Géza Gordos

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 prerecorded 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)
Scatternet formation is one of the most important issues of emerging wireless personal area networks (WPANs). Numerous papers pointed out that the performance of a WPAN highly depends on the scatternet structure; however, for next generation WPANs (IEEE 802.15.3 and 802.15.4) the issue of scatternet formation is not discussed in the literature so far. This(More)
Diverse synthesis methods and text-to-speech (TTS) architectures are being developed and applied almost every day. This tendency raises the need for durable program systems that effectively assist research and development in this area. A flexible development system for multilingual textto-speech and general speech research is introduced. The system was(More)
In Hungarian, as more or less in many other languages, a large percent of words and phrases can be pronounced in several, different, but correct ways. Introducing pronunciation alternatives for individual vocabulary elements may improve the efficiency of the recognition. But in connected word recognition tasks the modeling of inter-word phonetic changes has(More)