Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Najim Dehak

Unsupervised Speech Segmentation and Variable Rate Representation Learning using Segmental Contrastive Predictive Coding


Oct 08, 2021
Saurabhchand Bhati, Jes├║s Villalba, Piotr ┼╗elasko, Laureano Moro-Velazquez, Najim Dehak

* arXiv admin note: substantial text overlap with arXiv:2106.02170 

  Access Paper or Ask Questions

The JHU submission to VoxSRC-21: Track 3


Sep 28, 2021
Jejin Cho, Jesus Villalba, Najim Dehak


  Access Paper or Ask Questions

Beyond Isolated Utterances: Conversational Emotion Recognition


Sep 13, 2021
Raghavendra Pappagari, Piotr ┼╗elasko, Jes├║s Villalba, Laureano Moro-Velazquez, Najim Dehak

* Accepted for ASRU 2021 

  Access Paper or Ask Questions

Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios


Sep 13, 2021
Raghavendra Pappagari, Piotr Żelasko, Agnieszka Mikołajczyk, Piotr Pęzik, Najim Dehak

* Accepted for ASRU 2021 

  Access Paper or Ask Questions

Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems


Jul 09, 2021
Jes├║s Villalba, Sonal Joshi, Piotr ┼╗elasko, Najim Dehak

* Accepted at Interspeech 2021 

  Access Paper or Ask Questions

What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition


Jul 05, 2021
Piotr ┼╗elasko, Raghavendra Pappagari, Najim Dehak

* Accepted for publication in Transactions of the Association of Computational Linguistics. This is a pre-MIT Press publication version and it is subject to change 

  Access Paper or Ask Questions

WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis


Jun 19, 2021
Nanxin Chen, Yu Zhang, Heiga Zen, Ron J. Weiss, Mohammad Norouzi, Najim Dehak, William Chan

* Proceedings of INTERSPEECH 

  Access Paper or Ask Questions

Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation


Jun 03, 2021
Saurabhchand Bhati, Jes├║s Villalba, Piotr ┼╗elasko, Laureano Moro-Velazquez, Najim Dehak


  Access Paper or Ask Questions

Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification


Apr 03, 2021
Saurabh Kataria, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velázquez, Najim Dehak


  Access Paper or Ask Questions

Adversarial Attacks and Defenses for Speech Recognition Systems


Mar 31, 2021
Piotr ┼╗elasko, Sonal Joshi, Yiwen Shao, Jesus Villalba, Jan Trmal, Najim Dehak, Sanjeev Khudanpur

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

Adversarial Attacks and Defenses for Speaker Identification Systems


Jan 22, 2021
Sonal Joshi, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velázquez, Najim Dehak

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

Focus on the present: a regularization method for the ASR source-target attention layer


Nov 02, 2020
Nanxin Chen, Piotr ┼╗elasko, Jes├║s Villalba, Najim Dehak

* submitted to ICASSP2021. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works 

  Access Paper or Ask Questions

CopyPaste: An Augmentation Method for Speech Emotion Recognition


Oct 27, 2020
Raghavendra Pappagari, Jes├║s Villalba, Piotr ┼╗elasko, Laureano Moro-Velazquez, Najim Dehak

* Under ICASSP2021 peer-review 

  Access Paper or Ask Questions

How Phonotactics Affect Multilingual and Zero-shot ASR Performance


Oct 22, 2020
Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez, Ali Abavisani, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak

* Submitted to ICASSP 2021. The first 2 authors contributed equally to this work 

  Access Paper or Ask Questions

Learning Speaker Embedding from Text-to-Speech


Oct 21, 2020
Jaejin Cho, Piotr Zelasko, Jesus Villalba, Shinji Watanabe, Najim Dehak


  Access Paper or Ask Questions

Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery


Jul 26, 2020
Saurabhchand Bhati, Jes├║s Villalba, Piotr ┼╗elasko, Najim Dehak


  Access Paper or Ask Questions

That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages


May 16, 2020
Piotr Żelasko, Laureano Moro-Velázquez, Mark Hasegawa-Johnson, Odette Scharenborg, Najim Dehak

* Submitted to Interspeech 2020. For some reason, the ArXiv Latex engine rendered it in more than 4 pages 

  Access Paper or Ask Questions

Punctuation Prediction in Spontaneous Conversations: Can We Mitigate ASR Errors with Retrofitted Word Embeddings?


Apr 13, 2020
Łukasz Augustyniak, Piotr Szymanski, Mikołaj Morzy, Piotr Zelasko, Adrian Szymczak, Jan Mizgajski, Yishay Carmiel, Najim Dehak

* submitted to INTERSPEECH'20 

  Access Paper or Ask Questions

x-vectors meet emotions: A study on dependencies between emotion and speaker recognition


Feb 12, 2020
Raghavendra Pappagari, Tianzi Wang, Jesus Villalba, Nanxin Chen, Najim Dehak

* 45th International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2020 

  Access Paper or Ask Questions

Non-Autoregressive Transformer Automatic Speech Recognition


Nov 10, 2019
Nanxin Chen, Shinji Watanabe, Jes├║s Villalba, Najim Dehak


  Access Paper or Ask Questions

Hierarchical Transformers for Long Document Classification


Oct 23, 2019
Raghavendra Pappagari, Piotr ┼╗elasko, Jes├║s Villalba, Yishay Carmiel, Najim Dehak

* Automatic Speech Recognition and Understanding Workshop, 2019 
* 4 figures, 7 pages 

  Access Paper or Ask Questions

rVAD: An Unsupervised Segment-Based Robust Voice Activity Detection Method


Jun 09, 2019
Zheng-Hua Tan, Achintya kr. Sarkar, Najim Dehak

* Computer Speech & Language, 2019 
* Paper is to appear in CSL 

  Access Paper or Ask Questions

Speaker Sincerity Detection based on Covariance Feature Vectors and Ensemble Methods


Apr 26, 2019
Mohammed Senoussaoui, Patrick Cardinal, Najim Dehak, Alessandro Lameiras Koerich


  Access Paper or Ask Questions

ASSERT: Anti-Spoofing with Squeeze-Excitation and Residual neTworks


Apr 01, 2019
Cheng-I Lai, Nanxin Chen, Jes├║s Villalba, Najim Dehak

* Submitted to Interspeech 2019, Graz, Austria 

  Access Paper or Ask Questions

Low Resource Multi-modal Data Augmentation for End-to-end ASR


Dec 10, 2018
Matthew Wiesner, Adithya Renduchintala, Shinji Watanabe, Chunxi Liu, Najim Dehak, Sanjeev Khudanpur

* This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible 

  Access Paper or Ask Questions

Attentive Filtering Networks for Audio Replay Attack Detection


Oct 31, 2018
Cheng-I Lai, Alberto Abad, Korin Richmond, Junichi Yamagishi, Najim Dehak, Simon King

* Submitted to ICASSP 2019 

  Access Paper or Ask Questions

Low-Resource Contextual Topic Identification on Speech


Sep 28, 2018
Chunxi Liu, Matthew Wiesner, Shinji Watanabe, Craig Harman, Jan Trmal, Najim Dehak, Sanjeev Khudanpur

* Accepted for publication at 2018 IEEE Workshop on Spoken Language Technology (SLT) 

  Access Paper or Ask Questions

Punctuation Prediction Model for Conversational Speech


Jul 02, 2018
Piotr Żelasko, Piotr Szymański, Jan Mizgajski, Adrian Szymczak, Yishay Carmiel, Najim Dehak

* Accepted for Interspeech 2018 Conference 

  Access Paper or Ask Questions

Automatic Speech Recognition and Topic Identification for Almost-Zero-Resource Languages


Jun 18, 2018
Matthew Wiesner, Chunxi Liu, Lucas Ondel, Craig Harman, Vimal Manohar, Jan Trmal, Zhongqiang Huang, Najim Dehak, Sanjeev Khudanpur

* Accepted for publication at Interspeech 2018 

  Access Paper or Ask Questions

An Empirical Evaluation of Zero Resource Acoustic Unit Discovery


Feb 05, 2017
Chunxi Liu, Jinyi Yang, Ming Sun, Santosh Kesiraju, Alena Rott, Lucas Ondel, Pegah Ghahremani, Najim Dehak, Lukas Burget, Sanjeev Khudanpur

* 5 pages, 1 figure; Accepted for publication at ICASSP 2017 

  Access Paper or Ask Questions