Igor Szöke
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Igor Szöke has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- Jan Černocký
Brno University of Technology Czechia
3 shared publications Karel Veselý
2 shared publications- Ladislav Mošner
Speech@FIT IT4I Center of Excellence Brno University of Technology Czechia
2 shared publications - Martin Karafiat
Brno University of Technology
2 shared publications Carlos Segura
1 shared publication- František Grézl
Speech@FIT group, Brno University of Technology, Czech Republic
1 shared publication
Latest Publications
- Open Access
BUT CHiME-7 system description
This paper describes the joint effort of Brno University of Technology (BUT), AGH University of Krakow and University of Buenos Aires on the development of Automatic Speech Recognition systems for the CHiME-7 Challenge. We train and evaluate various end-to-end models with several toolkits. We heavily relied on Guided Source Separation (GSS) to convert multi-channel audio to single channel. The ASR is leveraging speech representations from models pre-trained by self-supervised learning, and we do a fusion of several ASR systems. In addition, we modified external data from the LibriSpeech corpus to become a close domain and added it to the training. Our efforts were focused on the far-field acoustic robustness sub-track of Task 1 - Distant Automatic Speech Recognition (DASR), our systems use oracle segmentation.
Open AccessBUT CHiME-7 system description
This paper describes the joint effort of Brno University of Technology (BUT), AGH University of Krakow and University of Buenos Aires on the development of Automatic Speech Recognition systems for the CHiME-7 Challenge. We train and evaluate various end-to-end models with several toolkits. We heavily relied on Guided Source Separation (GSS) to convert multi-channel audio to single channel. The ASR is leveraging speech representations from models pre-trained by self-supervised learning, and we do a fusion of several ASR systems. In addition, we modified external data from the LibriSpeech corpus to become a close domain and added it to the training. Our efforts were focused on the far-field acoustic robustness sub-track of Task 1 - Distant Automatic Speech Recognition (DASR), our systems use oracle segmentation.
- Top Cited Papers
- 17 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 13 (4) , 863-876
Building and evaluation of a real room impulse response dataset
This paper presents BUT ReverbDB - a dataset of real room impulse responses (RIR), background noises and re-transmitted speech data. The retransmitted data includes LibriSpeech test-clean, 2000 HUB5 English evaluation and part of 2010 NIST Speaker Recognition Evaluation datasets. We provide a detailed description of RIR collection (hardware, software, post-processing) that can serve as a "cook-book" for similar efforts. We also validate BUT ReverbDB in two sets of automatic speech recognition (ASR) experiments and draw conclusions for augmenting ASR training data with real and artificially generated RIRs. We show that a limited number of real RIRs, carefully selected to match the target environment, provide results comparable to a large number of artificially generated RIRs, and that both sets can be combined to achieve the best ASR results. The dataset is distributed for free under a non-restrictive license and it currently contains data from 8 rooms, which is growing. The distribution package also contains a Kaldi-based recipe for augmenting publicly available AMI close-talk meeting data and test the results on an AMI single distant microphone set, allowing it to reproduce our experiments.
- 17 May 2019
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Signal Processing
- Vol. 13 (4) , 863-876
Top Cited PapersBuilding and evaluation of a real room impulse response dataset
This paper presents BUT ReverbDB - a dataset of real room impulse responses (RIR), background noises and re-transmitted speech data. The retransmitted data includes LibriSpeech test-clean, 2000 HUB5 English evaluation and part of 2010 NIST Speaker Recognition Evaluation datasets. We provide a detailed description of RIR collection (hardware, software, post-processing) that can serve as a "cook-book" for similar efforts. We also validate BUT ReverbDB in two sets of automatic speech recognition (ASR) experiments and draw conclusions for augmenting ASR training data with real and artificially generated RIRs. We show that a limited number of real RIRs, carefully selected to match the target environment, provide results comparable to a large number of artificially generated RIRs, and that both sets can be combined to achieve the best ASR results. The dataset is distributed for free under a non-restrictive license and it currently contains data from 8 rooms, which is growing. The distribution package also contains a Kaldi-based recipe for augmenting publicly available AMI close-talk meeting data and test the results on an AMI single distant microphone set, allowing it to reproduce our experiments.
- 2 September 2018
- Published by International Speech Communication Association
BUT OpenSAT 2017 Speech Recognition System
- 2 September 2018
- Published by International Speech Communication Association
BUT OpenSAT 2017 Speech Recognition System