Balázs Tarján

According to our database, Balázs Tarján authored at least 23 papers between 2009 and 2022.

Collaborative distances:

• Dijkstra number of five.
• Erdős number of four.

2022

BEA-Base: A Benchmark for ASR of Spontaneous Hungarian.

Péter Mihajlik, András Balog, Tekla Etelka Gráczi, Anna Kohári, Balázs Tarján, Katalin Mády

Proceedings of the Thirteenth Language Resources and Evaluation Conference, 2022

2020

A low latency sequential model and its user-focused evaluation for automatic punctuation of ASR closed captions.

Máté Ákos Tündik, Balázs Tarján, György Szaszák

Comput. Speech Lang., 2020

Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR.

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

CoRR, 2020

On the Effectiveness of Neural Text Generation Based Data Augmentation for Recognition of Morphologically Rich Speech.

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

Proceedings of the Text, Speech, and Dialogue, 2020

Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model.

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

Proceedings of the 11th IEEE International Conference on Cognitive Infocommunications, 2020

2019

Investigation on N-Gram Approximated RNNLMs for Recognition of Morphologically Rich Speech.

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

Proceedings of the Statistical Language and Speech Processing, 2019

Investigating Sub-Word Embedding Strategies for the Morphologically Rich and Free Phrase-Order Hungarian.

Bálint Döbrössy, Márton Makrai, Balázs Tarján, György Szaszák

Proceedings of the 4th Workshop on Representation Learning for NLP, 2019

N-gram Approximation of LSTM Recurrent Language Models for Single-pass Recognition of Hungarian Call Center Conversations.

Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik

Proceedings of the 10th IEEE International Conference on Cognitive Infocommunications, 2019

2017

Low Latency MaxEnt- and RNN-Based Word Sequence Models for Punctuation Restoration of Closed Caption Data.

Máté Ákos Tündik, Balázs Tarján, György Szaszák

Proceedings of the Statistical Language and Speech Processing, 2017

First Results in Developing a Medieval Latin Language Charter Dictation System for the East-Central Europe Region.

Péter Mihajlik, Lili Szabó, Balázs Tarján, András Balog, Krisztina Rábai

Proceedings of the Interspeech 2017, 2017

Á bilingual comparison of MaxEnt-and RNN-based punctuation restoration in speech transcripts.

Máté Ákos Tündik, Balázs Tarján, György Szaszák

Proceedings of the 8th IEEE International Conference on Cognitive Infocommunications, 2017

2015

Automatic Close Captioning for Live Hungarian Television Broadcast Speech: A Fast and Resource-Efficient Approach.

Ádam Varga, Balázs Tarján, Zoltán Tobler, György Szaszák, Tibor Fegyó, Csaba Bordás, Péter Mihajlik

Proceedings of the Speech and Computer - 17th International Conference, 2015

2014

Automated transcription of conversational Call Center speech - with respect to non-verbal acoustic events.

Gellért Sárosi, Balázs Tarján, Tibor Fegyó, Péter Mihajlik

Intell. Decis. Technol., 2014

A bilingual study on the prediction of morph-based improvement.

Balázs Tarján, Tibor Fegyó, Péter Mihajlik

Proceedings of the 4th Workshop on Spoken Language Technologies for Under-resourced Languages, 2014

Writing with speech: A qualitative user evaluation study.

Lili Szabó, Balázs Tarján, Péter Mihajlik

Proceedings of the 5th IEEE Conference on Cognitive Infocommunications, 2014

2013

Improved recognition of Hungarian call center conversations.

Balázs Tarján, Gellért Sárosi, Tibor Fegyó, Péter Mihajlik

Proceedings of the 7th Conference on Speech Technology and Human-Computer Dialogue, 2013

2012

Broadcast news transcription in Central-East European languages.

Balázs Tarján, Tamás Mozsolics, András Balog, D. Halmos, Tibor Fegyó, Péter Mihajlik

Proceedings of the IEEE 3rd International Conference on Cognitive Infocommunications, 2012

On modeling non-word events in Large Vocabulary Continuous Speech Recognition.

Gellért Sárosi, Balázs Tarján, András Balog, Tamás Mozsolics, Péter Mihajlik, Tibor Fegyó

Proceedings of the IEEE 3rd International Conference on Cognitive Infocommunications, 2012

2010

Improved Recognition of Spontaneous Hungarian Speech - Morphological and Acoustic Modeling Techniques for a Less Resourced Task.

Péter Mihajlik, Zoltán Tüske, Balázs Tarján, Bottyán Németh, Tibor Fegyó

IEEE Trans. Speech Audio Process., 2010

Speech Recognition Experiments with Audiobooks.

László Tóth, Balázs Tarján, Gellért Sárosi, Péter Mihajlik

Acta Cybern., 2010

On morph-based LVCSR improvements.

Balázs Tarján, Péter Mihajlik

Proceedings of the 2nd Workshop on Spoken Language Technologies for Under-Resourced Languages, 2010

Recognition of Multiple Language Voice Navigation Queries in Traffic Situations.

Gellért Sárosi, Tamás Mozsolics, Balázs Tarján, András Balog, Péter Mihajlik, Tibor Fegyó

Proceedings of the Analysis of Verbal and Nonverbal Communication and Enactment. The Processing Issues, 2010

2009

Investigation of morph-based speech recognition improvements across speech genres.

Péter Mihajlik, Balázs Tarján, Zoltán Tüske, Tibor Fegyó

Proceedings of the INTERSPEECH 2009, 2009