Géza Gordos

Learn 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)
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 text-to-speech and general speech research is introduced. The system was(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)
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)