Piotr Zelasko

Publication Activity (10 Years)

Years Active: 2014-2024
Publications (10 Years): 72

Top Topics

Speaker Verification

Learning To Classify

Speech Recognition

Linguistically Motivated

Top Venues

Publications

Krishna C. Puvvada, Piotr Zelasko, He Huang, Oleksii Hrinchuk, Nithin Rao Koluguri, Kunal Dhawan, Somshubra Majumdar, Elena Rastorgueva, Zhehuai Chen, Vitaly Lavrukhin, Jagadeesh Balam, Boris Ginsburg
Less is More: Accurate Speech Recognition & Translation without Web-Scale Data. CoRR (2024)
Zhehuai Chen, He Huang, Oleksii Hrinchuk, Krishna C. Puvvada, Nithin Rao Koluguri, Piotr Zelasko, Jagadeesh Balam, Boris Ginsburg
BESTOW: Efficient and Streamable Speech Language Model with the Best of Two Worlds in GPT and T5. CoRR (2024)
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Piotr Zelasko, Najim Dehak
Time-Domain Speech Super-Resolution With GAN Based Modeling for Telephony Speaker Verification. IEEE ACM Trans. Audio Speech Lang. Process. 32 (2024)
Piotr Szymanski, Lukasz Augustyniak, Mikolaj Morzy, Adrian Szymczak, Krzysztof Surdyk, Piotr Zelasko
Why Aren't We NER Yet? Artifacts of ASR Errors in Named Entity Recognition in Spontaneous Speech Transcripts. ACL (1) (2023)
Wei Kang, Liyong Guo, Fangjun Kuang, Long Lin, Mingshuang Luo, Zengwei Yao, Xiaoyu Yang, Piotr Zelasko, Daniel Povey
Fast and Parallel Decoding for Transducer. ICASSP (2023)
Wei Kang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Long Lin, Piotr Zelasko, Daniel Povey
Delay-Penalized Transducer for Low-Latency Streaming ASR. ICASSP (2023)
Liyong Guo, Xiaoyu Yang, Quandong Wang, Yuxiang Kong, Zengwei Yao, Fan Cui, Fangjun Kuang, Wei Kang, Long Lin, Mingshuang Luo, Piotr Zelasko, Daniel Povey
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation. ICASSP (2023)
Wei Kang, Liyong Guo, Fangjun Kuang, Long Lin, Mingshuang Luo, Zengwei Yao, Xiaoyu Yang, Piotr Zelasko, Daniel Povey
Fast and parallel decoding for transducer. CoRR (2022)
Jaejin Cho, Raghavendra Pappagari, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
Non-Contrastive Self-Supervised Learning of Utterance-Level Speech Representations. CoRR (2022)
Jaejin Cho, Raghavendra Pappagari, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
Non-contrastive self-supervised learning of utterance-level speech representations. INTERSPEECH (2022)
Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Zelasko, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
Defense against Adversarial Attacks on Hybrid Speech Recognition System using Adversarial Fine-tuning with Denoiser. INTERSPEECH (2022)
Tianyu Cao, Laureano Moro-Velázquez, Piotr Zelasko, Jesús Villalba, Najim Dehak
Vsameter: Evaluation of a New Open-Source Tool to Measure Vowel Space Area and Related Metrics. SLT (2022)
Piotr Zelasko, Siyuan Feng, Laureano Moro-Velázquez, Ali Abavisani, Saurabhchand Bhati, Odette Scharenborg, Mark Hasegawa-Johnson, Najim Dehak
Discovering phonetic inventories with crosslingual automatic speech recognition. Comput. Speech Lang. 74 (2022)
Liyong Guo, Xiaoyu Yang, Quandong Wang, Yuxiang Kong, Zengwei Yao, Fan Cui, Fangjun Kuang, Wei Kang, Long Lin, Mingshuang Luo, Piotr Zelasko, Daniel Povey
Predicting Multi-Codebook Vector Quantization Indexes for Knowledge Distillation. CoRR (2022)
Wei Kang, Zengwei Yao, Fangjun Kuang, Liyong Guo, Xiaoyu Yang, Long Lin, Piotr Zelasko, Daniel Povey
Delay-penalized transducer for low-latency streaming ASR. CoRR (2022)
Piotr Zelasko, Siyuan Feng, Laureano Moro-Velázquez, Ali Abavisani, Saurabhchand Bhati, Odette Scharenborg, Mark Hasegawa-Johnson, Najim Dehak
Discovering Phonetic Inventories with Crosslingual Automatic Speech Recognition. CoRR (2022)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Unsupervised Speech Segmentation and Variable Rate Representation Learning Using Segmental Contrastive Predictive Coding. IEEE ACM Trans. Audio Speech Lang. Process. 30 (2022)
Sonal Joshi, Saurabh Kataria, Yiwen Shao, Piotr Zelasko, Jesús Villalba, Sanjeev Khudanpur, Najim Dehak
Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser. CoRR (2022)
Piotr Zelasko, Raghavendra Pappagari, Najim Dehak
What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition. CoRR (2021)
Jaejin Cho, Piotr Zelasko, Jesús Villalba, Najim Dehak
Improving Reconstruction Loss Based Speaker Embedding in Unsupervised and Semi-Supervised Scenarios. ICASSP (2021)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation. Interspeech (2021)
Raghavendra Pappagari, Piotr Zelasko, Agnieszka Mikolajczyk, Piotr Pezik, Najim Dehak
Joint Prediction of Truecasing and Punctuation for Conversational Speech in Low-Resource Scenarios. ASRU (2021)
Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
Beyond Isolated Utterances: Conversational Emotion Recognition. CoRR (2021)
Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
How Phonotactics Affect Multilingual and Zero-Shot ASR Performance. ICASSP (2021)
Piotr Zelasko, Raghavendra Pappagari, Najim Dehak
What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition. Trans. Assoc. Comput. Linguistics 9 (2021)
Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Odette Scharenborg
Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation. Interspeech (2021)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding. CoRR (2021)
Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak
Beyond Isolated Utterances: Conversational Emotion Recognition. ASRU (2021)
Raghavendra Pappagari, Piotr Zelasko, Agnieszka Mikolajczyk, Piotr Pezik, Najim Dehak
Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios. CoRR (2021)
Nanxin Chen, Shinji Watanabe, Jesús Villalba, Piotr Zelasko, Najim Dehak
Non-Autoregressive Transformer for Speech Recognition. IEEE Signal Process. Lett. 28 (2021)
Nanxin Chen, Piotr Zelasko, Laureano Moro-Velázquez, Jesús Villalba, Najim Dehak
Align-Denoise: Single-Pass Non-Autoregressive Speech Recognition. Interspeech (2021)
Sonal Joshi, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Adversarial Attacks and Defenses for Speaker Identification Systems. CoRR (2021)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation. CoRR (2021)
Piotr Zelasko, Daniel Povey, Jan "Yenda" Trmal, Sanjeev Khudanpur
Lhotse: a speech data representation library for the modern deep learning ecosystem. CoRR (2021)
Piotr Zelasko, Sonal Joshi, Yiwen Shao, Jesús Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur
Adversarial Attacks and Defenses for Speech Recognition Systems. CoRR (2021)
Miguel Del Rio, Natalie Delworth, Ryan Westerman, Michelle Huang, Nishchal Bhandari, Joseph Palakapilly, Quinten McNamara, Joshua Dong, Piotr Zelasko, Miguel Jette
Earnings-21: A Practical Benchmark for ASR in the Wild. CoRR (2021)
Jesús Villalba, Sonal Joshi, Piotr Zelasko, Najim Dehak
Representation Learning to Classify and Detect Adversarial Attacks Against Speaker and Speech Recognition Systems. Interspeech (2021)
Sonal Joshi, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Study of Pre-Processing Defenses Against Adversarial Attacks on State-of-the-Art Speaker Recognition Systems. IEEE Trans. Inf. Forensics Secur. 16 (2021)
Saurabh Kataria, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
Deep Feature CycleGANs: Speaker Identity Preserving Non-Parallel Microphone-Telephone Domain Adaptation for Speaker Verification. Interspeech (2021)
Nanxin Chen, Piotr Zelasko, Jesús Villalba, Najim Dehak
Focus on the Present: A Regularization Method for the ASR Source-Target Attention Layer. ICASSP (2021)
Miguel Del Rio, Natalie Delworth, Ryan Westerman, Michelle Huang, Nishchal Bhandari, Joseph Palakapilly, Quinten McNamara, Joshua Dong, Piotr Zelasko, Miguel Jette
Earnings-21: A Practical Benchmark for ASR in the Wild. Interspeech (2021)
Magdalena Rybicka, Jesús Villalba, Piotr Zelasko, Najim Dehak, Konrad Kowalczyk
Spine2Net: SpineNet with Res2Net and Time-Squeeze-and-Excitation Blocks for Speaker Recognition. Interspeech (2021)
Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Odette Scharenborg
Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation. CoRR (2021)
Raghavendra Pappagari, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
CopyPaste: An Augmentation Method for Speech Emotion Recognition. ICASSP (2021)
Raghavendra Pappagari, Jaejin Cho, Sonal Joshi, Laureano Moro-Velázquez, Piotr Zelasko, Jesús Villalba, Najim Dehak
Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource Scenarios. Interspeech (2021)
Lukasz Augustyniak, Piotr Szymanski, Mikolaj Morzy, Piotr Zelasko, Adrian Szymczak, Jan Mizgajski, Yishay Carmiel, Najim Dehak
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings? CoRR (2020)
Jaejin Cho, Piotr Zelasko, Jesús Villalba, Shinji Watanabe, Najim Dehak
Learning Speaker Embedding from Text-to-Speech. CoRR (2020)
Piotr Zelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
That Sounds Familiar: An Analysis of Phonetic Representations Transfer Across Languages. INTERSPEECH (2020)
Piotr Szymanski, Piotr Zelasko, Mikolaj Morzy, Adrian Szymczak, Marzena Zyla-Hoppe, Joanna Banaszczak, Lukasz Augustyniak, Jan Mizgajski, Yishay Carmiel
WER we are and WER we think we are. CoRR (2020)
Nanxin Chen, Piotr Zelasko, Jesús Villalba, Najim Dehak
Focus on the present: a regularization method for the ASR source-target attention layer. CoRR (2020)
Lukasz Augustyniak, Piotr Szymanski, Mikolaj Morzy, Piotr Zelasko, Adrian Szymczak, Jan Mizgajski, Yishay Carmiel, Najim Dehak
Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings? INTERSPEECH (2020)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Najim Dehak
Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery. INTERSPEECH (2020)
Saurabhchand Bhati, Jesús Villalba, Piotr Zelasko, Najim Dehak
Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery. CoRR (2020)
Jaejin Cho, Piotr Zelasko, Jesús Villalba, Shinji Watanabe, Najim Dehak
Learning Speaker Embedding from Text-to-Speech. INTERSPEECH (2020)
Raghavendra Pappagari, Jesús Villalba, Piotr Zelasko, Laureano Moro-Velázquez, Najim Dehak
CopyPaste: An Augmentation Method for Speech Emotion Recognition. CoRR (2020)
Ashish Arora, Desh Raj, Aswin Shanmugam Subramanian, Ke Li, Bar Ben-Yair, Matthew Maciejewski, Piotr Zelasko, Paola García, Shinji Watanabe, Sanjeev Khudanpur
The JHU Multi-Microphone Multi-Speaker ASR System for the CHiME-6 Challenge. CoRR (2020)
Piotr Zelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages. CoRR (2020)
Piotr Szymanski, Piotr Zelasko, Mikolaj Morzy, Adrian Szymczak, Marzena Zyla-Hoppe, Joanna Banaszczak, Lukasz Augustyniak, Jan Mizgajski, Yishay Carmiel
WER we are and WER we think we are. EMNLP (Findings) (2020)
Siyuan Feng, Piotr Zelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak
How Phonotactics Affect Multilingual and Zero-shot ASR Performance. CoRR (2020)
Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Yishay Carmiel, Najim Dehak
Hierarchical Transformers for Long Document Classification. ASRU (2019)
Piotr Zelasko, Jan Mizgajski, Mikolaj Morzy, Adrian Szymczak, Piotr Szymanski, Lukasz Augustyniak, Yishay Carmiel
Towards Better Understanding of Spontaneous Conversations: Overcoming Automatic Speech Recognition Errors With Intent Recognition. CoRR (2019)
Raghavendra Pappagari, Piotr Zelasko, Jesús Villalba, Yishay Carmiel, Najim Dehak
Hierarchical Transformers for Long Document Classification. CoRR (2019)
Jan Mizgajski, Adrian Szymczak, Robert Glowski, Piotr Szymanski, Piotr Zelasko, Lukasz Augustyniak, Mikolaj Morzy, Yishay Carmiel, Jeff Hodson, Lukasz Wójciak, Daniel Smoczyk, Adam Wróbel, Bartosz Borowik, Adam Artajew, Marcin Baran, Cezary Kwiatkowski, Marzena Zyla-Hoppe
Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations. INTERSPEECH (2019)
Jan Mizgajski, Adrian Szymczak, Robert Glowski, Piotr Szymanski, Piotr Zelasko, Lukasz Augustyniak, Mikolaj Morzy, Yishay Carmiel, Jeff Hodson, Lukasz Wójciak, Daniel Smoczyk, Adam Wróbel, Bartosz Borowik, Adam Artajew, Marcin Baran, Cezary Kwiatkowski, Marzena Zyla-Hoppe
Avaya Conversational Intelligence: A Real-Time System for Spoken Language Understanding in Human-Human Call Center Conversations. CoRR (2019)
Piotr Zelasko, Piotr Szymanski, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak
Punctuation Prediction Model for Conversational Speech. CoRR (2018)
Piotr Zelasko, Piotr Szymanski, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak
Punctuation Prediction Model for Conversational Speech. INTERSPEECH (2018)
Piotr Zelasko
Expanding Abbreviations in a Strongly Inflected Language: Are Morphosyntactic Tags Sufficient? LREC (2018)
Bartosz Ziólko, Piotr Zelasko, Ireneusz Gawlik, Tomasz Pedzimaz, Tomasz Jadczyk
An Application for Building a Polish Telephone Speech Corpus. LREC (2018)
Piotr Zelasko
LSTM Network for Inflected Abbreviation Expansion. CoRR (2017)
Marcin Witkowski, Stanislaw Kacprzak, Piotr Zelasko, Konrad Kowalczyk, Jakub Galka
Audio Replay Attack Detection Using High-Frequency Features. INTERSPEECH (2017)
Piotr Zelasko, Bartosz Ziólko, Tomasz Jadczyk, Dawid Skurzok
AGH corpus of Polish speech. Lang. Resour. Evaluation 50 (3) (2016)
Magdalena Igras, Bartosz Ziólko, Piotr Zelasko, Marcin Witkowski
Structure of pauses in speech in the context of speaker verification and classification of speech type. EURASIP J. Audio Speech Music. Process. 2016 (2016)
Piotr Zelasko, Bartosz Ziólko, Tomasz Jadczyk, Tomasz Pedzimaz
Linguistically motivated tied-state triphones for polish speech recognition. CYBCONF (2015)
Bartosz Ziólko, Tomasz Jadczyk, Dawid Skurzok, Piotr Zelasko, Jakub Galka, Tomasz Pedzimaz, Ireneusz Gawlik, Szymon Piotr Palka
SARMATA 2.0 automatic Polish language speech recognition system. INTERSPEECH (2015)
Piotr Zelasko, Tomasz Jadczyk, Bartosz Ziólko
HMM-based Breath and Filled Pauses Elimination in ASR. SIGMAP (2014)