Najim Dehak

The JHU submission to VoxSRC-21: Track 3

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

Figure 2 for The JHU submission to VoxSRC-21: Track 3

Access Paper or Ask Questions

Beyond Isolated Utterances: Conversational Emotion Recognition

Sep 13, 2021
Raghavendra Pappagari, Piotr Żelasko, Jesús Villalba, Laureano Moro-Velazquez, Najim Dehak

Figure 2 for Beyond Isolated Utterances: Conversational Emotion Recognition

Figure 3 for Beyond Isolated Utterances: Conversational Emotion Recognition

Figure 4 for Beyond Isolated Utterances: Conversational Emotion Recognition

* 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

Figure 2 for Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios

Figure 3 for Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios

Figure 4 for Joint prediction of truecasing and punctuation for conversational speech in low-resource scenarios

* 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
Jesús Villalba, Sonal Joshi, Piotr Żelasko, Najim Dehak

Figure 2 for Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems

Figure 3 for Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems

Figure 4 for Representation Learning to Classify and Detect Adversarial Attacks against Speaker and Speech Recognition Systems

* 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 Żelasko, Raghavendra Pappagari, Najim Dehak

Figure 1 for What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

Figure 2 for What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

Figure 3 for What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

Figure 4 for What Helps Transformers Recognize Conversational Structure? Importance of Context, Punctuation, and Labels in Dialog Act Recognition

* 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

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

Figure 3 for WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

Figure 4 for WaveGrad 2: Iterative Refinement for Text-to-Speech Synthesis

* Proceedings of INTERSPEECH

Access Paper or Ask Questions

Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

Jun 03, 2021
Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velazquez, Najim Dehak

Figure 2 for Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

Figure 3 for Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

Figure 4 for Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation

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

Figure 1 for Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification

Figure 2 for Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification

Figure 3 for Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification

Figure 4 for Deep Feature CycleGANs: Speaker Identity Preserving Non-parallel Microphone-Telephone Domain Adaptation for Speaker Verification

Access Paper or Ask Questions

Adversarial Attacks and Defenses for Speech Recognition Systems

Mar 31, 2021
Piotr Żelasko, 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

Figure 2 for Adversarial Attacks and Defenses for Speaker Identification Systems

Figure 3 for Adversarial Attacks and Defenses for Speaker Identification Systems

Figure 4 for Adversarial Attacks and Defenses for Speaker Identification Systems

* 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