VVI e-INFRA CZ (ORJ 90254, kód MŠMT MSMT-54/2023)

2025

• VÍDEŇSKÝ František, ZBOŘIL František a VEIGEND Petr. Integrating Late Variable Binding with SP-MCTS for Efficient Plan Execution in BDI Agents. In: Proceedings of the 17th International Conference on Agents and Artificial Intelligence - Volume 1: ICAART. Porto: SciTePress - Science and Technology Publications, 2025, s. 679-686. ISBN 978-989-758-737-5. Detail

2024

• ROHDIN Johan A., ZHANG Lin, PLCHOT Oldřich, STANĚK Vojtěch, MIHOLA David, PENG Junyi, STAFYLAKIS Themos, BEVERAKI Dmitriy, SILNOVA Anna, BRUKNER Jan a BURGET Lukáš. BUT systems and analyses for the ASVspoof 5 Challenge. In: Proceedings of ASV spoof 2024 Workshop. Kos Island: International Speech Communication Association, 2024, s. 24-31. Detail
• POLOK Alexander, KLEMENT Dominik, HAN Jiangyu, SEDLÁČEK Šimon, YUSUF Bolaji, MACIEJEWSKI Matthew, WIESNER Matthew a BURGET Lukáš. BUT/JHU System Description for CHiME-8 NOTSOFAR-1 Challenge. In: Proceedings of CHiME 2024 Workshop. Kos Island: International Speech Communication Association, 2024, s. 18-22. Detail
• KUNEŠOVÁ Marie, ZAJÍC Zbyněk, ŠMÍDL Luboš a KARAFIÁT Martin. Comparison of wav2vec 2.0 models on three speech processing tasks. International Journal of Speech Technology, roč. 27, č. 4, 2024, s. 847-859. ISSN 1572-8110. Detail
• HAN Jiangyu, LANDINI Federico Nicolás, ROHDIN Johan A., DIEZ Sánchez Mireia, BURGET Lukáš, CAO Yuhang, LU Heng a ČERNOCKÝ Jan. Diacorrect: Error Correction Back-End for Speaker Diarization. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Seoul: IEEE Signal Processing Society, 2024, s. 11181-11185. ISBN 979-8-3503-4485-1. Detail
• LANDINI Federico Nicolás, DIEZ Sánchez Mireia, STAFYLAKIS Themos a BURGET Lukáš. DiaPer: End-to-End Neural Diarization With Perceiver-Based Attractors. IEEE Transactions on Audio, Speech, and Language Processing, roč. 32, č. 7, 2024, s. 3450-3465. ISSN 1558-7916. Detail
• KLEMENT Dominik, DIEZ Sánchez Mireia, LANDINI Federico Nicolás, BURGET Lukáš, SILNOVA Anna, DELCROIX Marc a TAWARA Naohiro. Discriminative Training of VBx Diarization. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Seoul: IEEE Signal Processing Society, 2024, s. 11871-11875. ISBN 979-8-3503-4485-1. Detail
• ZHANG Lin, STAFYLAKIS Themos, LANDINI Federico Nicolás, DIEZ Sánchez Mireia, SILNOVA Anna a BURGET Lukáš. Do End-to-End Neural Diarization Attractors Need to Encode Speaker Characteristic Information?. In: Proceedings of Odyssey 2024: The Speaker and Language Recognition Workshop. Québec City: International Speech Communication Association, 2024, s. 123-130. Detail
• ČEGIŇ Ján, PECHER Branislav, ŠIMKO Jakub, SRBA Ivan a BIELIKOVÁ Mária. Effects of diversity incentives on sample diversity and downstream model performance in LLM-based text augmentation. In: Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers). Bangkok: Association for Computational Linguistics, 2024, s. 13148-13171. ISBN 979-8-8917-6094-3. Detail
• PECHER Branislav, ČEGIŇ Ján, BELANEC Róbert, SRBA Ivan, ŠIMKO Jakub a BIELIKOVÁ Mária. Fighting Randomness With Randomness: Mitigating Optimisation Instability of Fine-Tuning Using Ensemble and Noise Regularisation. In: Findings of the Association for Computational Linguistics: EMNLP 2024. Miami: Association for Computational Linguistics, 2024, s. 11005-11044. ISBN 979-8-8917-6168-1. Detail
• BENEŠ Karel, KOCOUR Martin a BURGET Lukáš. Hystoc: Obtaining Word Confidences for Fusion of End-To-End ASR Systems. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Seoul: IEEE Signal Processing Society, 2024, s. 11276-11280. ISBN 979-8-3503-4485-1. Detail
• STAFYLAKIS Themos, SILNOVA Anna, ROHDIN Johan A., PLCHOT Oldřich a BURGET Lukáš. Challenging margin-based speaker embedding extractors by using the variational information bottleneck. In: Proceedings of Interspeech 2024. Kos: International Speech Communication Association, 2024, s. 3220-3224. ISSN 1990-9772. Detail
• MOŠNER Ladislav, SERIZEL Romain, BURGET Lukáš, PLCHOT Oldřich, VINCENT Emmanuel, PENG Junyi a ČERNOCKÝ Jan. Multi-Channel Extension of Pre-trained Models for Speaker Verification. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Kos: International Speech Communication Association, 2024, s. 2135-2139. ISSN 1990-9772. Detail
• YUSUF Bolaji, ČERNOCKÝ Jan a SARAÇLAR Murat. Pretraining End-to-End Keyword Search with Automatically Discovered Acoustic Units. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Kos: International Speech Communication Association, 2024, s. 5068-5072. ISSN 1990-9772. Detail
• VILLATORO-TELLO Esaú, MADIKERI Srikanth, SHARMA Bidisha, KHALIL Driss, KUMAR Sashi, NIGMATULINA Iuliia, MOTLÍČEK Petr a GANAPATHIRAJU Aravind. Probability-Aware Word-Confusion-Network-to-Text Alignment Approach for Intent Classification. In: ICASSP 2024 - 2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Seoul: IEEE Signal Processing Society, 2024, s. 12617-12621. ISBN 979-8-3503-4485-1. Detail
• PENG Junyi, DELCROIX Marc, OCHIAI Tsubasa, ASHIHARA Takanori, PLCHOT Oldřich, ARAKI Shoko a ČERNOCKÝ Jan. Probing Self-Supervised Learning Models With Target Speech Extraction. In: 2024 IEEE International Conference on Acoustics, Speech, and Signal Processing Workshops, ICASSPW 2024 - Proceedings. Seoul: IEEE Signal Processing Society, 2024, s. 535-539. ISBN 979-8-3503-7451-3. Detail
• PEŠÁN Jan, JUŘÍK Vojtěch, RŮŽIČKOVÁ Alexandra, SVOBODA Vojtěch, JANOUŠEK Oto, NĚMCOVÁ Andrea, BOJANOVSKÁ Hana, ALDABAGHOVÁ Jasmína, KYSLÍK Filip, VODIČKOVÁ Kateřina, SODOMOVÁ Adéla, BARTYS Patrik, CHUDÝ Peter a ČERNOCKÝ Jan. Speech production under stress for machine learning: multimodal dataset of 79 cases and 8 signals. Nature Scientific Data, roč. 11, č. 1, 2024, s. 1-9. ISSN 2052-4463. Detail
• PENG Junyi, DELCROIX Marc, OCHIAI Tsubasa, PLCHOT Oldřich, ARAKI Shoko a ČERNOCKÝ Jan. Target Speech Extraction with Pre-Trained Self-Supervised Learning Models. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Seoul: IEEE Signal Processing Society, 2024, s. 10421-10425. ISBN 979-8-3503-4485-1. Detail
• YUSUF Bolaji a SARAÇLAR Murat. Written Term Detection Improves Spoken Term Detection. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, roč. 32, č. 06, 2024, s. 3213-3223. ISSN 2329-9290. Detail