learning. This course gives insights into the signal processing and statistical methods employed in ASR and in Speaker identification.
Content and learning outcomes
Course contents
The course consists of lectures, three laboratory sessions with hand-in assignments, as well as writing a thesis in a subject chosen in consultation with the teacher. The thesis is furthermore presented orally during a final seminar. The laboratory sessions consist of designing different parts of a speech recognition application, train the system and evaluate its performance.
The following theoretical components are included:
- algorithms for training, recognition as well as adaptation to properties of speakers and transmissions channel, including pattern recognition, Hidden Markov Models (HMMs) and Deep Neural Networks (DNNs)
- methods to decrease the sensitivity against disturbances and deviations
- probability theory
- signal processing and parameter extraction
- acoustic modelling of the static and dynamic spectral properties of the speech sounds statistical modelling of language in spontaneous and formal speech
- search strategies- basic methods and strategies for large vocabularies
- specific analysis and decision making methods for recognition of speakers.
Furthermore, certain practical insight to build an application is given. Here, implementing certain functions based on prototypes and testing them on real speech data are included.
Intended learning outcomes
After completion of the course the students should be able to:
- implement training and evaluation methods for speech recognition
- train and evaluate a speech recogniser using software packages
- compare different feature extraction and training methods
- document and discuss specific aspects related to speech and speaker recognition
- with the help of the literature, review and criticise other students' work in the subject
Course disposition
12 lectures, 3 labs, final project
Literature and preparations
Specific prerequisites
Doctoral students from EECS
Recommended prerequisites
Some knowledge of Machine learning, possibly DD2421, DD2434 or EN2202
Some programming knowledge, best if Python
Some knowledge in Signal Processing
Equipment
Literature
Huang, X., Acero, A., Hon, H.-W. Spoken Language Processing - A Guide to Theory, Algorithm and System Development, Prentice Hall, 2001.
Automatic Speech Recognition: A deep learning approach, Dong Yu and Li Deng, Springer 2015. You can download the PDF through KTH Library.
Research articles in speech recognition
Examination and completion
If the course is discontinued, students may request to be examined during the following two academic years.
Grading scale
Examination
- EXA1 - Exam, 7.5 credits, grading scale: P, F
Based on recommendation from KTH’s coordinator for disabilities, the examiner will decide how to adapt an examination for students with documented disability.
The examiner may apply another examination format when re-examining individual students.
LABl - Computer Lab, 4.5, grading scale: P, F
PROl - Project, 3.0, grading scale: P, F
Other requirements for final grade
Laboratory exercises with oral presentation
Research project with written report
Opportunity to complete the requirements via supplementary examination
Opportunity to raise an approved grade via renewed examination
Examiner
Ethical approach
- All members of a group are responsible for the group's work.
- In any assessment, every student shall honestly disclose any help received and sources used.
- In an oral assessment, every student shall be able to present and answer questions about the entire assignment and solution.
Further information
Course web
Further information about the course can be found on the Course web at the link below. Information on the Course web will later be moved to this site.
Course web FDT3119Offered by
Main field of study
Education cycle
Add-on studies
Supplementary information
The course is run in parallel with DT2119. The PhD version of the course requires a larger research project to be agreed with the course responsible.