|
|
Automatic speech recordings segmentation tool
Santa, Roman ; Zvončák, Vojtěch (oponent) ; Kováč, Daniel (vedoucí práce)
Automatic Segmentation tool processes recordings in order to extract voiced parts. It is important for further speech analysis to work only with extracted speech and not noise. For analysis of the difference between syllables of patients with parkinson disease and heatlhy ones, this segmentation tool should help with processing recordings. Goal of this thesis is to implement and test voice detectors with Google WebRTC detector and pick the best speech detector with minimal error rate. Also, develop a segmentation tool for given recordings and test voice recognition with dymanic time warping. Database from the Brain Diseases Analysis Laboratory was used. It contains czech and hungarian recordings with equal number of male and female as well as heathy and diseased patients. Energy detector performed as the best detetor in the tests. There was no significant difference in error rates between male and female or healthy and diseased patients. Recordings with lower Signal-to-Noise ratio were harder to process with an error rate starting at 12\%. Based on the results, new detector for the segmentation tool was proposed to process examined recordings. Finally, dynamic time warping algorithm was tested with mel frequency cepstral coefficients to recognize similarities between speakers.
|
|
|
Implementation and Evaluation of the LTE Cat-M Technology Using the Network Simulator 3
Santa, Roman ; Komosný, Dan (oponent) ; Mašek, Pavel (vedoucí práce)
This master's thesis contains theoretical introduction to LTE Cat-M technology. Next-generation mobile systems are mentioned in first chapter with an emphasis on 5G cellular IoT technologies. Second chapter describes mMTC from 3GPP standardization standpoint, IoT communication scenarios, and also includes comparison of LPWA technologies. LTE for Machines is a part of third chapter, with technology overview and physical resources. Simulation environment and used modules are reviewed in the fourth chapter. The simulation results are gathered at the end of fourth chapter. Including testing different number of devices connected and energy consumption with PSM and eDRX.
|
|
|
Automatic speech recordings segmentation tool
Santa, Roman ; Zvončák, Vojtěch (oponent) ; Kováč, Daniel (vedoucí práce)
Automatic Segmentation tool processes recordings in order to extract voiced parts. It is important for further speech analysis to work only with extracted speech and not noise. For analysis of the difference between syllables of patients with parkinson disease and heatlhy ones, this segmentation tool should help with processing recordings. Goal of this thesis is to implement and test voice detectors with Google WebRTC detector and pick the best speech detector with minimal error rate. Also, develop a segmentation tool for given recordings and test voice recognition with dymanic time warping. Database from the Brain Diseases Analysis Laboratory was used. It contains czech and hungarian recordings with equal number of male and female as well as heathy and diseased patients. Energy detector performed as the best detetor in the tests. There was no significant difference in error rates between male and female or healthy and diseased patients. Recordings with lower Signal-to-Noise ratio were harder to process with an error rate starting at 12\%. Based on the results, new detector for the segmentation tool was proposed to process examined recordings. Finally, dynamic time warping algorithm was tested with mel frequency cepstral coefficients to recognize similarities between speakers.
|
host ::
RSS.