|
|
Voice Activity Detection
Břenek, Roman ; Grézl, František (referee) ; Matějka, Pavel (advisor)
This thesis describes techniques for voice activity detection in audio recordings. It is necessary to correctly classify all non-speech segments and recognize speech with noisy background. The whole process of voice activity detection (VAD) is described in this thesis, i.e. digitizing audio signal, feature extraction, training of the system, post-processing and final evaluation. There are three different systems compared within the thesis . The first one is based on phoneme recognition using neural network, the other two are variations of Gaussian Mixture Models (GMM). Each system was tested on three data sets - Tactical Speaker Identification Speech Corpus (TSID), Ham Radio (HR) and Rich Transcription Evaluation (RT05-RT07). The best results of each system are compared with the results of the third side.
|
|
|
Voice activity detection
Mitáček, Štěpán ; Pfeifer, Václav (referee) ; Míča, Ivan (advisor)
This work dreals with the comparison of different detection methods of speach from various audio recordings. In comparing it assesses not only the high of adjusted threshold during deciding, but also the size of individual segments to which the audiotape spreads. Detection of individual recordings can be various in different speakers and also if the interference noise occurs in the recording or not. Finaly it should be compared, which one of the tested methods is the most precise. .
|
|
|
Implementation of voice activity detectors using open-source libraries in C language
Mach, Václav ; Špiřík, Jan (referee) ; Míča, Ivan (advisor)
This diploma thesis discusses the issue of Voice Activity Detection. There are two types of detectors described: energetic and statistics. Their funktionality is proved in the Matlab environment. Further, the implemetation of VADs is made through C language with standard libraries and GSL open-source libraries. The realized algorithms are compared in the scope of processing time of computation, memory management and a single mathematical operations stress. Also a comparism of the processing time according to segment length was made.
|
|
|
Real-time voice command recognition system
Šíbl, Evžen ; Kiac, Martin (referee) ; Přinosil, Jiří (advisor)
The bachelor thesis deals with the development of a system for voice command recognition. The classifier of this system was created using a neural network. In this thesis you will learn about the history and problems of speech recognition. A system has been created that detects a section in a recording containing a speech signal, which then uses the classifier to decide what word from the word table it is. Three models with the same architecture but with different training data were created. These models were then compared with each other. A simple user interface was created for the resulting system.
|
|
|
Speech activity detector in digital signal processor
Kovařík, Jiří ; Mach, Václav (referee) ; Sysel, Petr (advisor)
In this diploma thesis were created voice activity detectors according to the standard ITU-T G.729 and G.723.1. The voice activity detectors were implements in the digital signal processor TMS320C6416 made by Texas Instruments. At the same time detectors were designed using by MATLAB programming language. The diploma thesis can be divided into two parts. In the theoretical section provides information on how to report detectors in the standard ITU-T G.729 and G.723.1. In the implementation part is described steps in the implementation of the detector in signal processor TMS320C6416 and there are discussed various differences compared to the documentation.
|
|
|
Identification of Speech Activity in Noisy Speech Signal
Pelikán, Martin ; Sysel, Petr (referee) ; Smékal, Zdeněk (advisor)
This paper is focused on identification of pauses in noisy speech signal and following filtering of the noise from the signal. Firstly the signal processing methods are theoretically described, then voice activity detectors and in the end noise filtering methods are described. Several voice activity detectors were created and their pause detection rate was compared.
|
|
|
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.
|
|
|
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.
|
|
|
Automatické rozpoznávání zpěvu ptáků
Břenek, Roman
This master thesis deals with methods of automatic recognition of bird species by their voices. In first, I defined the database of records and created a reference data by handmade evaluation. The next step is to find the optimal features for describing a bird singing. I use a Human Frequency cepstral Coefficients (HFCC). For the best accuracy of recognition is necessary to correctly classify a bird's vocalization from a non-vocalization segments. The VAD system is based on an algorithm k-Nearest Neighbours. The last step describes the system based on Hidden Markov Models which allows to recognize the concrete bird species from the parts of bird's singing.
|
|
|
Real-time voice command recognition system
Šíbl, Evžen ; Kiac, Martin (referee) ; Přinosil, Jiří (advisor)
The bachelor thesis deals with the development of a system for voice command recognition. The classifier of this system was created using a neural network. In this thesis you will learn about the history and problems of speech recognition. A system has been created that detects a section in a recording containing a speech signal, which then uses the classifier to decide what word from the word table it is. Three models with the same architecture but with different training data were created. These models were then compared with each other. A simple user interface was created for the resulting system.
|
guest ::
