E-LIB Suche - Ergebnisse für: Mosner, Ladislav

1

Parameter-Efficient Transfer Learning of Pre-Trained Transf..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Peng, Junyi ; Stafylakis, Themos ; Gu, Rongzhi... - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

2

Extracting Speaker and Emotion Information from Self-Superv..:

, In: 2022 IEEE Spoken Language Technology Workshop (SLT),

Stafylakis, Themos ; Mosner, Ladislav ; Kakouros, Sofoklis... - p. 1136-1143 , 2023

Link: https://doi.org/10.1109/..

3

An Attention-Based Backend Allowing Efficient Fine-Tuning o..:

, In: 2022 IEEE Spoken Language Technology Workshop (SLT),

Peng, Junyi ; Plchot, Oldrich ; Stafylakis, Themos... - p. 555-562 , 2023

Link: https://doi.org/10.1109/..

4

Speech-Based Emotion Recognition with Self-Supervised Model..:

, In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Kakouros, Sofoklis ; Stafylakis, Themos ; Mosner, Ladislav. - p. 1-5 , 2023

Link: https://doi.org/10.1109/..

5

Analysis of Impact of Emotions on Target Speech Extraction ..:

, In: 2022 International Workshop on Acoustic Signal Enhancement (IWAENC),

Svec, Jan ; Zmolikova, Katerina ; Kocour, Martin... - p. 1-5 , 2022

Link: https://doi.org/10.1109/..

6

Multisv: Dataset for Far-Field Multi-Channel Speaker Verifi..:

, In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Mosner, Ladislav ; Plchot, Oldrich ; Burget, Lukas. - p. 7977-7981 , 2022

Link: https://doi.org/10.1109/..

7

Multi-Channel Speaker Verification with Conv-Tasnet Based B..:

, In: ICASSP 2022 - 2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Mosner, Ladislav ; Plchot, Oldrich ; Burget, Lukas. - p. 7982-7986 , 2022

Link: https://doi.org/10.1109/..

8

13 years of speaker recognition research at BUT, with longi..:

Matějka, Pavel ; Plchot, Oldřich ; Glembek, Ondřej...
Computer Speech & Language. 63 (2020) - p. 101035 , 2020

Link: https://doi.org/10.1016/..

9

But System for the Second Dihard Speech Diarization Challen..:

, In: ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Landini, Federico ; Wang, Shuai ; Diez, Mireia... - p. 6529-6533 , 2020

Link: https://doi.org/10.1109/..

10

Improving Noise Robustness of Automatic Speech Recognition ..:

, In: ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP),

Mosner, Ladislav ; Wu, Minhua ; Raju, Anirudh... - p. 6475-6479 , 2019

Link: https://doi.org/10.1109/..

11

Speaker Verification with Application-Aware Beamforming:

, In: 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU),

Mosner, Ladislav ; Plchot, Oldrich ; Rohdin, Johan.. - p. 411-418 , 2019

Link: https://doi.org/10.1109/..

12

Improving Speaker Verification with Self-Pretrained Transfo..:

Peng, Junyi ; Plchot, Oldřich ; Stafylakis, Themos...
http://arxiv.org/abs/2305.10517. , 2023

Link: http://arxiv.org/abs/230..

13

BUT CHiME-7 system description:

Karafiát, Martin ; Veselý, Karel ; Szöke, Igor...
http://arxiv.org/abs/2310.11921. , 2023

Link: http://arxiv.org/abs/231..

14

Speech-based emotion recognition with self-supervised model..:

Kakouros, Sofoklis ; Stafylakis, Themos ; Mošner, Ladislav.
10.1109/ICASSP49357.2023.10094673. , 2023

Link: http://hdl.handle.net/10..

15

Probabilistic Spherical Discriminant Analysis: An Alternati..:

Brümmer, Niko ; Swart, Albert ; Mošner, Ladislav...
http://arxiv.org/abs/2203.14893. , 2022

Link: http://arxiv.org/abs/220..