Login
 Forum
 
 
Personal data sheet
 Print preview
personal data approved: 2019. III. 26.
Personal data
Bálint Gyires-Tóth
name Bálint Gyires-Tóth
name of institution
doctoral school
BME Doctoral School of Informatics (Supervisor)
BME Géza Pattantyús-Ábrahám Doctoral School of Mechanical Engineering (Supervisor)
BME Doctoral School of Electrical Engineering (Supervisor)
the share of work in the different doctoral schools. BME Doctoral School of Informatics 50%
BME Géza Pattantyús-Ábrahám Doctoral School of Mechanical Engineering 25%
BME Doctoral School of Electrical Engineering 25%
Contact details
E-mail address toth.btmit.bme.hu
phone number +36 1 463-3512
own web page
Academic title
scientific degree, title Ph.D.
year degree was obtained 2014
discipline to which degree belongs electrical engineering
institution granting the degree Budapest University of Technology and Economics
Employment
2008 - Budapest University of Technology and Economics
university professor or researcher
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:
Róbert Moni (PhD) (2023/01)  DSEE
Hamdi M.H. Abed (PhD) (2022/08)  DSEE
(50%) Gergely Hajgató (PhD) (2021/08)  PAGDSME
Sevinj Yolchuyeva (PhD) (2020/08)  DSI-BME
  Thesis topic proposals
Research
research area deep learning, deep neural networks, modeling time series, pattern recognition, novel machine learning architectures
research field in which current research is conducted computer sciences
electrical engineering
Publications
2019

Yolchuyeva Sevinj, Németh Géza, Gyires-Tóth Bálint: End-to-end Convolutional neural networks for Intent Detection, In: Berend, Gábor; Gosztolya, Gábor; Vincze, Veronika (szerk.) XV. Magyar Számítógépes Nyelvészeti Konferencia, Szegedi Tudományegyetem, Informatikai Intézet (2019) p. 123.
type of document: Part of book/Proceedings Paper
language: English
2016

Bálint Pál Tóth, Márton Osváth, Dávid Papp, Gábor Szücs: Deep Learning and SVM Classification for Plant Recognition in Content-Based Large Scale Image Retrieval, In: Krisztian, Balog; Linda, Cappellato; Nicola, Ferro; Craig, Macdonald (szerk.) Working Notes of Conference and Labs of the Evaluation Forum, (2016) pp. 569-578.
type of document: Conference paper/Előadás vagy poszter cikke
number of independent citations: 5
language: English
2016

Bálint Pál Tóth, Tamás Gábor Csapó: Continuous Fundamental Frequency Prediction with Deep Neural Networks, In: European Signal Processing Conference (EUSIPCO 2016), IEEE (2016) pp. 1348-1352.
type of document: Conference paper/Előadás vagy poszter cikke
number of independent citations: 2
language: English
Full text 
2016

Tóth Bálint Pál, Czeba Bálint: Convolutional Neural Networks for Large-Scale Bird Song Classification in Noisy Environment, In: Krisztian, Balog; Linda, Cappellato; Nicola, Ferro; Craig, Macdonald (szerk.) Working Notes of Conference and Labs of the Evaluation Forum, (2016) pp. 560-568.
type of document: Conference paper/Előadás vagy poszter cikke
number of independent citations: 7
language: English
2016

Tóth Bálint Pál, Kornél István Kis, Szaszák György, Németh Géza: Ensemble Deep Neural Network Based Waveform-Driven Stress Model for Speech Synthesis, In: Andrey, Ronzhin; Rodmonga, Potapova; Géza, Németh (szerk.) Speech and Computer, Springer International Publishing (2016) pp. 271-278.
type of document: Part of book/Proceedings Paper
number of independent citations: 1
language: English
2015

György Szaszák, András Beke, Gábor Olaszy, Bálint Pál Tóth: Using automatic stress extraction from audio for improved prosody modeling in speech synthesis, In: Sebastian, Möller; Hermann, Ney; Bernd, Möbius; Elmar, Nöth; Stefan, Steidl (szerk.) Speech Beyond Speech Towards a Better Understanding of the Most Important Biosignal: Proceedings of the Annual Conference of the International Speech Communication Association (INTERSPEECH 2015), International Speech Communication Association (ISCA) (2015) pp. 2227-2231.
type of document: Part of book/Proceedings Paper
number of independent citations: 3
language: English
Full text 
2012

Tóth Bálint Pál, Németh Géza: Optimizing HMM Speech Synthesis for Low-Resource Devices, JOURNAL OF ADVANCED COMPUTATIONAL INTELLIGENCE AND INTELLIGENT INFORMATICS 16: (2) pp. 327-334.
type of document: Journal paper/Article
number of independent citations: 4
language: English
URL 
2012

Éva Székely, Tamás Gábor Csapó, Bálint Tóth, Péter Mihajlik, Julie Carson-Berndsen: Synthesizing Expressive Speech from Amateur Audiobook Recordings, In: IEEE Workshop on Spoken Language Technology, (2012) pp. 297-302.
type of document: Conference paper/Előadás vagy poszter cikke
number of independent citations: 10
language: English
2010

Tóth Bálint Pál, Fegyó Tibor, Németh Géza: Some Aspects of ASR Transcription based Unsupervised Speaker Adaptation for HMM Speech Synthesis, In: Petr, Sojka; Ivan, Kopecek; Karel, Pala (szerk.) TSD 2010 Text Speech and Dialogue, Springer (2010) pp. 408-415.
type of document: Conference paper/Előadás vagy poszter cikke
language: English
2010

Tóth Bálint Pál, Németh Géza: Improvements of Hungarian Hidden Markov Model-based Text-to-Speech Synthesis, ACTA CYBERNETICA 19: (4) pp. 715-731.
type of document: Journal paper/Article
number of independent citations: 2
language: English
Number of independent citations to these publications:34 
Scientometric data
list of publications and citations
number of scientific publications that meet accreditation criteria:
39
number of scientific publications:
51
monographs and professional books:
0
monographs/books in which chapters/sections were contributed:
0 
number of independent citations to scientific publications and creative works:
80


2019. IX. 13.
ODT ülés
Az ODT következő ülésére 2019. október 11-én 12.00 órakor kerül sor a Semmelweis Egyetem Szenátusi termében (Bp. Üllői út 26. I. emelet).

 
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. )