Project Details

Neural Representations in multi-modal and multi-lingual modeling

Project Period: 1. 1. 2019 - 31. 12. 2023

Project Type: grant

Code: GX19-26934X

Agency: Czech Science Foundation

Program: Grantové projekty exelence v základním výzkumu EXPRO - 2019

Czech title
Neuronové reprezentace v multimodálním a mnohojazyčném modelování
Type
grant
Keywords

deep learning;machine learning;neural networks;continuous representations;natural language processing;speech and text processing;machine translation;multi-modality;multi-linguality

Abstract

The NEUREM3 project encompasses basic research in speech processing (SP) and natural language processing (NLP) with accent on multi-linguality and multi-modality (speech and text processing with the support of visual information). Current deep machine learning methods are based on continuous vector representations that are created by the neural networks (NN) themselves during the training. Although empirically, the results of such NNs are often excellent, our knowledge and understanding of such representations is insufficient. NEUREM3 has an ambition to fill this gap and to study neural representations for speech and text units of different scopes (from phonemes and letters to whole spoken and written documents) and representations acquired both for isolated tasks and multi-task setups. NEUREM3 will also improve NN architectures and training techniques, so that they can be trained on incomplete or incoherent data.

Team members
Burget Lukáš, doc. Ing., Ph.D. (UPGM FIT VUT) , research leader
Karafiát Martin, Ing., Ph.D. (UPGM FIT VUT) , team leader
Veselý Karel, Ing., Ph.D. (UPGM FIT VUT) , team leader
Baskar Murali K. (UPGM FIT VUT)
Beneš Karel, Ing. (UPGM FIT VUT)
Kesiraju Santosh (UPGM FIT VUT)
Peng Junyi, Msc. Eng. (UPGM FIT VUT)
Sarvaš Marek, Bc. (UPGM FIT VUT)
Publications

2021

  • YUSUF Bolaji, ONDEL Lucas Antoine Francois, BURGET Lukáš, ČERNOCKÝ Jan and SARAÇLAR Murat. A Hierarchical Subspace Model for Language-Attuned Acoustic Unit Discovery. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 3710-3714. ISBN 978-1-7281-7605-5. Detail
  • LANDINI Federico Nicolás, GLEMBEK Ondřej, MATĚJKA Pavel, ROHDIN Johan A., BURGET Lukáš, DIEZ Sánchez Mireia and SILNOVA Anna. Analysis of the BUT Diarization System for Voxconverse Challenge. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 5819-5823. ISBN 978-1-7281-7605-5. Detail
  • KARAFIÁT Martin, VESELÝ Karel, ČERNOCKÝ Jan, PROFANT Ján, NYTRA Jiří, HLAVÁČEK Miroslav and PAVLÍČEK Tomáš. Analysis of X-Vectors for Low-Resource Speech Recognition. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 6998-7002. ISBN 978-1-7281-7605-5. Detail
  • KIŠŠ Martin, BENEŠ Karel and HRADIŠ Michal. AT-ST: Self-Training Adaptation Strategy for OCR in Domains with Limited Transcriptions. In: Lladós J., Lopresti D., Uchida S. (eds) Document Analysis and Recognition - ICDAR 2021. Lecture Notes in Computer Science. Lausanne: Springer Nature Switzerland AG, 2021, pp. 463-477. ISBN 978-3-030-86336-4. Detail
  • KOCOUR Martin, CÁMBARA Guillermo, LUQUE Jordi, BONET David, FARRÚS Mireia, KARAFIÁT Martin, VESELÝ Karel and ČERNOCKÝ Jan. BCN2BRNO: ASR System Fusion for Albayzin 2020 Speech to Text Challenge. In: Proceedings of IberSPEECH 2021. Vallaloid: International Speech Communication Association, 2021, pp. 113-117. Detail
  • LANDINI Federico Nicolás, LOZANO Díez Alicia, BURGET Lukáš, DIEZ Sánchez Mireia, SILNOVA Anna, ŽMOLÍKOVÁ Kateřina, GLEMBEK Ondřej, MATĚJKA Pavel, STAFYLAKIS Themos and BRUMMER Niko. BUT System Description for The Third DIHARD Speech Diarization Challenge. In: Proceedings available at Dihard Challenge Github. on-line by LDC and University of Pennsylvania, 2021, pp. 1-5. Detail
  • BASKAR Murali K., BURGET Lukáš, WATANABE Shinji, ASTUDILLO Ramon and ČERNOCKÝ Jan. Eat: Enhanced ASR-TTS for Self-Supervised Speech Recognition. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 6753-6757. ISBN 978-1-7281-7605-5. Detail
  • PENG Junyi, QU Xiaoyang, GU Rongzhi, WANG Jianzong, XIAO Jing, BURGET Lukáš and ČERNOCKÝ Jan. Effective Phase Encoding for End-To-End Speaker Verification. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 2366-2370. ISSN 1990-9772. Detail
  • PENG Junyi, QU Xiaoyang, WANG Jianzong, GU Rongzhi, XIAO Jing, BURGET Lukáš and ČERNOCKÝ Jan. ICSpk: Interpretable Complex Speaker Embedding Extractor from Raw Waveform. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 511-515. ISSN 1990-9772. Detail
  • ŽMOLÍKOVÁ Kateřina, DELCROIX Marc, BURGET Lukáš, NAKATANI Tomohiro and ČERNOCKÝ Jan. Integration of Variational Autoencoder and Spatial Clustering for Adaptive Multi-Channel Neural Speech Separation. In: Proceedings of SLT 2021. Shenzhen - virtual : IEEE Signal Processing Society, 2021, pp. 889-896. ISBN 978-1-7281-7066-4. Detail
  • VYDANA Hari K., KARAFIÁT Martin, ŽMOLÍKOVÁ Kateřina, BURGET Lukáš and ČERNOCKÝ Jan. Jointly Trained Transformers Models for Spoken Language Translation. In: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Toronto, Ontario: IEEE Signal Processing Society, 2021, pp. 7513-7517. ISBN 978-1-7281-7605-5. Detail
  • EGOROVA Ekaterina, VYDANA Hari K., BURGET Lukáš and ČERNOCKÝ Jan. Out-of-Vocabulary Words Detection with Attention and CTC Alignments in an End-to-End ASR System. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 2901-2905. ISSN 1990-9772. Detail
  • STAFYLAKIS Themos, ROHDIN Johan A. and BURGET Lukáš. Speaker embeddings by modeling channel-wise correlations. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 501-505. ISSN 1990-9772. Detail
  • BENEŠ Karel and BURGET Lukáš. Text Augmentation for Language Models in High Error Recognition Scenario. In: Proceedings Interspeech 2021. Brno: International Speech Communication Association, 2021, pp. 1872-1876. ISSN 1990-9772. Detail

2020

  • MATĚJKA Pavel, PLCHOT Oldřich, GLEMBEK Ondřej, BURGET Lukáš, ROHDIN Johan A., ZEINALI Hossein, MOŠNER Ladislav, SILNOVA Anna, NOVOTNÝ Ondřej, DIEZ Sánchez Mireia and ČERNOCKÝ Jan. 13 years of speaker recognition research at BUT, with longitudinal analysis of NIST SRE. Computer Speech and Language, vol. 2020, no. 63, pp. 1-15. ISSN 0885-2308. Detail
  • ALAM Jahangir, BOULIANNE Gilles, BURGET Lukáš, DAHMANE Mohamed, DIEZ Sánchez Mireia, GLEMBEK Ondřej, LALONDE Marc, LOZANO Díez Alicia, MATĚJKA Pavel, MIZERA Petr, MOŠNER Ladislav, NOISEUX Cédric, MONTEIRO Joao, NOVOTNÝ Ondřej, PLCHOT Oldřich, ROHDIN Johan A., SILNOVA Anna, SLAVÍČEK Josef, STAFYLAKIS Themos, ST-CHARLES Pierre-Luc, WANG Shuai and ZEINALI Hossein. Analysis of ABC Submission to NIST SRE 2019 CMN and VAST Challenge. In: Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop. Tokyo: International Speech Communication Association, 2020, pp. 289-295. ISSN 2312-2846. Detail
  • DIEZ Sánchez Mireia, BURGET Lukáš, LANDINI Federico Nicolás and ČERNOCKÝ Jan. Analysis of Speaker Diarization based on Bayesian HMM with Eigenvoice Priors. IEEE/ACM TRANSACTIONS ON AUDIO, SPEECH AND LANGUAGE PROCESSING, vol. 28, no. 1, 2020, pp. 355-368. ISSN 2329-9290. Detail
  • ZULUAGA-GOMEZ Juan, MOTLÍČEK Petr, ZHAN Qingran, VESELÝ Karel and BRAUN Rudolf. Automatic Speech Recognition Benchmark for Air-Traffic Communications. In: Proceedings of Interspeech 2020. Shanghai: International Speech Communication Association, 2020, pp. 2297-2301. ISSN 1990-9772. Detail
  • BURGET Lukáš, GLEMBEK Ondřej, LOZANO Díez Alicia, MATĚJKA Pavel, NOVOTNÝ Ondřej, PLCHOT Oldřich, PULUGUNDLA Bhargav, ROHDIN Johan A., SILNOVA Anna and VESELÝ Karel. BUT System Description to SdSV Challenge 2020. In: Proceedings of Short-duration Speaker Verification Challenge 2020 Workshop. Shanghai, on-line event of Interspeech 2020 Conference, 2020, pp. 1-5. Detail
  • LOZANO Díez Alicia, SILNOVA Anna, PULUGUNDLA Bhargav, ROHDIN Johan A., VESELÝ Karel, BURGET Lukáš, PLCHOT Oldřich, GLEMBEK Ondřej, NOVOTNÝ Ondřej and MATĚJKA Pavel. BUT Text-Dependent Speaker Verification System for SdSV Challenge 2020. In: Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH. Shanghai: International Speech Communication Association, 2020, pp. 761-765. ISSN 1990-9772. Detail
  • WANG Shuai, ROHDIN Johan A., PLCHOT Oldřich, BURGET Lukáš, YU Kai and ČERNOCKÝ Jan. Investigation of Specaugment for Deep Speaker Embedding Learning. In: ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings. Barcelona: IEEE Signal Processing Society, 2020, pp. 7139-7143. ISBN 978-1-5090-6631-5. Detail
  • SILNOVA Anna, BRUMMER Niko, ROHDIN Johan A., STAFYLAKIS Themos and BURGET Lukáš. Probabilistic embeddings for speaker diarization. In: Proceedings of Odyssey 2020 The Speaker and Language Recognition Workshop. Tokyo: International Speech Communication Association, 2020, pp. 24-31. ISSN 2312-2846. Detail

2019

  • ZEINALI Hossein, ČERNOCKÝ Jan and BURGET Lukáš. A multi purpose and large scale speech corpus in Persian and English for speaker and speech Recognition: the DeepMine database. In: IEEE Automatic Speech Recognition and Understanding Workshop - Proceedings (ASRU). Sentosa, Singapore: IEEE Signal Processing Society, 2019, pp. 397-402. ISBN 978-1-7281-0306-8. Detail
  • ALAM Jahangir, BOULIANNE Gilles, BURGET Lukáš, GLEMBEK Ondřej, LOZANO Díez Alicia, MATĚJKA Pavel, MIZERA Petr, MOŠNER Ladislav, NOVOTNÝ Ondřej, PLCHOT Oldřich, ROHDIN Johan A., SILNOVA Anna, SLAVÍČEK Josef, STAFYLAKIS Themos, WANG Shuai, ZEINALI Hossein, DAHMANE Mohamed, ST-CHARLES Pierre-Luc, LALONDE Marc, NOISEUX Cédric and MONTEIRO Joao. ABC System Description for NIST Multimedia Speaker Recognition Evaluation 2019. In: Proceedings of NIST 2019 SRE Workshop. Sentosa, Singapore: National Institute of Standards and Technology, 2019, pp. 1-7. Detail
  • MATĚJKA Pavel, PLCHOT Oldřich, ZEINALI Hossein, MOŠNER Ladislav, SILNOVA Anna, BURGET Lukáš, NOVOTNÝ Ondřej and GLEMBEK Ondřej. Analysis of BUT Submission in Far-Field Scenarios of VOiCES 2019 Challenge. In: Proceedings of Interspeech. Graz: International Speech Communication Association, 2019, pp. 2448-2452. ISSN 1990-9772. Detail
  • NOVOTNÝ Ondřej, PLCHOT Oldřich, GLEMBEK Ondřej, ČERNOCKÝ Jan and BURGET Lukáš. Analysis of DNN Speech Signal Enhancement for Robust Speaker Recognition. Computer Speech and Language, vol. 2019, no. 58, pp. 403-421. ISSN 0885-2308. Detail
  • DIEZ Sánchez Mireia, BURGET Lukáš, WANG Shuai, ROHDIN Johan A. and ČERNOCKÝ Jan. Bayesian HMM based x-vector clustering for Speaker Diarization. In: Proceedings of Interspeech. Graz: International Speech Communication Association, 2019, pp. 346-350. ISSN 1990-9772. Detail
  • ONDEL Lucas Antoine Francois, VYDANA Hari K., BURGET Lukáš and ČERNOCKÝ Jan. Bayesian Subspace Hidden Markov Model for Acoustic Unit Discovery. In: Proceedings of Interspeech 2019. Graz: International Speech Communication Association, 2019, pp. 261-265. ISSN 1990-9772. Detail
  • ZEINALI Hossein, WANG Shuai, SILNOVA Anna, MATĚJKA Pavel and PLCHOT Oldřich. BUT System Description to VoxCeleb Speaker Recognition Challenge 2019. In: Proceedings of The VoxCeleb Challange Workshop 2019. Graz, 2019, pp. 1-4. Detail
  • ROHDIN Johan A., SILNOVA Anna, DIEZ Sánchez Mireia, PLCHOT Oldřich, MATĚJKA Pavel, BURGET Lukáš and GLEMBEK Ondřej. End-to-end DNN based text-independent speaker recognition for long and short utterances. Computer Speech and Language, vol. 2020, no. 59, 2019, pp. 22-35. ISSN 0885-2308. Detail
  • NOVOTNÝ Ondřej, PLCHOT Oldřich, GLEMBEK Ondřej and BURGET Lukáš. Factorization of Discriminatively Trained i-Vector Extractor for Speaker Recognition. In: Proceedings of Interspeech. Graz: International Speech Communication Association, 2019, pp. 4330-4334. ISSN 1990-9772. Detail
  • WANG Shuai, ROHDIN Johan A., BURGET Lukáš, PLCHOT Oldřich, QIAN Yanmin, YU Kai and ČERNOCKÝ Jan. On the Usage of Phonetic Information for Text-independent Speaker Embedding Extraction. In: Proceedings of Interspeech. Graz: International Speech Communication Association, 2019, pp. 1148-1152. ISSN 1990-9772. Detail
  • STAFYLAKIS Themos, ROHDIN Johan A., PLCHOT Oldřich, MIZERA Petr and BURGET Lukáš. Self-supervised speaker embeddings. In: Proceedings of Interspeech. Graz: International Speech Communication Association, 2019, pp. 2863-2867. ISSN 1990-9772. Detail
  • ŽMOLÍKOVÁ Kateřina, DELCROIX Marc, KINOSHITA Keisuke, OCHIAI Tsubasa, NAKATANI Tomohiro, BURGET Lukáš and ČERNOCKÝ Jan. SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures. IEEE Journal of Selected Topics in Signal Processing, vol. 13, no. 4, 2019, pp. 800-814. ISSN 1932-4553. Detail
Products

2020

  • Bayesian HMM based x-vector clustering - VBx, software, 2020
    Authors: Diez Sánchez Mireia, Landini Federico Nicolás, Burget Lukáš Detail
Back to top