Alert button
Picture for Najim Dehak

Najim Dehak

Alert button

Time Scale Network: A Shallow Neural Network For Time Series Data

Nov 10, 2023
Trevor Meyer, Camden Shultz, Najim Dehak, Laureano Moro-Velazquez, Pedro Irazoqui

Figure 1 for Time Scale Network: A Shallow Neural Network For Time Series Data
Figure 2 for Time Scale Network: A Shallow Neural Network For Time Series Data
Figure 3 for Time Scale Network: A Shallow Neural Network For Time Series Data
Figure 4 for Time Scale Network: A Shallow Neural Network For Time Series Data
Viaarxiv icon

DPM-TSE: A Diffusion Probabilistic Model for Target Sound Extraction

Oct 10, 2023
Jiarui Hai, Helin Wang, Dongchao Yang, Karan Thakkar, Najim Dehak, Mounya Elhilali

Viaarxiv icon

Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning

Sep 08, 2023
Saurabhchand Bhati, Jesús Villalba, Laureano Moro-Velazquez, Thomas Thebaud, Najim Dehak

Figure 1 for Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning
Figure 2 for Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning
Figure 3 for Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning
Figure 4 for Leveraging Pretrained Image-text Models for Improving Audio-Visual Learning
Viaarxiv icon

DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model

Jun 18, 2023
Helin Wang, Thomas Thebaud, Jesus Villalba, Myra Sydnor, Becky Lammers, Najim Dehak, Laureano Moro-Velazquez

Figure 1 for DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
Figure 2 for DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
Figure 3 for DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
Figure 4 for DuTa-VC: A Duration-aware Typical-to-atypical Voice Conversion Approach with Diffusion Probabilistic Model
Viaarxiv icon

Regularizing Contrastive Predictive Coding for Speech Applications

Apr 26, 2023
Saurabhchand Bhati, Jesús Villalba, Piotr Żelasko, Laureano Moro-Velazquez, Najim Dehak

Figure 1 for Regularizing Contrastive Predictive Coding for Speech Applications
Figure 2 for Regularizing Contrastive Predictive Coding for Speech Applications
Figure 3 for Regularizing Contrastive Predictive Coding for Speech Applications
Figure 4 for Regularizing Contrastive Predictive Coding for Speech Applications
Viaarxiv icon

Stabilized training of joint energy-based models and their practical applications

Mar 07, 2023
Martin Sustek, Samik Sadhu, Lukas Burget, Hynek Hermansky, Jesus Villalba, Laureano Moro-Velazquez, Najim Dehak

Figure 1 for Stabilized training of joint energy-based models and their practical applications
Figure 2 for Stabilized training of joint energy-based models and their practical applications
Figure 3 for Stabilized training of joint energy-based models and their practical applications
Figure 4 for Stabilized training of joint energy-based models and their practical applications
Viaarxiv icon

Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition

Mar 07, 2023
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Thomas Thebaud, Najim Dehak

Figure 1 for Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Figure 2 for Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Figure 3 for Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Figure 4 for Self-FiLM: Conditioning GANs with self-supervised representations for bandwidth extension based speaker recognition
Viaarxiv icon

Time-domain speech super-resolution with GAN based modeling for telephony speaker verification

Sep 04, 2022
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Piotr Żelasko, Najim Dehak

Figure 1 for Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
Figure 2 for Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
Figure 3 for Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
Figure 4 for Time-domain speech super-resolution with GAN based modeling for telephony speaker verification
Viaarxiv icon

Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech

Aug 10, 2022
Jaejin Cho, Jes'us Villalba, Laureano Moro-Velazquez, Najim Dehak

Figure 1 for Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Figure 2 for Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Figure 3 for Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Figure 4 for Non-Contrastive Self-supervised Learning for Utterance-Level Information Extraction from Speech
Viaarxiv icon