|
|
Speaker Recognition in the VoIP Environment
Remeš, Jan ; Pešán, Jan (referee) ; Plchot, Oldřich (advisor)
Tato práce popisuje použití systémů pro rozpoznávání mluvčího v~prostředí VoIP, úspěšnost systému a přístupy k jejímu zlepšení. Popisuje architekturu těchto systémů, metriky pro vyhodnocení jejich úspěšnosti a klíčové komponenty VoIP z hlediska rozpoznávání mluvčího. Je zde popsáno vytvoření simulace VoIP prostředí, úspěšnost systému je vyhodnocena na datech pocházejících z různých druhů VoIP prostředí a výsledky jsou demostrovány. Adaptace a kalibrace systému je provedena a jejich přínosy zhodnoceny.
|
|
|
Web Based Audio Editor
Myler, Jan ; Pešán, Jan (referee) ; Schwarz, Petr (advisor)
This thesis deals with the creation of simple web-based audio editor using JavaScript, HTML5 and new Web APIs for audio processing (especially the Web Audio API). The thesis describes the current state of development and implementation of APIs for audio processing in browsers. It also contains a description of the resulting application design and its implementation. In the conclusion is a summary of findings of the applications development and proposal of possible future use and expansion.
|
|
|
Adhoc VoIP for Maemo or Meego
Klapal, Tomáš ; Pešán, Jan (referee) ; Mlích, Jozef (advisor)
This bachelor thesis deals with sound capture and transfer through computer network. It also looks into design of application for voice communication on Maemo platform. First, the platform is introduced. Then, sound processing is described. Later, computer networks and their communication is presented. Existing applications are described also. Second half of this document introduces design and implementation of own application from modular point of view. Last, restrictions and enhancements are mentioned.
|
|
|
Visualization of User Pronunciations for Electronic Dictionarties
Pešán, Jan ; Chalupníček, Kamil (referee) ; Černocký, Jan (advisor)
The aim of this bachelor's work is to try to find a new way for development in learning capabilities of electronic dictionaries. There is an introduction of the main concept of learning pronunciations with visualization of phonemes in the first part. It is followed by chapter, which does a global review of methods for speech processing used in this project, e.g. HMM or Viterbi algorithm. In the third chapter, there is description of tools that we have used for implementation of the whole system. Next chapter explains more in detail technology of neural networks, used here as probability estimator. There is also a description of problem with compatibility of the used phoneme sets and in addition, it describes used phoneme models. Chapter 5 is whole about implementation of the system. There are also described scripts and tools applied for the preparation of the source data. In the next chapter, there is a user testing with screenshots. Moreover, in the last chapter I wrote a short conclusion and possible future ways for further developing of this system.
|
|
| |
|
|
Adaptation of Speaker Recognition Systems
Novotný, Ondřej ; Pešán, Jan (referee) ; Plchot, Oldřich (advisor)
In this paper, we propose techniques for adaptation of speaker recognition systems. The aim of this work is to create adaptation for Probabilistic Linear Discriminant Analysis. Special attention is given to unsupervised adaptation. Our test shows appropriate clustering techniques for speaker estimation of the identity and estimation of the number of speakers in adaptation dataset. For the test, we are using NIST and Switchboard corpora.
|
|
| |
|
|
Application of Mean Normalized Stochastic Gradient Descent for Speech Recognition
Klusáček, Jan ; Hradiš, Michal (referee) ; Pešán, Jan (advisor)
Umělé neuronové sítě jsou v posledních letech na vzestupu. Jednou z možných optimalizačních technik je mean-normalized stochastic gradient descent, který navrhli Wiesler a spol. [1]. Tato práce dále vysvětluje a zkoumá tuto metodu na problému klasifikace fonémů. Ne všechny závěry Wieslera a spol. byly potvrzeny. Mean-normalized SGD je vhodné použít pouze pokud je síť dostatečně velká, nepříliš hluboká a pracuje-li se sigmoidou jako nelineárním prvkem. V ostatních případech mean-normalized SGD mírně zhoršuje výkon neuronové sítě. Proto nemůže být doporučena jako obecná optimalizační technika. [1] Simon Wiesler, Alexander Richard, Ralf Schluter, and Hermann Ney. Mean-normalized stochastic gradient for large-scale deep learning. In Acoustics, Speech and Signal Processing (ICASSP), 2014 IEEE International Conference on, pages 180{184. IEEE, 2014.
|
|
|
Gate Unlocking by Voice
Bauer, Jan ; Pešán, Jan (referee) ; Schwarz, Petr (advisor)
The aim of this BSc. thesis is to create a device for authentication based on human voice. The solution is based on the BSAPI speech processing library developed by Phonexia. The library written in C++ was ported to the Raspberry Pi B+ device. The core functionality of the application was implemented in a Python script. The resulting solution is certainly interesting and may become a reliable security system in near future.
|
|
|
Prediction of Raining from Meteoradar
Vlček, Michael ; Pešán, Jan (referee) ; Szőke, Igor (advisor)
This thesis deals with rain prediction using information from meteoradar images and some other relevant factors through the computational model of a neural network. It focuses on exploring different prediction possibilities using this model and defining the most successful model configuration to fulfill the chosen task.
|
guest ::
