5 papers
Speaker-Aware Simulation Improves Conversational Speech Recognition
Máté Gedeon, Péter Mihajlik
Automatic speech recognition (ASR) for conversational speech remains challenging due to the limited availability of large-scale, well-annotated multi-speaker dialogue data and the…
Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets
Máté Gedeon, Piroska Zsófia Barta, Péter Mihajlik +3
The advancement of automatic speech recognition (ASR) has been largely enhanced by extensive datasets in high-resource languages, while languages such as Hungarian remain underrepr…
A Comparative Analysis of Static Word Embeddings for Hungarian
Máté Gedeon
This paper presents a comprehensive analysis of various static word embeddings for Hungarian, including traditional models such as Word2Vec, FastText, as well as static embeddings…
Retrieval-Enhanced Few-Shot Prompting for Speech Event Extraction
Máté Gedeon
Speech Event Extraction (SpeechEE) is a challenging task that lies at the intersection of Automatic Speech Recognition (ASR) and Natural Language Processing (NLP), requiring the id…
Do Attention Heads Compete or Cooperate during Counting?
Pál Zsámboki, Ádám Fraknói, Máté Gedeon +2
We present an in-depth mechanistic interpretability analysis of training small transformers on an elementary task, counting, which is a crucial deductive step in many algorithms. I…