Informatik 6 - Automatic Speech Recognition, WS 2009/2010

Automatic Speech Recognition, WS 2009/2010

News - Download - Schedule - Exercises - Info - Literature - Contact

News

20. October 2009

IMPORTANT: The doodle poll for the exercise date was created. Please make your choice.

29. October 2009

IMPORTANT

The lectures on Dec 15, 17, and 22, 2009, and on Jan 12, and 14, 2009 have to be cancelled due to a conference and two project workshops.

Due to an unforeseen project meeting, the lecture on Thursday, January 28, 2010 needs to be cancelled also. These lectures will be replaced by lectures on:

Fr. Nov. 20, 2009, 10:30-12:00h

Fr. Nov. 27, 2009, 10:30-12:00h

Fr. Dec. 11, 2009, 10:30-12:00h

Fr. Jan. 08, 2010, 10:30-12:00h

Mo. Feb. 01, 2010, 14:00-17:00h

in the seminar room of the I6.

Download

Here you can find the download material for the lecture. The exercise sheets as well as other documents needed for the solution of the exercises will be made available on this page.

Lecture Notes:

Lecture notes (now complete)

Exercises:

Type	Date	Download	others

The exercises should be treated in groups of 3 students.
Requirement for the issuing of certificates (Schein/Leistungsnachweis) will be that at least 50% of the exercise points are obtained.
Solutions to problems without points will be presented in the exercise lesson.

For the later exercises you will need a mathematical toolkit, for which we strongly suggest the usage of the public domain toolkit Octave (similar to MatLab). Solutions to the exercises will be given only in Octave code.

You can download Octave and its documentation here.

The RWTH Aachen University Speech Recognition System can be downloaded here.

Exercises

1. Exercise Sheet (Submission: October, 30^th 2009)

2. Exercise Sheet (Submission: November, 6^th 2009)

3. Exercise Sheet (Submission: November, 18^th 2009)

4. Exercise Sheet (Submission: November, 25^th 2009)

5. Exercise Sheet (Submission: December, 2^nd 2009)

6. Exercise Sheet (Submission: December, 16^nd 2009)

7. Exercise Sheet (Submission: January, 5^th 2010)

8. Exercise Sheet (Submission: January, 15^th 2010)

spoken.txt recognized.txt ref.dat test.dat lev_skeleton.cc

9. Exercise Sheet (Submission: January, 22^th 2010)

probe1.ascii obs.data segmentation.pdf

10. Exercise Sheet (Submission: January, 29^th 2010)

probe1.ascii obs.data segmentation.pdf

Schedule

Type	Date	Room	Start	Instructor
V3/4	Di, 11:45 - 13:15	AH 6		Dr.rer.nat. R. Schlüter, Prof. Dr.-Ing. H. Ney
	Do, 12:30 - 14:00	AH 6	16. Oct. 2009
Ü2	Mi, 17:45 - 19:15	seminar room i6	17. Oct. 2009	Nussbaum, Schlüter, Ney

info

Content:
The aim of automatic speech recognition is to extract the spoken word sequence from the acoustic signal. An automatic speech recognition system consists typically of four parts:

the signal analysis extracts time-dependent features from the acoustic signal
the acoustic model establishes a link between features and phonemes
the language model covers syntactic and semantic constraints of the language
the search process determines the word sequence that fits best to the features taking the acoustic and language model into account.

Assignment:
Applied Computer Science or Field of Specialization.

Requirements:
4 terms of university (Fachsemester), knowledge of probability theory / statistics

Language of instruction:
English

Literature

L. Rabiner, R. Schafer: "Fundamentals of Speech Recognition", Foundations and Trends® in Signal Processing: Vol. 1: No 1-2, pp 1-194, 2007. (free download)
T. Lehmann, W. Oberschelp, E. Pelikan, R. Repges: "Bildverarbeitung für die Medizin. Grundlagen, Modelle, Methoden, Anwendungen.", Springer-Verlag, Berlin, 1997.
A. V. Oppenheim, R. W. Schafer: "Discrete Time Signal Processing",Prentice Hall, Englewood Cliffs, New Jersey, 1989.
L. Rabiner, B. H. Juang: "Fundamentals of Speech Recognition", Prentice Hall, Englewood Cliffs, New Jersey, 1993.
M.Gales, S. Young: "The Application of Hidden Markov Models in Speech Recognition", Foundations and Trends® in Signal Processing: Vol. 1: No 3, pp 195-304, 2008. (free download)
W. K. Pratt: "Digital Image Processing",John Wiley and Sons, New York, NY, 1991.

Contact

Dr. Ralf Schlüter	schlueter@informatik.rwth-aachen.de	Tel. 80-21612
Markus Nussbaum-Thom	nussbaum@informatik.rwth-aachen.de	Tel. 80-21602

Office hours: by arrangement