The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
In this paper an analysis of multithread approach to speaker recognition is presented. Two cases have been investigated — the use of multithreading first, to reduce the total time of training and testing (when processing the speaker database) and second, to reduce the time of a single speaker recognition (e.g. in voice-based access systems). We have investigated the processing time in function of...
The paper presents implementation aspects of real time speaker recognition from Internet radio broadcasts. The proposed solution is based on the free and open source Python development tools. The prepared software was tested with the Windows environment and then adapted to the Unix operating system running on the Raspberry Pi platform. We show what libraries are most convenient in order to implement...
The paper presents a comparison of speaker models used for fast speaker identification in short recordings of telephone conversations. The knowledge of the encoder type used during the transmission of speech allows to apply a model that takes specific characteristics of the encoder into account. This improves efficiency of the speaker recognition process. The influence of the following GSM encoders...
A problem of design of a system for real-time voice watermarking using a digital signal processor (DSP) is studied and presented in this paper. The authors prepared and compared three versions of the considered system using different types of data formats (fixed-point and floating-point) and various ways of programming (Matlab/Simulik compiler for Code Composer Studio and plain C/C++ programming).
This paper presents analysis of impact of the image resolution on the efficacy of the automatic face recognition. During experimental studies three databases were tested, where the head in the photos is set at different angles. The effectiveness of face location detection was examined with the use of the skin color and geometric models. Next, we tested the influence of the head position and the image...
The paper presents an analysis of speaker activity in online recordings from the Internet radio. The proposed system has been developed in the Matlab environment. Our research is based on four 1-hour length public debates acquired from the Internet radio. 7–8 speakers (including one presenter) participated in the recordings. The speaker recognition was performed on short utterances to facilitate real...
In this paper we analyze reliability of the real-time system for face detection and recognition from low-resolution images, e.g., from video monitoring images. First, we briefly describe main features of the standards for biometric face images. Available scientific databases have been checked for compliance with these biometric standards. During the research we have considered both the correctness...
This paper presents a concept for fast prototyping of real-time hardware/software video processing systems for urban surveillance monitoring equipment. The evaluation module with the TMS320DM6437 signal processor linked with the Code Composer Studio through Matlab/Simulink has been used. The processed video signals have been acquired using BOSCH NBC-255-P network camera with the CMOS ¼″ sensor. We...
This paper studies effectiveness of speaker identification based on short Polish sequences. The results have been got as a continuation of the experiments presented by the authors during the previous SPA conference. An impact of automatic removal of silence on the speaker recognition accuracy is considered. Several methods to detect the beginnings and ends of the words have been used. Experimental...
The article presents test algorithm that is used for segmentation of the speakers in a telephone conversation. The proposed algorithm is based on the use of a watermark inserted into the speech signal. The program was written in the Matlab / Simulink environment and implemented on a signal processor TMS320C6713 DSK. A watermark insertion algorithm was tested, and the signal from the telephone line...
This article presents the results of studies on the effects of multiple transcoding operations in the case of GSM standards. Differences between the MFCC coefficients, obtained by successive transcoding were considered. The aim of comparisons is to check the possibility for separation and detection of the used GSM encoder. During the research we used the TIMIT database recordings, transcoded four...
This paper presents results of speaker recognition experiments using short Polish sentences. We developed and analyzed various vector quantization representations in order to first maximize identification effectiveness and second to compare VQ (vector quantization) and GMM (Gaussian mixture model) approaches. For the research and experiments we created and exploited database, containing specially...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.