Learn More
The close similarity of the voices of consanguineous persons has suggested that there must exist hereditary phonetic parameters. To test this hypothesis, a method for characterizing numerically the similarity or dissimilarity of voices of twins with zygosity previously established by anthropological methods was elaborated. By speech processing and(More)
In this paper a variety of front-end configurations are evaluated on Hungarian telephone speech databases. Our aim was to measure directly the efficiency of the front-ends on real noisy and normal speech data. As a baseline the ETSI ADSR standard front-end is used. Some simplification on the standard is introduced resulting in better performance on our(More)
In limited vocabulary speaking systems where several pre-recorded speech items are concatenated to generate the message one of the main problems is to add new items to the message set recorded formerly. This procedure is complicated, expensive and the new message(s) cannot be integrated into the original system without leaving the impression that the new(More)
Name and address reading is an important combined application area of language processing and text-to-speech (TTS) systems. It is the cornerstone of both traditional reverse directory telephone services and new, location based, traffic and tour guide applications. The language processing aspects of a solution for Hungarian is described. The work was based(More)
This paper describes an objective speech quality assessment method developed for the Hungarian NMT-450 mobile telephone system. The method is based on a psychoacoustic front end followed by a cognitive modeling component. Special problems of the NMT system, such as handovers , the effects of automatic gain control (AGC) and intrusion of signaling noise are(More)