Obserwuj
Piotr Żelasko
Piotr Żelasko
Principal Research Scientist @ Nvidia
Zweryfikowany adres z nvidia.com
Tytuł
Cytowane przez
Cytowane przez
Rok
Hierarchical transformers for long document classification
R Pappagari, P Zelasko, J Villalba, Y Carmiel, N Dehak
2019 IEEE automatic speech recognition and understanding workshop (ASRU …, 2019
3432019
Audio Replay Attack Detection Using High-Frequency Features
M Witkowski, S Kacprzak, P Żelasko, K Kowalczyk, J Gałka
Interspeech 2017, 27-31, 2017
1942017
Non-autoregressive transformer for speech recognition
N Chen, S Watanabe, J Villalba, P Żelasko, N Dehak
IEEE Signal Processing Letters 28, 121-125, 2020
1502020
Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource Scenarios.
R Pappagari, J Cho, S Joshi, L Moro-Velázquez, P Zelasko, J Villalba, ...
Interspeech 2021, 3825-3829, 2021
652021
Punctuation prediction model for conversational speech
P Żelasko, P Szymański, J Mizgajski, A Szymczak, Y Carmiel, N Dehak
Interspeech 2018, 2018
642018
Copypaste: An augmentation method for speech emotion recognition
R Pappagari, J Villalba, P Żelasko, L Moro-Velazquez, N Dehak
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
612021
Segmental contrastive predictive coding for unsupervised word segmentation
S Bhati, J Villalba, P Żelasko, L Moro-Velazquez, N Dehak
Interspeech 2021, 2021
592021
Earnings-21: a practical benchmark for ASR in the wild
M Del Rio, N Delworth, R Westerman, M Huang, N Bhandari, J Palakapilly, ...
Interspeech 2021, 2021
582021
Study of pre-processing defenses against adversarial attacks on state-of-the-art speaker recognition systems
S Joshi, J Villalba, P Żelasko, L Moro-Velázquez, N Dehak
IEEE Transactions on Information Forensics and Security 16, 4811-4826, 2021
57*2021
WER we are and WER we think we are
P Szymański, P Żelasko, M Morzy, A Szymczak, M Żyła-Hoppe, ...
EMNLP 2020, 2020
552020
Structure of pauses in speech in the context of speaker verification and classification of speech type
M Igras-Cybulska, B Ziółko, P Żelasko, M Witkowski
EURASIP Journal on Audio, Speech, and Music Processing 2016, 1-16, 2016
512016
Adversarial attacks and defenses for speech recognition systems
P Żelasko, S Joshi, Y Shao, J Villalba, J Trmal, N Dehak, S Khudanpur
arXiv preprint arXiv:2103.17122, 2021
342021
Unsupervised speech segmentation and variable rate representation learning using segmental contrastive predictive coding
S Bhati, J Villalba, P Żelasko, L Moro-Velazquez, N Dehak
IEEE/ACM Transactions on Audio, Speech, and Language Processing 30, 2002-2014, 2022
282022
That sounds familiar: an analysis of phonetic representations transfer across languages
P Żelasko, L Moro-Velázquez, M Hasegawa-Johnson, O Scharenborg, ...
Interspeech 2020, 2020
272020
AGH corpus of Polish speech
P Żelasko, B Ziółko, T Jadczyk, D Skurzok
Language Resources and Evaluation 50, 585-601, 2016
272016
Lhotse: a speech data representation library for the modern deep learning ecosystem
P Żelasko, D Povey, J Trmal, S Khudanpur
NeurIPS 2021 Data-Centric AI Workshop, 2021
232021
Self-expressing autoencoders for unsupervised spoken term discovery
S Bhati, J Villalba, P Żelasko, N Dehak
Interspeech 2020, 2020
222020
How phonotactics affect multilingual and zero-shot asr performance
S Feng, P Żelasko, L Moro-Velázquez, A Abavisani, ...
ICASSP 2021-2021 IEEE International Conference on Acoustics, Speech and …, 2021
202021
Discovering phonetic inventories with crosslingual automatic speech recognition
P Żelasko, S Feng, LM Velazquez, A Abavisani, S Bhati, O Scharenborg, ...
Computer Speech & Language 74, 101358, 2022
162022
Speech recognition with next-generation kaldi (k2, lhotse, icefall)
D Povey, P Zelasko, S Khudanpur
Interspeech: tutorials, 2021
162021
Nie można teraz wykonać tej operacji. Spróbuj ponownie później.
Prace 1–20