National Repository of Grey Literature 47 records found  1 - 10nextend  jump to record: Search took 0.01 seconds. 
Enhancement of degraded speech by removing dissonant components
Sadil, Jiří ; Míča, Ivan (referee) ; Smékal, Zdeněk (advisor)
This work deals with the method of partial removal of interference from the speech signal, thereby improving the overall quality of depreciated speech signal and improve signal-to-noise ratio. Specifically, the elimination of frequent disturbance, such as crosstalk from other interviews, noise, car noise, computer fans wind coming to the microphone and general noise. The method described below is based on frequency filtering, which can be thought of as the discordant tones of intervals. The size range of discordant phenomena, be applied to the basic tone of speech, which can be thought of as a tone tempered tuning C, and thus a spectrum of dissonant speech appear as notes F #, B, and C #. The aim of my work is finding its own working methods and technical solutions for realization of removing the greatest proportion of interfering components in the signal deteriorated by filtration discordant elements.
System for speaker diarization
Bradáč, Josef ; Atassi, Hicham (referee) ; Míča, Ivan (advisor)
Speaker diarization system has wide application in the field of processing and analysis speech signals. This work is broken down to introduction and follow for designing the system. Result of this work is an implementation of the system itself and its evaluation based on interview´s database.
Methods for detecting acoustic sources using microphone arrays
Durkoš, Michal ; Rampl, Ivan (referee) ; Míča, Ivan (advisor)
his paper denotes various possibilities of localization of sources of acoustic signals. It informs the reader about possibilities of using beamforming and it´s basic conditions and rules. In detail it denotes delay-and-sum beamforming, which can be used for both localization of signal sources and for improving the signal by extending signal-to-noise ratio. In the last part of this paper process of simulation of incidence of sound signal on the microphone array is shown, experimental measures are noted and so is their evaluation.
Acoustic Power Measurement Using Acoustic Intensity Probe
Bílek, Ondřej ; Míča, Ivan (referee) ; Schimmel, Jiří (advisor)
This bachelor thesis focuses on the problematics of measuring acoustic power using intensity probe by two different methods - scanning method and measuring in points. Values of accustic microphone pressures, collected during the measurement, are going to be processed in MATLAB computing environment.
Localization acoustic near-field sources
Šuránek, David ; Sysel, Petr (referee) ; Míča, Ivan (advisor)
This thesis is focused on acoustic source localization in near field situation. First part of this thesis is dedicated to examining the fundamental issues of acoustic source localization. After that are some of acoustic source localization methods described. Next part is focused on implementation, verification of functionality, comparing of the successfulness and results of the localization. In conclusion are summarized the outcomes of the thesis.
Assessment of speech signal quality
Tuleja, Peter ; Balík, Miroslav (referee) ; Míča, Ivan (advisor)
This paper discusses methods for evaluating the quality of the speech signal. Briefly describe the subjective methods for determining the quality of the speech signal. From subjective methods the pair-wise comparison and MOS score are presented. Objective intrusive methods are described in more detailed way - namely methods of the segmental SNR evaluated in time domain, method of the segmental SNR evaluated in the frequency domain and frame normalization method which uses LSE based estimator. At the end of this paper is described an experiment, in which the aforementioned methods are compared and than statistically evaluated.
Database of recordings for detection of voice activity
Pelikán, Pavel ; Hudec, Antonín (referee) ; Míča, Ivan (advisor)
This thesis deals with voice activity detection (VAD) and requirements for creating a speech database. One of the existing tools for marking recordings was chosen. On the basis of the gained knowledge, database of isolated words, sentences, text and spontaneous speech was created. The practical part consists of a detailed description of database and mark creation. Furthermore, the thesis deals with the conversion of marks into Matlab. There are also some auxiliary scripts for operations with marks. Prepared and a database was created in an anechoic chamber and includes recordings from 16 speakers.
Smart home with single board computer
Piro, Šimon ; Míča, Ivan (referee) ; Koutný, Martin (advisor)
This thesis describes the issue of smart homes, reviews of current solutions, design simpler and less financially demanding solutions, the selection of the control unit in the form of single board computer based on an embedded Linux OS, realization of graphical user application for touch screen, implementing remote access via HTTP webpage, proposal of peripheral unit with integrated microprocessor.
Optimized Voice Activity Detection under Varying Environments
Míča, Ivan ; Přibil, Jiří (referee) ; Vích, Robert (referee) ; Smékal, Zdeněk (advisor)
This thesis deals with the issue of algorithmic voice activity detection. Impacts of adverse conditions on the reliability of detection is analysed, and main historical and up-to-date approaches to this issue are discussed. Simulations on both synthetic, and application specific labeled speech databases are used to support the theoretical analysis of important VAD methods. Based on the theoretical analysis together with the performance results, an optimization is proposed that is capable to overcome some limitations of the current methods when dealing with variable working conditions.}
Very limited Vocabulary Speech Recognizer
Vystavěl, Kamil ; Míča, Ivan (referee) ; Sysel, Petr (advisor)
This bachelor thesis deals with the implementation of voice diagnostic method with limited number of recognized words in Matlab environment. Recognizer is designed for recognition of isolated words and is based on the dynamic programming method. This method is realized by the dynamic time warping algorithm (DTW). Features of the speech signal are calculated by methods of short-term analysis in time and frequency domain and by methods that are based on cepstral analysis and linear predictive analysis. The representation of the word, which is generated from its features, is suitable for quantifying the degree of similarity with the representation of another word. In order to achieve the highest degree of similarity, the dynamic time warping algorithm eliminates influence of fluctuation of the speech rate by non-linear normalization time axis of one of the compared words. The degree of the similarity of the two compared words is enumerated as the words’ distance. The representations of known words are stored in a word-book. The unknown word is compared with all words in the word-book and recognizer calculates distances between every known word and the unknown word. The unknown word is defined as identical with the known word that has the shortest distance to the unknown word. The successfulness depends mainly on the choice of the features.

National Repository of Grey Literature : 47 records found   1 - 10nextend  jump to record:
Interested in being notified about new results for this query?
Subscribe to the RSS feed.