@article{MTMT:2695587, title = {Automated transcription of conversational Call Center speech–with respect to non-verbal acoustic events}, url = {https://m2.mtmt.hu/api/publication/2695587}, author = {Sárosi, Gellért and Tarján, Balázs and Fegyó, Tibor and Mihajlik, Péter}, doi = {10.3233/idt-140195}, journal-iso = {INTELL DECIS TECHNOL}, journal = {INTELLIGENT DECISION TECHNOLOGIES}, volume = {8}, unique-id = {2695587}, issn = {1872-4981}, year = {2014}, pages = {265-275}, orcid-numbers = {Tarján, Balázs/0000-0002-9676-3082; Fegyó, Tibor/0000-0003-0938-1965; Mihajlik, Péter/0000-0001-7532-9773} } @inproceedings{MTMT:2695417, title = {Improved Recognition of Hungarian Call Center Conversations}, url = {https://m2.mtmt.hu/api/publication/2695417}, author = {Tarján, Balázs and Sárosi, Gellért and Fegyó, Tibor and Mihajlik, Péter}, booktitle = {2013 7th Conference on Speech Technology and Human - Computer Dialogue (SpeD)}, doi = {10.1109/SpeD.2013.6682652}, unique-id = {2695417}, year = {2013}, orcid-numbers = {Tarján, Balázs/0000-0002-9676-3082; Fegyó, Tibor/0000-0003-0938-1965; Mihajlik, Péter/0000-0001-7532-9773} } @inproceedings{MTMT:2689931, title = {On Modeling Non-word Events in Large Vocabulary Continuous Speech Recognition}, url = {https://m2.mtmt.hu/api/publication/2689931}, author = {Sárosi, Gellért and Tarján, Balázs and András, Balog and Tamás, Mozsolics and Mihajlik, Péter and Fegyó, Tibor}, booktitle = {3rd International Conference on Cognitive Infocommunications (CogInfoCom)}, doi = {10.1109/CogInfoCom.2012.6421932}, unique-id = {2689931}, year = {2012}, pages = {649-653}, orcid-numbers = {Tarján, Balázs/0000-0002-9676-3082; Mihajlik, Péter/0000-0001-7532-9773; Fegyó, Tibor/0000-0003-0938-1965} } @CONFERENCE{MTMT:2683927, title = {LVCSR-based Speech Analytics of a Hungarian Language Call-Center}, url = {https://m2.mtmt.hu/api/publication/2683927}, author = {Sárosi, Gellért and Fegyó, Tibor and Mihajlik, Péter and Tarján, Balázs and Judit, Pancza and Zoltán, Hans}, booktitle = {Workshop on Innovation and Applications in Speech Technology}, unique-id = {2683927}, year = {2012}, orcid-numbers = {Fegyó, Tibor/0000-0003-0938-1965; Mihajlik, Péter/0000-0001-7532-9773; Tarján, Balázs/0000-0002-9676-3082} } @article{MTMT:2666039, title = {Recognition of Multiple Language Voice Navigation Queries in Traffic Situations}, url = {https://m2.mtmt.hu/api/publication/2666039}, author = {Sárosi, Gellért and T, Mozsolics and Tarján, Balázs and A, Balog and Mihajlik, Péter and Fegyó, Tibor}, doi = {10.1007/978-3-642-25775-9_20}, journal-iso = {LNCS}, journal = {LECTURE NOTES IN COMPUTER SCIENCE}, volume = {6800}, unique-id = {2666039}, issn = {0302-9743}, year = {2011}, eissn = {1611-3349}, pages = {199-213}, orcid-numbers = {Tarján, Balázs/0000-0002-9676-3082; Mihajlik, Péter/0000-0001-7532-9773; Fegyó, Tibor/0000-0003-0938-1965} } @inproceedings{MTMT:2666038, title = {Comparison of Feature Extraction Methods for Speech Recognition in Noise-Free and in Traffic Noise Environment}, url = {https://m2.mtmt.hu/api/publication/2666038}, author = {Sárosi, Gellért and Mozsáry, M and Mihajlik, Péter and Fegyó, Tibor}, booktitle = {2011 6th Conference on Speech Technology and Human-Computer Dialogue (SpeD)}, doi = {10.1109/SPED.2011.5940729}, unique-id = {2666038}, abstract = {A crucial part of a speech recognizer is the acoustic feature extraction, especially when the application is intended to be used in noisy environment. In this paper we investigate several novel front-end techniques and compare them to multiple baselines. Recognition tests were performed on studio quality wide band recordings on Hungarian as well as on narrow band telephone speech including real-life noises collected in six languages: English, German, French, Italian, Spanish and Hungarian. The following baseline feature types were used with several settings: Mel Frequency Cepstral Coefficients (MFCC), Perceptual Linear Prediction (PLP) features implemented in HTK, SPHINX, or by ourselves. Novel methods include Perceptual Minimum Variance Distortionless Response (PMVDR) and multiple variations of the Power-Normalized Cepstral Coefficients (PNCC). Also, adaptive techniques are applied to reduce convolutive distortions. We have experienced a significant difference between the MFCC implementations, and there were major differences in the PNCC variations useful in the different bandwidths and noise conditions.}, year = {2011}, pages = {1-8}, orcid-numbers = {Mihajlik, Péter/0000-0001-7532-9773; Fegyó, Tibor/0000-0003-0938-1965} } @inproceedings{MTMT:2666036, title = {Lényegkiemelő módszerek összehasonlítása közlekedési zajban történő beszédfelismerés céljából}, url = {https://m2.mtmt.hu/api/publication/2666036}, author = {Sárosi, Gellért and Tobler, Z and Mihajlik, Péter and Fegyó, Tibor}, booktitle = {VII. Magyar Számítógépes Nyelvészeti Konferencia : MSZNY 2010}, unique-id = {2666036}, year = {2010}, pages = {384-388}, orcid-numbers = {Mihajlik, Péter/0000-0001-7532-9773; Fegyó, Tibor/0000-0003-0938-1965} } @article{MTMT:2666035, title = {Hallásmodellek a gépi beszédfelismerésben. Akusztikai lényegkiemelő módszerek összehasonlítása többnyelvű, közlekedési zajjal terhelt beszédfelismerési feladatban}, url = {https://m2.mtmt.hu/api/publication/2666035}, author = {Sárosi, Gellért and Mihajlik, Péter and Tobler, Z and Fegyó, Tibor}, journal-iso = {AKUSZTIKAI SZEMLE}, journal = {AKUSZTIKAI SZEMLE}, volume = {10}, unique-id = {2666035}, issn = {1419-6301}, year = {2010}, pages = {48-55}, orcid-numbers = {Mihajlik, Péter/0000-0001-7532-9773; Fegyó, Tibor/0000-0003-0938-1965} } @article{MTMT:1436367, title = {Speech Recognition Experiments with Audiobooks}, url = {https://m2.mtmt.hu/api/publication/1436367}, author = {Tóth, László and Tarján, Balázs and Sárosi, Gellért and Mihajlik, Péter}, journal-iso = {ACTA CYBERN-SZEGED}, journal = {ACTA CYBERNETICA}, volume = {19}, unique-id = {1436367}, issn = {0324-721X}, year = {2010}, eissn = {2676-993X}, pages = {695-713}, orcid-numbers = {Tóth, László/0000-0003-0161-1375; Tarján, Balázs/0000-0002-9676-3082; Mihajlik, Péter/0000-0001-7532-9773} }