|
|
Recognition of Isolated Words for Electronic Dictionaries
Hrdlička, Pavel ; Szőke, Igor (referee) ; Grézl, František (advisor)
This work is concerned with creation of isolated word recognizer for electronic dictionaires, testing its functionality on data sample and improvement by normalisation and speaker adaptation techniques. Word recognizer is built on HTK (Hidden Markov Model Toolkit). At the beginning of this document, the main aims of the work are set. In the next chapter is theoretical analysis, which describes process of recognition of isolated words with hidden Markov models. Next chapter specifies the speech data, which were used for testing. Other resources for building recognizer, like models, dictionary and grammar are described in next chapter. Before creation of recognizer, it was necessary to solve conversion between the phonemes set which was used in dictionary and set, which uses the recognizer. The recognizer was built with 8~kHz models first, than 16~kHz models were also used. Normalisation and speaker adaptation techniques were used. Obtained data were processed and results are analyzed in separate chapter. Finally is discussed, if the goals of the work were reached and what are the next steps of application development.
|
|
|
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.
|
|
|
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.
|
|
|
Speech segmentation into phonemes
Andrla, Petr ; Balík, Miroslav (referee) ; Sysel, Petr (advisor)
The programme for the segmentation of a speech into fonems was created as a part of the bachelor´s thesis. This programme was made in the programme Matlab and consists of several scripts. The programme serves for automatic and hand segmentation. Automatic segmentation is based on the method of following symptom. 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 bachelor´s thesis briefly descripted, its implementations in the programme and reasons of set of its parameters.
|
|
|
Text Dependent Speaker Verification
Fux, Jan ; Glembek, Ondřej (referee) ; Matějka, Pavel (advisor)
The goal of this Bachelor's thesis was to design text dependent speaker recognition system. There were few systems tested for MIT database. This database contains recordings of 0.46s average length. Best case for recognition is to use a combination of DTW system using posterior probability estimation (posteriograms) as an output of Phoneme recognizer and acoustic SID system based on iVectors and PLDA (Probabilistic Linear Component Analysis). Fusion with Neural network gives the best results (EER). These are 17.84% EER for women and 16.38% for men. It's 49.9% relative improvement for women and 54.2% for men against acoustic recognition alone.
|
|
|
Keyword Detection in Speech Data
Pfeifer, Václav ; Makáň, Florian (referee) ; Dostál, Otto (referee) ; Balík, Miroslav (advisor)
Speech processing systems have been developed for many years but the integration into devices had started with the deployment of the modern powerful computational systems. This dissertation thesis deals with development of the keyword detection system in speech data. The proposed detection system is based on the Large Margin and Kernel methods and the key part of the system is phoneme classifier. Two hierarchical frame-based classifiers have been proposed -- linear and non-linear. An efficient training algorithm for each of the proposed classifier have been introduced. Simultaneously, classifier based on the Gaussian Mixture Models with the implementation of the hierarchical structure have been proposed. An important part of the detection system is feature extraction and therefor all algorithms were evaluated on the current most common feature techniques. A part of the thesis technical solution was implementation of the keyword detection system in MATLAB and design of the hierarchical phoneme structure for Czech language. All of the proposed algorithms were evaluated for Czech and English language over the DBRS and TIMIT speech corpus.
|
|
|
Hybrid Recognizer of Isoladed Words
Veselý, Karel ; Černocký, Jan (referee) ; Grézl, František (advisor)
The speaker independent isolated words recignizer has various practical applications. For example it can be used to control home gadgets by PC. Even more interesting is possibility that it can be built in the user interface of any application or even into operating system to perform command based control such as invocation of applications, or execution of any other specific action. The most remarkable application of isolated recognition is in electronical dictionaries. A voice controlled word lookup could be new feature of the next generation dictionaries. Very useful is the ability to ouptut ordered list of the most likely words, which gives the user ability to learn and distinguish similar words.
|
|
|
Phonetic realization of coda /t/ in current Southern British English pronunciation
Bocková, Barbora ; Skarnitzl, Radek (advisor) ; Luef, Eva Maria (referee)
The phoneme /t/ is known for featuring a wide variety of realizations in speech throughout the English-speaking world. Its realization is conditioned both by linguistic factors, such as phonetic environment or stress, and by social factors, such as region, sex, or socioeconomic background. The present bachelor thesis aims to explore and analyse the manifestations of coda /t/ in current Southern British English pronunciation. The theoretical section includes a general description of stops in world languages and an overview of various realizations of /t/ in varieties of English and recent pronunciation developments in standard British English. In the empirical part, recordings of 16 speakers of Southern British English from political radio debates were collected and processed. An auditory analysis of the phonetic realization of the target consonants was conducted and subsequently, the occurrence of individual variants was evaluated in terms of segmental, prosodic as well as semantic context. The results confirm that stress, the word's position within a phrase, its segmental environment and semantic status, and the speaker's sex all have an influence on the realization of /t/ in speech. Furthermore, the thesis documents the recent development of the sociolinguistic status of glottalling, which has...
|
|
|
Minimal pairs in Czech sign language
Silovská, Zuzana ; Richterová, Klára (advisor) ; Macurová, Alena (referee)
This thesis research focuses on the minimal pairs in the Czech sign language, in which segment a distinctive position may be filled by any parameter character (hand shape, place of articulation, movement, palm orientation, the orientation of the fingers, hands arrangement, and contact). The main part of this work is a one-handed and two-hand analysis of characters in which the hand / hands in the shape of the hand and closed, respectively in the shape of A, A0, A roof, sA and tA. The analyzed material was obtained from the Czech elicitation deaf native Czech sign language, and several excerption Czech sign language dictionaries. The main attention is concentrated on a detailed description of the manual components of signs and indication of possible semantic relationships between the characters figures in minimal pairs. In conclusion, the analytical part is an overview of phonemes found, possible variants of phonemes and frequency representation of character types and shapes of the hand / hands, places of articulation and places of contacts. Key words: phonology, phoneme, allophone, minimal pair, Czech sign language, sign parameter, manual component character
|
|
| |
guest ::
