|
|
Deep learning based sound event recognition
Bajzík, Jakub ; Kiska, Tomáš (oponent) ; Přinosil, Jiří (vedoucí práce)
This paper deals with processing and recognition of events in audio signal. The work explores the possibility of using audio signal visualization and subsequent use of convolutional neural networks as a classifier for recognition in real use. Recognized audio events are gunshots placed in a sound background such as street noise, human voice, animal sounds, and other forms of random noise. Before the implementation, a large database with various parameters, especially reverberation and time positioning within the processed section, is created. In this work are used freely available platforms Keras and TensorFlow for work with neural networks.
|
|
|
Design and realization of USB sound card with a guitar and microphone preamplifier
Bajzík, Jakub ; Hanák, Pavel (oponent) ; Krajsa, Ondřej (vedoucí práce)
The term paper analyzes the available audio codecs platforms for the implementation of an external sound card with USB interface. It includes a complete design of differential microphone preamplifier with balanced input and single-ended guitar preamplifier with unbalanced input. The main circuit is completed by dual supply voltage, phantom power and signal indication. The term paper also includes a software simulation of preamplifier circuits and design of the printed circuit board. The final product was measured focusing on audio signal transfer.
|
|
|
Deep Learning Based Sound Event Recognition
Bajzík, Jakub
The main paper deals with the analysis of the methods of processing and recognition of events in the audio signal and the implementation of the selected method in real use. Recognized events are gunshots placed in a background sound such as traffic noise, human voice, animal sounds and other forms of environmental sounds. For events classification and class recognition, the freely available machine learning framework TensorFlow is used.
|
|
|
Deep learning based sound event recognition
Bajzík, Jakub ; Kiska, Tomáš (oponent) ; Přinosil, Jiří (vedoucí práce)
This paper deals with processing and recognition of events in audio signal. The work explores the possibility of using audio signal visualization and subsequent use of convolutional neural networks as a classifier for recognition in real use. Recognized audio events are gunshots placed in a sound background such as street noise, human voice, animal sounds, and other forms of random noise. Before the implementation, a large database with various parameters, especially reverberation and time positioning within the processed section, is created. In this work are used freely available platforms Keras and TensorFlow for work with neural networks.
|
|
|
Design and realization of USB sound card with a guitar and microphone preamplifier
Bajzík, Jakub ; Hanák, Pavel (oponent) ; Krajsa, Ondřej (vedoucí práce)
The term paper analyzes the available audio codecs platforms for the implementation of an external sound card with USB interface. It includes a complete design of differential microphone preamplifier with balanced input and single-ended guitar preamplifier with unbalanced input. The main circuit is completed by dual supply voltage, phantom power and signal indication. The term paper also includes a software simulation of preamplifier circuits and design of the printed circuit board. The final product was measured focusing on audio signal transfer.
|
host ::
RSS.