Automatic Speech Recognition, WS 2009/2010

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


20. October 2009

29. October 2009


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)

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.


  • 1. Exercise Sheet (Submission: October, 30th 2009)  
  • 2. Exercise Sheet (Submission: November, 6th 2009)  
  • 3. Exercise Sheet (Submission: November, 18th 2009)  
  • 4. Exercise Sheet (Submission: November, 25th 2009)  
  • 5. Exercise Sheet (Submission: December, 2nd 2009)  
  • 6. Exercise Sheet (Submission: December, 16nd 2009)  
  • 7. Exercise Sheet (Submission: January, 5th 2010)  
  • 8. Exercise Sheet (Submission: January, 15th 2010)   spoken.txt recognized.txt ref.dat test.dat
  • 9. Exercise Sheet (Submission: January, 22th 2010)   probe1.ascii segmentation.pdf
  • 10. Exercise Sheet (Submission: January, 29th 2010)   probe1.ascii 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


    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:

    Applied Computer Science or Field of Specialization.

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

    Language of instruction:



    Dr. Ralf Schlüter Tel. 80-21612
    Markus Nussbaum-Thom Tel. 80-21602

    Office hours: by arrangement

    Oct 2008