TY - JOUR AU - Nagy, Péter AU - Németh, Géza TI - Improving HMM Speech Synthesis of Interrogative Sentences by Pitch Track Transformations JF - SPEECH COMMUNICATION J2 - SPEECH COMMUN VL - 82 PY - 2016 SP - 97 EP - 112 PG - 16 SN - 0167-6393 DO - 10.1016/j.specom.2016.06.005 UR - https://m2.mtmt.hu/api/publication/3088550 ID - 3088550 N1 - Cited By :4 Export Date: 14 February 2023 CODEN: SCOMD Correspondence Address: Nagy, P.; Department of Telecommunications and Media Informatics, Magyar tudósok krt. 2, Hungary; email: nagyp@tmit.bme.hu LA - English DB - MTMT ER - TY - JOUR AU - Nagy, Péter AU - Németh, Géza TI - DNN-Based Duration Modeling for Synthesizing Short Sentences JF - LECTURE NOTES IN COMPUTER SCIENCE J2 - LNCS VL - 9811 PY - 2016 SP - 254 EP - 261 PG - 8 SN - 0302-9743 DO - 10.1007/978-3-319-43958-7_30 UR - https://m2.mtmt.hu/api/publication/3120602 ID - 3120602 N1 - Megjelent a Speech and Computer c. kötetben, Softcover ISBN: 978-3-319-43957-0 LA - English DB - MTMT ER - TY - CHAP AU - Nagy, Péter AU - Zainkó, Csaba AU - Németh, Géza TI - Synthesis of Speaking Styles with Corpus- and HMM-Based Approaches T2 - 2015 6th IEEE International Conference on Cognitive Infocommunications (CogInfoCom) PB - Institute of Electrical and Electronics Engineers (IEEE) CY - New York, New York SN - 9781467381307 T3 - International Conference on Cognitive Infocommunications, ISSN 2375-1312 PY - 2015 SP - 195 EP - 200 PG - 6 DO - 10.1109/CogInfoCom.2015.7390589 UR - https://m2.mtmt.hu/api/publication/2970189 ID - 2970189 N1 - Conference code: 119131 Cited By :1 Export Date: 25 October 2022 AB - In this paper we compare two state-of-the-art speech synthesis techniques (corpus- and HMM-based) in terms of expressive speech synthesis. Two corpora were composed with different speaking styles (broadcast news and literature reading) from the same female speaker. Our aim was to determine to what extent the different technologies reproduce these styles. The corpora and the synthetic expressive speech samples were evaluated based on objective measures, and a carefully designed perceptual test was carried out in order to evaluate naturalness, quality and style identification rates of the generated samples. In our objective assessment we focused on prosodic features that principally influence the speaking style: F 0 contour, average values and articulatory speed. Our evaluation of the perceptual test shows that both techniques were able to capture the main features of expressive speech and although listeners preferred the HMM-based voice, the speaking style was recognizable in case of both methods. LA - English DB - MTMT ER - TY - JOUR AU - Gyires-Tóth, Bálint Pál AU - Nagy, Péter AU - Németh, Géza TI - Towards Modeling Interrogative Sentences in HMM-based Speech Synthesis JF - PHONETICIAN J2 - PHONET VL - 109-110 PY - 2014 IS - I-II SP - 24 EP - 42 PG - 19 SN - 0741-6164 UR - https://m2.mtmt.hu/api/publication/2956228 ID - 2956228 LA - English DB - MTMT ER - TY - CHAP AU - Nagy, Péter AU - Gyires-Tóth, Bálint Pál AU - Németh, Géza ED - Vlado, Delić TI - Adaptation of Large Corpus Average Voice Model in HMM Speech Synthesis for Synthesizing Short Sentences T2 - Proceedings of 2nd International Acoustics and Audio Engineering Conference PB - s.n. CY - Újvidék SN - 9788678925559 PY - 2013 SP - 80 EP - 83 PG - 4 UR - https://m2.mtmt.hu/api/publication/2695927 ID - 2695927 LA - English DB - MTMT ER - TY - CHAP AU - Gyires-Tóth, Bálint Pál AU - Nagy, Péter AU - Németh, Géza ED - Miesenberger, Klaus ED - Karshmer, Arthur ED - Penaz, Petr ED - Zagler, Wolfgang TI - New Features in the VoxAid Communication Aid for Speech Impaired People T2 - Computers Helping People with Special Needs PB - Springer Netherlands CY - Berlin CY - Heidelberg SN - 9783642315336 T3 - Lecture Notes in Computer Science, ISSN 0302-9743 ; 7383. PY - 2012 SP - 295 EP - 302 PG - 8 DO - 10.1007/978-3-642-31534-3_45 UR - https://m2.mtmt.hu/api/publication/2687110 ID - 2687110 LA - English DB - MTMT ER -