|
|
Recognition of isolated words
Ondruška, Jiří ; Švrček, Martin (referee) ; Kolářová, Jana (advisor)
Human speech recognition in biometric systems is an actual problem, which science intensively deals with. One of most used methods is the method of hidden Markovov’s models. Attention in isolated words recognition is focused on characteristic speech signal parameters obtaining, enabling most clear identification due to hiddem Markov model application. This work concentrates on biometric systems, its methods, and then is focused on isolated words recognition problems. The hidden Markov model recognition system with usage of some Matlab functions is designed. Concept focuses on characteristic speech signal parameters obtaining, code book making through vector quantization, words model training and finally probability of concrete model and obtained word similarity evaluation. Ratio for one speaker's spoken words recognition reaches 40%.
|
|
|
Speech segmentation
Andrla, Petr ; Míča, Ivan (referee) ; Sysel, Petr (advisor)
The programme for the segmentation of a speech into fonems was created as a part of the master´s thesis. This programme was made in the programme Matlab and consists of several scripts. The programme serves for automatic segmentation. Speech segmentation is the process of identifying the boundaries between phonemes in spoken natural languages. Automatic segmentation is based on vector quantization. In the first step of algorithm, feature extraction is realized. Then speech segments are assigned to calculated centroids. Position where centroid is changed is marked as a boundary of phoneme. The audiorecords were elaborated by the programme and a operation of the automatic segmentation was analysed. A detailed manual was created to the programme too. Individual used methods of the elaboration of a speech were in the master´s thesis briefly descripted, its implementations in the programme and reasons of set of its parameters.
|
|
|
Identification of persons via voice imprint
Mekyska, Jiří ; Atassi, Hicham (referee) ; Smékal, Zdeněk (advisor)
This work deals with the text-dependent speaker recognition in systems, where just a few training samples exist. For the purpose of this recognition, the voice imprint based on different features (e.g. MFCC, PLP, ACW etc.) is proposed. At the beginning, there is described the way, how the speech signal is produced. Some speech characteristics important for speaker recognition are also mentioned. The next part of work deals with the speech signal analysis. There is mentioned the preprocessing and also the feature extraction methods. The following part describes the process of speaker recognition and mentions the evaluation of the used methods: speaker identification and verification. Last theoretically based part of work deals with the classifiers which are suitable for the text-dependent recognition. The classifiers based on fractional distances, dynamic time warping, dispersion matching and vector quantization are mentioned. This work continues by design and realization of system, which evaluates all described classifiers for voice imprint based on different features.
|
|
|
Static image compression techniques
Jirounek, Matěj ; Šmirg, Ondřej (referee) ; Krajsa, Ondřej (advisor)
Bachelor’s thesis dissert on nowadays used compression technologies static image, about their keystones, advantages and disadvantages in field of application and their reciprocal comparison. Work is divided to the seven capitols, second of which handles indicative allocation data compression, third about lossless compression and their main representative and fourth chapter is about less compression picture with her advantages and disadvantages as well as about colour models. In fifth chapter there are summarized used criteria for classification picture and in sixth chapter is shownd implementation programme in environment MATLAB.
|
|
|
Static image compression techniques
Jirounek, Matěj ; Šmirg, Ondřej (referee) ; Krajsa, Ondřej (advisor)
Bachelor’s thesis dissert on nowadays used compression technologies static image, about their keystones, advantages and disadvantages in field of application and their reciprocal comparison. Work is divided to the seven capitols, second of which handles indicative allocation data compression, third about lossless compression and their main representative and fourth chapter is about less compression picture with her advantages and disadvantages as well as about colour models. In fifth chapter there are summarized used criteria for classification picture and in sixth chapter is shownd implementation programme in environment MATLAB.
|
|
|
Speech segmentation
Andrla, Petr ; Míča, Ivan (referee) ; Sysel, Petr (advisor)
The programme for the segmentation of a speech into fonems was created as a part of the master´s thesis. This programme was made in the programme Matlab and consists of several scripts. The programme serves for automatic segmentation. Speech segmentation is the process of identifying the boundaries between phonemes in spoken natural languages. Automatic segmentation is based on vector quantization. In the first step of algorithm, feature extraction is realized. Then speech segments are assigned to calculated centroids. Position where centroid is changed is marked as a boundary of phoneme. The audiorecords were elaborated by the programme and a operation of the automatic segmentation was analysed. A detailed manual was created to the programme too. Individual used methods of the elaboration of a speech were in the master´s thesis briefly descripted, its implementations in the programme and reasons of set of its parameters.
|
|
|
Identification of persons via voice imprint
Mekyska, Jiří ; Atassi, Hicham (referee) ; Smékal, Zdeněk (advisor)
This work deals with the text-dependent speaker recognition in systems, where just a few training samples exist. For the purpose of this recognition, the voice imprint based on different features (e.g. MFCC, PLP, ACW etc.) is proposed. At the beginning, there is described the way, how the speech signal is produced. Some speech characteristics important for speaker recognition are also mentioned. The next part of work deals with the speech signal analysis. There is mentioned the preprocessing and also the feature extraction methods. The following part describes the process of speaker recognition and mentions the evaluation of the used methods: speaker identification and verification. Last theoretically based part of work deals with the classifiers which are suitable for the text-dependent recognition. The classifiers based on fractional distances, dynamic time warping, dispersion matching and vector quantization are mentioned. This work continues by design and realization of system, which evaluates all described classifiers for voice imprint based on different features.
|
|
|
Recognition of isolated words
Ondruška, Jiří ; Švrček, Martin (referee) ; Kolářová, Jana (advisor)
Human speech recognition in biometric systems is an actual problem, which science intensively deals with. One of most used methods is the method of hidden Markovov’s models. Attention in isolated words recognition is focused on characteristic speech signal parameters obtaining, enabling most clear identification due to hiddem Markov model application. This work concentrates on biometric systems, its methods, and then is focused on isolated words recognition problems. The hidden Markov model recognition system with usage of some Matlab functions is designed. Concept focuses on characteristic speech signal parameters obtaining, code book making through vector quantization, words model training and finally probability of concrete model and obtained word similarity evaluation. Ratio for one speaker's spoken words recognition reaches 40%.
|
|
|
Komprese dvousměrných texturních dat založaná na víceůrovňové vektorové kvantizaci - doplňkový materiál
Havran, V. ; Filip, Jiří ; Myszkowski, K.
The Bidirectional Texture Function (BTF) is becoming widely used for accurate representation of real-world material appearance. In this paper a novel BTF compression model is proposed. The model resamples input BTF data into a parametrization, allowing decomposition of individual view and illumination dependent texels into a set of multidimensional conditional probability density functions. These functions are compressed in turn using a novel multi-level vector quantization algorithm. The result of this algorithm is a set of index and scale code-books for individual dimensions. BTF reconstruction from the model is then based on fast chained indexing into the nested stored code-books. In the proposed model, luminance and chromaticity are treated separately to achieve further compression. The proposed model achieves low distortion and compression ratios 1:233-1:2040, depending on BTF sample variability.
|
|
| |
guest ::
