Péter Mihajlik

55 papers A 12B 1C 1Journal 13Unranked 28

Year	Rank	Type	Title / Venue / Authors
2026	—	`conf`	Detecting Infant Cries in Noisy NICU Recordings: A Study on SSL Models. BIOSTEC (1) Ákos Antal, Péter Földesy, Péter Mihajlik
2026	J	`jnl`	Speaker-Aware Simulation Improves Conversational Speech Recognition. CoRR Máté Gedeon, Péter Mihajlik
2025	—	`conf`	Best Data is more Supervised Data - Even for Hungarian ASR. SPECOM (2) Gergely Dobsinszki, Péter Mihajlik, Mate S. Kadar, Tibor Fegyó, Katalin Mády
2025	—	`conf`	Cross-lingual Transfer Learning Experiments for Arabic ASR. SpeD Amin Hassairi, Péter Mihajlik
2025	—	`conf`	From CHAT towards ASR: A Hybrid Pipeline for Constructing the HUKILC-CO Hungarian Child Speech Dataset. IWSSIP Yue Luo, Xihang Xia, Kinga Jelencsik-Mátyus, Shaimaa Alwaisi, Péter Mihajlik
2025	J	`jnl`	From Independence to Interaction: Speaker-Aware Simulation of Multi-Speaker Conversational Timing. CoRR Máté Gedeon, Péter Mihajlik
2025	—	`conf`	How Far Can Synthetic Speech Go? Enhancing ASR in Low-Resource Scenarios via Voice Cloning. TSD (1) Dalai Mengke, Yan Meng, Péter Mihajlik
2025	—	`conf`	Impact of Text Origin and Real-Synthetic Data Ratio in TTS-Augmented Low-Resource ASR. SpeD Dalai Mengke, Wuyerigen, Péter Mihajlik
2025	—	`conf`	Improved Dysarthric Speech to Text Conversion via TTS Personalization. EUSIPCO Péter Mihajlik, Éva Székely, Piroska Barta, Máté Soma Kádár, Gergely Dobsinszki, László Tóth
2025	J	`jnl`	Improved Dysarthric Speech to Text Conversion via TTS Personalization. CoRR Péter Mihajlik, Éva Székely, Piroska Barta, Mate S. Kadar, Gergely Dobsinszki, László Tóth
2025	J	`jnl`	LibriConvo: Simulating Conversations from Read Literature for ASR and Diarization. CoRR Máté Gedeon, Péter Mihajlik
2025	—	`conf`	Robust Disfluency Labeling in Spontaneous Speech: Insights from Diverse Hungarian Corpora Including Atypical Speakers. TSD (1) Yan Meng, Péter Mihajlik, Dalai Mengke, Katalin Mády
2025	J	`jnl`	Toward Conversational Hungarian Speech Recognition: Introducing the BEA-Large and BEA-Dialogue Datasets. CoRR Máté Gedeon, Piroska Barta, Péter Mihajlik, Tekla Etelka Gráczi, Anna Kohári, Katalin Mády
2025	—	`conf`	Towards Hungarian-English Code-Switching Speech Dataset Construction by using Multi Speaker-adaptive Text-to-Speech Synthesis. SpeD Piroska Barta, Péter Mihajlik
2025	A	`conf`	Voice Reconstruction through Large-Scale TTS Models: Comparing Zero-Shot and Fine-tuning Approaches to Personalise TTS in Assistive Communication. INTERSPEECH Éva Székely, Péter Mihajlik, Máté Soma Kádár, László Tóth
2024	—	`conf`	Comparison of Well and Lower-Resourced Self-training in ASR. SPECOM (1) Yue Luo, Péter Mihajlik
2024	—	`conf`	Is Spoken Hungarian Low-resource?: A Quantitative Survey of Hungarian Speech Data Sets. LREC/COLING Péter Mihajlik, Katalin Mády, Anna Kohári, Fruzsina Sára Fruzsina, Gábor Kiss, Tekla Etelka Gráczi, A. Seza Dogruöz
2024	A	`conf`	On Disfluency and Non-lexical Sound Labeling for End-to-end Automatic Speech Recognition. INTERSPEECH Péter Mihajlik, Yan Meng, Mate S. Kadar, Julian Linke, Barbara Schuppler, Katalin Mády
2023	A	`conf`	What do self-supervised speech representations encode? An analysis of languages, varieties, speaking styles and speakers. INTERSPEECH Julian Linke, Mate Kadar, Gergely Dosinszky, Péter Mihajlik, Gernot Kubin, Barbara Schuppler
2022	B	`conf`	BEA-Base: A Benchmark for ASR of Spontaneous Hungarian. LREC Péter Mihajlik, András Balog, Tekla Etelka Gráczi, Anna Kohári, Balázs Tarján, Katalin Mády
2022	J	`jnl`	BEA-Base: A Benchmark for ASR of Spontaneous Hungarian. CoRR Péter Mihajlik, András Balog, Tekla Etelka Gráczi, Anna Kohári, Balázs Tarján, Katalin Mády
2020	J	`jnl`	Deep Transformer based Data Augmentation with Subword Units for Morphologically Rich Online ASR. CoRR Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2020	—	`conf`	Improving Real-time Recognition of Morphologically Rich Speech with Transformer Language Model. CogInfoCom Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2020	—	`conf`	On the Effectiveness of Neural Text Generation Based Data Augmentation for Recognition of Morphologically Rich Speech. TDS Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2020	J	`jnl`	On the Effectiveness of Neural Text Generation based Data Augmentation for Recognition of Morphologically Rich Speech. CoRR Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2019	—	`conf`	Investigation on N-Gram Approximated RNNLMs for Recognition of Morphologically Rich Speech. SLSP Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2019	J	`jnl`	Investigation on N-gram Approximated RNNLMs for Recognition of Morphologically Rich Speech. CoRR Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2019	—	`conf`	N-gram Approximation of LSTM Recurrent Language Models for Single-pass Recognition of Hungarian Call Center Conversations. CogInfoCom Balázs Tarján, György Szaszák, Tibor Fegyó, Péter Mihajlik
2017	A	`conf`	First Results in Developing a Medieval Latin Language Charter Dictation System for the East-Central Europe Region. INTERSPEECH Péter Mihajlik, Lili Szabó, Balázs Tarján, András Balog, Krisztina Rábai
2017	—	`conf`	Unified Simplified Grapheme Acoustic Modeling for Medieval Latin LVCSR. TSD Lili Szabó, Péter Mihajlik, András Balog, Tibor Fegyó
2015	—	`conf`	Automatic Close Captioning for Live Hungarian Television Broadcast Speech: A Fast and Resource-Efficient Approach. SPECOM Ádam Varga, Balázs Tarján, Zoltán Tobler, György Szaszák, Tibor Fegyó, Csaba Bordás, Péter Mihajlik
2014	—	`conf`	A bilingual study on the prediction of morph-based improvement. SLTU Balázs Tarján, Tibor Fegyó, Péter Mihajlik
2014	J	`jnl`	Automated transcription of conversational Call Center speech - with respect to non-verbal acoustic events. Intell. Decis. Technol. Gellért Sárosi, Balázs Tarján, Tibor Fegyó, Péter Mihajlik
2014	—	`conf`	Writing with speech: A qualitative user evaluation study. CogInfoCom Lili Szabó, Balázs Tarján, Péter Mihajlik
2013	—	`conf`	Improved recognition of Hungarian call center conversations. SpeD Balázs Tarján, Gellért Sárosi, Tibor Fegyó, Péter Mihajlik
2013	—	`conf`	Lightly supervised acoustic model training for imprecisely and asynchronously transcribed speech. SpeD Péter Mihajlik, András Balog
2012	—	`conf`	Broadcast news transcription in Central-East European languages. CogInfoCom Balázs Tarján, Tamás Mozsolics, András Balog, D. Halmos, Tibor Fegyó, Péter Mihajlik
2012	—	`conf`	On modeling non-word events in Large Vocabulary Continuous Speech Recognition. CogInfoCom Gellért Sárosi, Balázs Tarján, András Balog, Tamás Mozsolics, Péter Mihajlik, Tibor Fegyó
2012	—	`conf`	Synthesizing expressive speech from amateur audiobook recordings. SLT Éva Székely, Tamás Gábor Csapó, Bálint Tóth, Péter Mihajlik, Julie Carson-Berndsen
2011	—	`conf`	Comparison of feature extraction methods for speech recognition in noise-free and in traffic noise environment. SpeD Gellért Sárosi, Mihály Mozsáry, Péter Mihajlik, Tibor Fegyó
2010	J	`jnl`	Improved Recognition of Spontaneous Hungarian Speech - Morphological and Acoustic Modeling Techniques for a Less Resourced Task. IEEE Trans. Speech Audio Process. Péter Mihajlik, Zoltán Tüske, Balázs Tarján, Bottyán Németh, Tibor Fegyó
2010	—	`conf`	On morph-based LVCSR improvements. SLTU Balázs Tarján, Péter Mihajlik
2010	—	`conf`	Recognition of Multiple Language Voice Navigation Queries in Traffic Situations. COST 2102 Conference Gellért Sárosi, Tamás Mozsolics, Balázs Tarján, András Balog, Péter Mihajlik, Tibor Fegyó
2010	J	`jnl`	Speech Recognition Experiments with Audiobooks. Acta Cybern. László Tóth, Balázs Tarján, Gellért Sárosi, Péter Mihajlik
2009	A	`conf`	Investigation of morph-based speech recognition improvements across speech genres. INTERSPEECH Péter Mihajlik, Balázs Tarján, Zoltán Tüske, Tibor Fegyó
2008	C	`conf`	Automated Drug Information System for Aged and Visually Impaired Persons. ICCHP Géza Németh, Gábor Olaszy, Mátyás Bartalis, Géza Kiss, Csaba Zainkó, Péter Mihajlik, Csaba Haraszti
2007	A	`conf`	A morpho-graphemic approach for the recognition of spontaneous speech in agglutinative languages - like Hungarian. INTERSPEECH Péter Mihajlik, Tibor Fegyó, Zoltán Tüske, Pavel Ircing
2007	A	`conf`	Speech based drug information system for aged and visually impaired persons. INTERSPEECH Géza Németh, Gábor Olaszy, Mátyás Bartalis, Géza Kiss, Csaba Zainkó, Péter Mihajlik
2007	—	`conf`	Towards Automatic Transcription of Large Spoken Archives in Agglutinating Languages - Hungarian ASR for the MALACH Project. TSD Péter Mihajlik, Tibor Fegyó, Bottyán Németh, Zoltán Tüske, Viktor Trón
2005	A	`conf`	Evaluation and optimization of noise robust front-end technologies for the automatic recognition of Hungarian telephone speech. INTERSPEECH Péter Mihajlik, Zoltán Tobler, Zoltán Tüske, Géza Gordos
2005	A	`conf`	Robust voice activity detection based on the entropy of noise-suppressed spectrum. INTERSPEECH Zoltán Tüske, Péter Mihajlik, Zoltán Tobler, Tibor Fegyó
2003	A	`conf`	Comparative study on hungarian acoustic model sets and training methods. INTERSPEECH Tibor Fegyó, Péter Mihajlik, Péter Tatai
2003	A	`conf`	Voxenter^TM - intelligent voice enabled call center for hungarian. INTERSPEECH Tibor Fegyó, Péter Mihajlik, Máté Szarvas, Péter Tatai, Gábor Tatai
2001	A	`conf`	Pronunciation modeling in hungarian number recognition. INTERSPEECH Tibor Fegyó, Péter Mihajlik, Péter Tatai, Géza Gordos
2000	J	`jnl`	Automatic Recognition of Hungarian: Theory And Practice. Int. J. Speech Technol. Máté Szarvas, Tibor Fegyó, Péter Mihajlik, Péter Tatai