|
|
Deep learning based sound records analysis
Kramář, Denis ; Říha, Kamil (referee) ; Přinosil, Jiří (advisor)
This master thesis deals with the problem of audio-classification of the chainsaw logging sound in natural environment using mainly convolutional neural networks. First, a theory of grafical representation of audio signal is discussed. Following part is devoted to the machine learning area. In third chapter, some of present works dealing with this problematics are given. Within the practical part, used dataset and tested neural networks are presented. Final resultes are compared by achieved accuracy and by ROC curves. The robustness of the presented solutions was tested by proposed detection program and evaluated using objective criteria.
|
|
|
Restoration of signals after passing through the limiter with the use of psychoacoustic model
Kramář, Denis ; Rajmic, Pavel (referee) ; Záviška, Pavel (advisor)
This bachelor thesis deals with the use of sparse representaions for the purpose of restoration clipping-damaged audiosignal. First, a theory of limiter and signal limiting itself is discussed. Subsequently, some of present methods based on sparse representations theory are given. The theory of sparse representations is discussed in following chapture. After that is here described a psychoacoustic model and it's use for declipping. At the end of theoretical part, two methods dealing with this problem are introduced. First is based on synthesis model of signal using Douglas-Rachford algorithm. Second is based on analysis signal model using Chambolle-Pock algorithm. In the next part is their implementation in the Matlab environment. Finally, the result achieved by both algorithms are evaluated.
|
|
|
Deep learning based sound records analysis
Kramář, Denis ; Říha, Kamil (referee) ; Přinosil, Jiří (advisor)
This master thesis deals with the problem of audio-classification of the chainsaw logging sound in natural environment using mainly convolutional neural networks. First, a theory of grafical representation of audio signal is discussed. Following part is devoted to the machine learning area. In third chapter, some of present works dealing with this problematics are given. Within the practical part, used dataset and tested neural networks are presented. Final resultes are compared by achieved accuracy and by ROC curves. The robustness of the presented solutions was tested by proposed detection program and evaluated using objective criteria.
|
|
|
Restoration of signals after passing through the limiter with the use of psychoacoustic model
Kramář, Denis ; Rajmic, Pavel (referee) ; Záviška, Pavel (advisor)
This bachelor thesis deals with the use of sparse representaions for the purpose of restoration clipping-damaged audiosignal. First, a theory of limiter and signal limiting itself is discussed. Subsequently, some of present methods based on sparse representations theory are given. The theory of sparse representations is discussed in following chapture. After that is here described a psychoacoustic model and it's use for declipping. At the end of theoretical part, two methods dealing with this problem are introduced. First is based on synthesis model of signal using Douglas-Rachford algorithm. Second is based on analysis signal model using Chambolle-Pock algorithm. In the next part is their implementation in the Matlab environment. Finally, the result achieved by both algorithms are evaluated.
|
guest ::
