Alert button
Picture for Laureano Moro-Velázquez

Laureano Moro-Velázquez

Alert button

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

Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification

Mar 30, 2022
Saurabh Kataria, Jesús Villalba, Laureano Moro-Velázquez, Najim Dehak

Figure 1 for Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Figure 2 for Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Figure 3 for Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Figure 4 for Joint domain adaptation and speech bandwidth extension using time-domain GANs for speaker verification
Viaarxiv icon

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
Viaarxiv icon

Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation

Apr 02, 2021
Siyuan Feng, Piotr Żelasko, Laureano Moro-Velázquez, Odette Scharenborg

Figure 1 for Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation
Figure 2 for Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation
Figure 3 for Unsupervised Acoustic Unit Discovery by Leveraging a Language-Independent Subword Discriminative Feature Representation
Viaarxiv icon

Adversarial Attacks and Defenses for Speaker Identification Systems

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

Figure 1 for Adversarial Attacks and Defenses for Speaker Identification Systems
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
Viaarxiv icon

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

Figure 1 for How Phonotactics Affect Multilingual and Zero-shot ASR Performance
Figure 2 for How Phonotactics Affect Multilingual and Zero-shot ASR Performance
Figure 3 for How Phonotactics Affect Multilingual and Zero-shot ASR Performance
Figure 4 for How Phonotactics Affect Multilingual and Zero-shot ASR Performance
Viaarxiv icon

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

Figure 1 for That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
Figure 2 for That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
Figure 3 for That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
Figure 4 for That Sounds Familiar: an Analysis of Phonetic Representations Transfer Across Languages
Viaarxiv icon