Image and Speech Recognition

1. R. Duda, P. Hart, D. Stork: Pattern Classification. 2nd edition, John Wiley & Sons, New York, 2001. (Chapters: 2, 3, 4, 10)
2. Christopher M. Bishop: Pattern Recognition and Machine Learning. Springer Science-Businessmedia, 2006. (Chapters: 1-5, 9, 12-14)
3. Charu C. Aggarwal: Neural Networks and Deep Learning. A Textbook. Springer International Publishing, 2018.
4. R. C. Gonzales, Woods: Digital Image Processing. Prentice Hall, 2008 (3d edition), 2018 (4th edition). (Chapters: 3-6, 9-13)
5. OpenCV - Open Source Computer Vision library - diverse image processing and analysis algorithms in C++ and Python interface. https://docs.opencv.org/master/
6. L. R. Rabiner and R. W. Schafer, Introduction to Digital Speech Processing, Foundations and Trends in Signal Processing, 2007 (Sections: 1-6, 9).
7. Kaldi - speech recognition resources. https://www.kaldi-asr.org/
8. librosa - audio processing library. https://librosa.org/doc/latest/index.html
9. T. Amaratunga: Deep Learning on Windows. Building Deep Learning Computer Vision Systems on Microsoft Windows. Springer International Publishing, 2021.
10. A. Geron: Hands on machine learning with Scikit-Learn, Keras and TensorFlow. 2nd ed.,O'Reilly Media Inc., Sebastopol, CA, 2019.
11. scikit-learn: Machine Learning in Python. https://scikit-learn.org/stable/index.html
12. KERAS - the Python Deep Learning library. https://keras.io/
13. TensorFlow - an open source machine learning library. https://www.tensorflow.org/

Knowledge

• has extended knowledge in mathematics, related to probability theory and stochastic processes, required for the understanding, description and analysis of pattern recognition systems.
• has fundamental knowledge about automatic image and speech recognition systems
• has knowledge about recent trends in the application of image and speech recognition methods.

Skills

• is able to acquire technical knowledge from literature, program repositories and program documentations;
• is able to prepare a written report from research and program development activities regarding image and speech recognition methods;
• is able to use analytic methods, simulation and experiments in order to specify and solve complex engineering tasks and basic research problems
• is able to identify and specify complex engineering tasks in the ICT domain, including non-typical tasks and their non-technical aspects, especially using techniques of DSP, pattern recognition and machine learning as applied for image and speech recognition.
• is able to evaluate the usability and performance of methods and tools applied for engineering solutions including the ability to use conceptually new methods to solve nonstandard problems with research elements – both in the domain of automatic image and speech recognition systems,

Social Competence

• is able creatively to think and to act.