Login
 Forum
 
 
Personal data sheet
 Print preview
personal data approved: 2020. I. 28.
Personal data
György Szaszák
name György Szaszák
name of institution
doctoral school
BME Doctoral School of Informatics (Academic staff member)
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:
Máté Ákos Tündik PhD 2020  DSI-BME

completed course requirement, without degree or degree granting in process:
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
2019

Döbrössy Bálint, Makrai Márton, Tarján Balázs, Szaszák György: Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian, In: Isabelle, Augenstein; Spandana, Gella; Sebastian, Ruder; Katharina, Kann; Burcu, Can; Johannes, Welbl; Alexis, Conneau; Xiang, Ren; Marek, Rei (szerk.) Proceedings of the 4th Workshop on Representation Learning for NLP (RepL4NLP-2019), Association for Computational Linguistics (2019) pp. 187-193.
type of document: Conference paper/Előadás vagy poszter cikke
language: English
URL 
2019

Szaszák György, Tündik Máté Ákos: Leveraging a Character, Word and Prosody Triplet for an ASR Error Robust and Agglutination Friendly Punctuation Approach, In: Gernot, Kubin; Zdravko, Kačič (szerk.) The 20th Annual Conference of the International Speech Communication Association, ISCA-INT SPEECH COMMUNICATION ASSOC (2019) pp. 2988-2992.
type of document: Part of book/Proceedings Paper
language: English
URL 
2019

Tündik Máté Ákos, Kaszás Valér, Szaszák György: Assessing the Semantic Space Bias Caused by ASR Error Propagation and its Effect on Spoken Document Summarization, In: Gernot, Kubin; Zdravko, Kačič (szerk.) The 20th Annual Conference of the International Speech Communication Association, ISCA-INT SPEECH COMMUNICATION ASSOC (2019) pp. 1333-1337.
type of document: Part of book/Proceedings Paper
language: English
URL 
2018

György Szaszák, Máté Ákos Tündik, Branislav Gerazov: Prosodic stress detection for fixed stress languages using formal atom decomposition and a statistical hidden Markov hybrid, SPEECH COMMUNICATION 102: pp. 14-26.
type of document: Journal paper/Article
number of independent citations: 1
language: English
URL 
2018

Máté Ákos Tündik, György Szaszák, Gábor Gosztolya, András Beke: User-centric Evaluation of Automatic Punctuation in ASR Closed Captioning, In: B, Yegnanarayana (szerk.) Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH 2018, International Speech Communication Association (ISCA) (2018) pp. 2628-2632.
type of document: Part of book/Proceedings Paper
language: English
URL 
2017

Szaszák György, Beke András: An empirical approach for comparing syntax and pros ody driven prominence marking, PHONETICIAN 114: (1) pp. 46-57.
type of document: Journal paper/Article
language: English
URL 
2016

Beke A, Szaszák G: Automatic summarization of highly spontaneous speech, LECTURE NOTES IN COMPUTER SCIENCE 9811: pp. 140-147.
type of document: Journal paper/Article
language: English
URL 
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 
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 
Number of independent citations to these publications:21 
Scientometric data
list of publications and citations
number of scientific publications that meet accreditation criteria:
82
number of scientific publications:
89
monographs and professional books:
0
monographs/books in which chapters/sections were contributed:
3 
number of independent citations to scientific publications and creative works:
155

 
All rights reserved © 2007, Hungarian Doctoral Council. Doctoral Council registration number at commissioner for data protection: 02003/0001. Program version: 2.2358 ( 2017. X. 31. )