|
|
Tone and Chord Recognition as an Android Application
Kucharovič, Oliver ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
The aim of this work is to recognize tones and chords on any musical instrument using the microphone on Android mobile devices. The app scans or records the sounds which are analyzed. It writes to a visual representation which is similar to the musical notation. The work describes the problems of recognition and the solution of the problem using fast Fourier transformation and analysis of the spectrum of volumes. Work describes the theory of music and the training of individual tones. The application was subjected to user tests and recognition accuracy tests. The conclusion includes tests results and statistics from the Google Play publication.
|
|
|
Audio Saving Module
Strašil, Ivo ; Kouřil, Jiří (referee) ; Říha, Kamil (advisor)
The aim of this thesis was to design and construct an autonomous, hardware voice recorder/player module. The device is made as a compact, built-in component for a motherboard of a target appliance. During recording, the incoming analog voice signal is converted to a digital stream by an ADC with 16 bits resolution and 24 kHz sample rate. Microcontroller LPC2103 (ARM7TDMI core) processes data, recalculates resolution and sample rate, encodes and converts to WAV format and save into a FAT/FAT32 filesystem on a Secure Digital memory card. At playback, the process is opposite: the microcontroller reads file from the memory card, decodes the stream and sends it to a DAC and then to a reconstruction filter. So there is an analog voice signal at the output again. The firmware allows control by logic inputs or by a serial bus, processing of uncompressed WAV files or WAV files with A-law or IMA ADPCM compression, continual recording including automatic freeing of card space by deleting the oldest records and a usage of a voice emphasis filter or of a signal dynamic compression circuit.
|
|
|
Recorder with SD card
Dohnal, Petr ; Fiedler, Petr (referee) ; Bradáč, Zdeněk (advisor)
This thesis presents the design and construction of Recorder with SD card. The paper deals with methods of communication between integrated circuit devices and the various functional blocks of equipment. Thesis also discusses the use of the FAT system for storing data on an SD card, file format .wav and convert analog signal to digital.
|
|
|
Sestem for removal of children speech defects
Pokorný, Vojtěch ; Sekora, Jiří (referee) ; Harabiš, Vratislav (advisor)
Speech is one of the basic forms of human communication and disruption of communication ability can negatively affect the life of man. deals with the elaboration of logopedic theory, which serves as a basis for the follow-up design and application creation in the field of speech therapy. The thesis is divided into five chapters. The first chapter deals with the history of speech therapy with an emphasis on domestic logopaedia, the logopedic intervention process in its entirety, and the differentiation of individual types of impaired communication skills. The second chapter focuses on a specific disruption of communication skills - dyslalia.The application for the treatment of dyslalia is determined by the application, which is elaborated in the third chapter. The fourth chapter contains a detailed description of the designed and created application, including an explanation of the processes running in the application when the application is being used. The last chapter of this diploma thesis contains a summary of the results of the practical testing of the application together with suggestions for improvement of the application.
|
|
|
Recognition of musical recordings
Masár, Igor ; Horka, Michal (referee) ; Sigmund, Milan (advisor)
This thesis analyzes the specific audio signal-music. It describes the basic methods of analysis of musical signals. The following are mentioned the most common music file formats and the possibility of cross transfer. There are explained terms of music theory, which are also present in this work. They are described and created three ways of detecting melody. It is selected optimal algorithm based on the successful detection of the reference melodies recordings. User interface is created in MATLAB GUI allows recognition of recordings. This interface is tested on few melodies.
|
|
|
Speech signal processing via web interface
Markovič, Michal ; Smékal, Zdeněk (referee) ; Mekyska, Jiří (advisor)
This work is resolving the possibility of processing a speech signal by using the web interface. A record of the speech signal is made and then saved and stored in servers. Then it’s possible to analyse and process the record with the help of a web application written in the C++ programming language. The results are shown in website.
|
|
|
New Method of the Optical Record and Reproduction of the 16mm Film Sound-Track
Vacula, Richard ; Neubauer, Petr (referee) ; Wilfert, Otakar (advisor)
The work deals with the recording and reproduction of sound tracks on 16mm film and with old forgotten film optic sound technologies, as well as plans experiments and research, which examines possible methods for reading and writing tracks using modern optoelectronic devices. The final output is intended to drive the writing negative audio (analog and digital) on the photosensitive material and design of the device for synchronous playback of digital audio tracks from an external memory card. The work is done in collaboration with film laboratories Barrandov Studio a.s. and Meopta-Optika, spol. s r.o.
|
|
|
Conversion of Piano Recording from WAV to MIDI
Bednařík, Jan ; Černocký, Jan (referee) ; Szőke, Igor (advisor)
The aim of the thesis is to propose a system capable of automatic conversion of polyphonic piano recordings from the audio format WAV to MIDI. The thesis describes problems related to single tone recognition in music recordings and proposes a solution based on a probabilistic model that uses the Probabilistic Latent Component Analysis method. Recordings of isolated digital piano tones were used to train the system. The proposed system was tested on classical recordings of the Classical Piano MIDI database and on recordings of a Korg SP-250 piano and evaluated using a variety of metrics. The conclusion part contains the results of recognition success rate and their comparison with other existing systems.
|
|
|
Web application for speech and voice acquisition
Levák, Adam ; Galáž, Zoltán (referee) ; Mekyska, Jiří (advisor)
This bachelor’s thesis deals with designing and building a web application for speech and voice recording. The main goal of the thesis was to write a theoretical background, create a prototype and build the final web application. The theoretical background involves comparing mobile applications, a comparison of already available solutions for voice and speech recording and an introduction to database systems. The web application prototype was created in an online vector graphics editor Figma. The implementation of the actual web application, which is able to record speech exercises and voice exercises, was written in the JavaScript programming language. The application consists of a set of exercises, specifically picture description, elongated phonation, a diadochokinetic exercise, sentence repetition and text reading. Each exercise will have a text and a voice instruction assisting the user in performing the exercise correctly. Exercise recordings will be safely transferred to an online storage Google Drive. Moreover, a reward system was designed and implemented. It intends to motivate the users to do the exercises regularly, leading to more data collection as these exercises will be done repeatedly. The system is working and tested and is implemented as a progressive web application.
|
|
|
Digital Audio Steganography
Kabelka, Petr ; Malaník, Petr (referee) ; Strnadel, Josef (advisor)
The field of steganography deals with concealing information with the goal of hiding their very existence. The goal of this work is to create a summary of existing digital audio steganography methods and implement some of them. This work presents easily extensible and usable multiplatform library for audio steganography written in the Python programming language and a program that uses it. At the end of this work are the implemented methods compared against each other and against the published methods. Because it is hard to find concrete implementations of various published methods, the presented library enables almost anyone to easily use the implemented steganographic methods and to continue working on research in this field without the need to reimplement all of them.
|
guest ::
