Ladislav Mosner

Dr. Ladislav Mosner


Research Focus & Metrics

Academic Career Length

8Years (2019-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
17 May 2019 in IEEE Journal of Selected Topics in Signal Processing
Verified
Journal Article
Closed access
ISIgor Szoke
Igor Szoke
MSMiroslav Skacel
Miroslav Skacel
LMLadislav Mosner
Ladislav Mosner
JPJakub Paliesek
Jakub Paliesek
HCHonza Cernocky
Honza Cernocky
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.

9 January 2023
Verified
Conference Paper
Open access
JPJunyi Peng
Junyi Peng
OPOldrich Plchot
Oldrich Plchot
TSThemos Stafylakis
Themos Stafylakis
LMLadislav Mosner
Ladislav Mosner
LBLukas Burget
Lukas Burget
HCHonza Cernocky
Honza Cernocky
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification task have yet to be fully explored. In this paper, we analyze several feature extraction approaches built on top of a pre-trained model, as well as regularization and a learning rate scheduler to stabilize the fine-tuning process and further boost performance: multi-head factorized attentive pooling is proposed to factorize the comparison of speaker representations into multiple phonetic clusters. We regularize towards the parameters of the pre-trained model and we set different learning rates for each layer of the pre-trained model during fine-tuning. The experimental results show our method can significantly shorten the training time to 4 hours and achieve SOTA performance: 0.59%, 0.79% and 1.77% EER on Vox1-O, Vox1-E and Vox1-H, respectively. 1 1 Code is available at https://github.com/JunyiPeng00/IEEE-SLT22-Pretrained-Model-for-SV.

4 October 2022 in arXiv
Verified
Preprint
Open access
PDF file
JPJunyi Peng
Junyi Peng
OPOldrich Plchot
Oldrich Plchot
TSThemos Stafylakis
Themos Stafylakis
LMLadislav Mosner
Ladislav Mosner
LBLukas Burget
Lukas Burget
HCHonza Cernocky
Honza Cernocky
In recent years, self-supervised learning paradigm has received extensive attention due to its great success in various down-stream tasks. However, the fine-tuning strategies for adapting those pre-trained models to speaker verification task have yet to be fully explored. In this paper, we analyze several feature extraction approaches built on top of a pre-trained model, as well as regularization and learning rate schedule to stabilize the fine-tuning process and further boost performance: multi-head factorized attentive pooling is proposed to factorize the comparison of speaker representations into multiple phonetic clusters. We regularize towards the parameters of the pre-trained model and we set different learning rates for each layer of the pre-trained model during fine-tuning. The experimental results show our method can significantly shorten the training time to 4 hours and achieve SOTA performance: 0.59%, 0.79% and 1.77% EER on Vox1-O, Vox1-E and Vox1-H, respectively.

18 October 2023 in arXiv
Verified
Preprint
Open access
PDF file
MKMartin Karafiát
Martin Karafiát
KVKarel Veselý
Karel Veselý
ISIgor Szöke
Igor Szöke
LMLadislav Mosner
Ladislav Mosner
KBKarel Beneš
Karel Beneš
LPLeonardo Pepino
Leonardo Pepino
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.

15 March 2019 in arXiv
Verified
Preprint
Open access
PDF file
LMLadislav Mosner
Ladislav Mosner
MWMinhua Wu
Minhua Wu
ARAnirudh Raju
Anirudh Raju
SPSree Hari Krishnan Parthasarathi
Sree Hari Krishnan Parthasarathi
KKKenichi Kumatani
Kenichi Kumatani
BHBjörn Hoffmeister
Björn Hoffmeister
For real-world speech recognition applications, noise robustness is still a challenge. In this work, we adopt the teacher-student (T/S) learning technique using a parallel clean and noisy corpus for improving automatic speech recognition (ASR) performance under multimedia noise. On top of that, we apply a logits selection method which only preserves the k highest values to prevent wrong emphasis of knowledge from the teacher and to reduce bandwidth needed for transferring data. We incorporate up to 8000 hours of untranscribed data for training and present our results on sequence trained models apart from cross entropy trained ones. The best sequence trained student model yields relative word error rate (WER) reductions of approximately 10.1%, 28.7% and 19.6% on our clean, simulated noisy and real test sets respectively comparing to a sequence trained teacher.

9 August 2022 in arXiv
Verified
Preprint
Open access
PDF file
TSThemos Stafylakis
Themos Stafylakis
LMLadislav Mosner
Ladislav Mosner
OPOldřich Plchot
Oldřich Plchot
JRJohan Rohdin
Johan Rohdin
ASAnna Silnova
Anna Silnova
JČJan Honza'' Černocký
Jan Honza'' Černocký
In this paper, we demonstrate a method for training speaker embedding extractors using weak annotation. More specifically, we are using the full VoxCeleb recordings and the name of the celebrities appearing on each video without knowledge of the time intervals the celebrities appear in the video. We show that by combining a baseline speaker diarization algorithm that requires no training or parameter tuning, a modified loss with aggregation over segments, and a two-stage training approach, we are able to train a competitive ResNet-based embedding extractor. Finally, we experiment with two different aggregation functions and analyze their behaviour in terms of their gradients.