Enhancement of deep learning based semantic representations with acoustic-prosodic features for automatic spoken document summarization and retrieval  Page description

Help  Print 
Back »

 

Details of project

 
Identifier
124413
Type FK
Principal investigator Szaszák, György
Title in Hungarian Mély tanulás alapú szemantikus reprezentációk kiterjesztése prozódiai-akusztikai jellemzőkkel beszéd automatikus tartalmi kivonatolásában és összefoglalásában
Title in English Enhancement of deep learning based semantic representations with acoustic-prosodic features for automatic spoken document summarization and retrieval
Keywords in Hungarian mély tanulás, beágyazás, szemantikus térbeli reprezentáció, prozódia, tartalmi kivonatolás
Keywords in English deep learning, embedding, semantic space representation, speech prosody, speech summarization
Discipline
Information Technology (Council of Physical Sciences)60 %
Ortelius classification: Applied informatics
Linguistics (Council of Humanities and Social Sciences)40 %
Ortelius classification: Computational linguistics
Panel Informatics and Electrical Engineering
Department or equivalent Department of Telecommunications and Media Informatics (Budapest University of Technology and Economics)
Participants Beke, András
Gosztolya, Gábor
Kiss, Gábor
Sztahó, Dávid
Vicsi, Klára
Starting date 2017-12-01
Closing date 2021-11-30
Funding (in million HUF) 34.873
FTE (full time equivalent) 7.00
state running project




Back »