Login
 Forum
 
 
Personal data sheet
 Print preview
personal data approved: 2017. II. 27.
Personal data
György Szaszák
name György Szaszák
year of birth 1979
name of institution
doctoral school
BME Doctoral School of Informatics (Supervisor)
Contact details
E-mail address szaszaktmit.bme.hu
phone number +36 1 463-1886
own web page
Academic title
scientific degree, title Ph.D.
year degree was obtained 2009
discipline to which degree belongs computer sciences
institution granting the degree Budapest University of Technology and Economics
Employment
2002 - Budapest University of Technology and Economics
egyetemi kutató
Thesis topic supervisor
number of doctoral students supervised until now 0
number of students who fulfilled course requirements 0
students who obtained their degrees:
present PhD students:
Máté Ákos Tündik (PhD) (2018/08)  DSI-BME
  Thesis topic proposals
Research
research area Speech technology, speech prosody, machine learning, signal processing
research field in which current research is conducted computer sciences
electrical engineering
Publications
2016

Szaszák G, Tündik MÁ, Gerazov B, Gjoreski A: Combining atom decomposition of the F0 track and HMM-based phonological phrase modelling for robust stress detection in speech, LECTURE NOTES IN COMPUTER SCIENCE 9811: pp. 165-173.
type of document: Journal paper/Article
language: English
DOI 
2015

György Szaszák, András Beke, Gábor Olaszy, Bálint Pál Tóth: Using automatic stress extraction from audio for improved prosody modeling in speech synthesis, In: Interspeech 2015 - Proceedings of the 16th Annual Conference of the International Speech Communication Association.Drezda, Németország, 2015.09.06-2015.09.10. International Speech Communication Association (ISCA), pp. 2227-2231. Kiadvány: International Speech Communication Association (ISCA), 2015.
type of document: Conference paper/Előadás vagy poszter cikke
number of independent citations: 1
language: English
Full text 
2014

Szaszák György, Tulics Miklós Gábriel, Tündik Máté Ákos: Analyzing F0 Discontinuity for Speech Prosody Enhancement, ACTA UNIVERSITATIS SAPIENTIAE ELECTRICAL AND MECHANICAL ENGINEERING 6: pp. 59-67.
type of document: Journal paper/Article
language: English
2014

Beke András, Szaszák György: Combining NLP techniques and acoustic analysis for semantic focus detection in speech, In: Szerk.: Institute of Electrical and Electronics Engineers 5th IEEE International Conference on Cognitive Infocommunications: CogInfoCom 2014 : Proceedings. Piscataway: IEEE, 2014. pp. 493-497.
type of document: Part of book/Proceedings Paper
language: English
DOI 
2013

György Szaszák, András Beke: Using Phonological Phrase Segmentation to Improve Automatic Keyword Spotting for the Highly Agglutinating Hungarian Language, In: Proc. Interspeech 2013.Lyon, Franciaország, 2013.08.25-2013.08.29. pp. 1589-1593. Kiadvány: 2013. (Proc. Interspeech 2013)
type of document: Conference paper/Előadás vagy poszter cikke
language: English
2012

Szaszák György, Beke András: Exploiting Prosody for Syntactic Analysis in Automatic Speech Understanding, JOURNAL OF LANGUAGE MODELLING 2012: (1) pp. 143-172.
type of document: Journal paper/Article
language: English
2011

Ringeval F, Demouy J, Szaszak G, Chetouani M, Robel L, Xavier J, Cohen D, Plaza M: Automatic Intonation Recognition for the Prosodic Assessment of Language Impaired Children, IEEE TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING 19: (5) pp. 1328-1342.
type of document: Journal paper/Article
number of independent citations: 19
language: English
DOI 
2010

Vicsi K, Szaszák Gy: Using prosody to improve automatic speech recognition, SPEECH COMMUNICATION 52: (5) pp. 413-426.
type of document: Journal paper/Article
number of independent citations: 19
language: English
DOI 
2010

Beke András, Szaszák György: Automatic recognition of schwa variants in spontaneous Hungarian speech, ACTA LINGUISTICA HUNGARICA 57: (2) pp. 329-353.
type of document: Journal paper/Article
number of independent citations: 1
language: English
DOI 
2007

Vicsi Klára, Szaszák György, Németh Zsolt: Folyamatos magyar beszéd mondatfajtáinak automatikus felismerése, In: Szerk.: Gósy M Beszédkutatás 2007. Budapest: MTA Kiadó, 2007. pp. 162-172. (Beszédkutatás 2007)
type of document: Part of book/Könyvfejezet (to be translated)
language: Hungarian
Number of independent citations to these publications:40 
Scientometric data
list of publications and citations
number of scientific publications that meet accreditation criteria:
68
number of scientific publications:
73
monographs and professional books:
0
monographs/books in which chapters/sections were contributed:
3 
number of independent citations to scientific publications and creative works:
130

 
All rights reserved © 2007, Hungarian Doctoral Council. Doctoral Council registration number at commissioner for data protection: 02003/0001. Program version: 1.2357 ( 2017. V. 15. )