J. Villalba

发表

Preventing replay attacks on speaker verification systems

Eduardo Lleida, Jesus Villalba, J. Villalba, 2011, 2011 Carnahan Conference on Security Technology.

State-of-the-Art Speaker Recognition for Telephone and Video Speech: The JHU-MIT Submission for NIST SRE18

Sanjeev Khudanpur, Alan McCree, Daniel Garcia-Romero, 2019, INTERSPEECH.

Feature Enhancement with Deep Feature Losses for Speaker Verification

Nanxin Chen, Jes'us Villalba, Najim Dehak, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Non-Autoregressive Transformer for Speech Recognition

Piotr Żelasko, Shinji Watanabe, Najim Dehak, 2021, IEEE Signal Processing Letters.

Speaker verification and identification using Phoneme Dependent Multi-Environment Models based LInear Normalization in adverse and dynamic acoustic environments

J. Villalba, L. Buera, A. Miguel, 2005 .

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

Piotr Żelasko, J. Villalba, Saurabh Kataria, 2022, 2209.01702.

A forced gaussians based methodology for the differential evaluation of Parkinson's Disease by means of speech processing

Juan Ignacio Godino-Llorente, Najim Dehak, Jesús Villalba, 2019, Biomed. Signal Process. Control..

Using X-Vectors to Automatically Detect Parkinson’s Disease from Speech

Najim Dehak, Jesús Villalba, Laureano Moro-Velázquez, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

End-to-end Deep Neural Network Age Estimation

Sanjeev Khudanpur, Daniel Povey, Nanxin Chen, 2018, INTERSPEECH.

Measuring Uncertainty in Deep Regression Models: The Case of Age Estimation from Speech

Nanxin Chen, Najim Dehak, Jesús Villalba, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

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

L. Burget, H. Hermansky, J. Villalba, 2023, arXiv.org.

Unclonable photonic keys hardened against machine learning attacks

Najim Dehak, Jesús Villalba, Mark A. Foster, 2020 .

Perceptual Loss Based Speech Denoising with an Ensemble of Audio Pattern Recognition and Self-Supervised Models pdf

Saurabh Kataria, Jes'us Villalba, Najim Dehak, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Diarization is Hard: Some Experiences and Lessons Learned for the JHU Team in the Inaugural DIHARD Challenge

Shinji Watanabe, Sanjeev Khudanpur, Alan McCree, 2018, INTERSPEECH.

State-of-the-art speaker recognition with neural network embeddings in NIST SRE18 and Speakers in the Wild evaluations

Alan McCree, Daniel Garcia-Romero, Gregory Sell, 2020, Comput. Speech Lang..

Analysis of Deep Feature Loss based Enhancement for Speaker Verification

J. Villalba, Saurabh Kataria, P. S. Nidadavolu, 2020, Odyssey.

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

J. Villalba, Saurabh Kataria, N. Dehak, 2023, INTERSPEECH 2023.

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

Piotr Żelasko, J. Villalba, Saurabh Kataria, 2021, Interspeech.

Single Channel Far Field Feature Enhancement For Speaker Verification In The Wild pdf

L. Paola García-Perera, Najim Dehak, Phani Sankar Nidadavolu, 2020, ArXiv.

Speaker detection in the wild: Lessons learned from JSALT 2019 pdf

Xin Wang, Jun Du, Kong Aik Lee, 2019, Odyssey.

Unsupervised Feature Enhancement for Speaker Verification

Leibny Paola García-Perera, J. Villalba, Saurabh Kataria, 2019, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Low-Resource Domain Adaptation for Speaker Recognition Using Cycle-Gans

J. Villalba, Saurabh Kataria, P. S. Nidadavolu, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

The JHU Speaker Recognition System for the VOiCES 2019 Challenge

Sanjeev Khudanpur, Daniel Povey, Nanxin Chen, 2019, INTERSPEECH.

The JHU-MIT System Description for NIST SRE18

Alan McCree, Daniel Garcia-Romero, Nanxin Chen, 2019 .

Effectiveness of Single-Channel BLSTM Enhancement for Language Identification

Shinji Watanabe, Zheng-Hua Tan, Najim Dehak, 2018, INTERSPEECH.

Non-Autoregressive Transformer for Speech Recognition

Shinji Watanabe, Nanxin Chen, Najim Dehak, 2021, IEEE Signal Processing Letters.

Hierarchical Transformers for Long Document Classification

Jes'us Villalba, Najim Dehak, Raghavendra Pappagari, 2019, 2019 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

X-Vectors Meet Emotions: A Study On Dependencies Between Emotion and Speaker Recognition

Nanxin Chen, Najim Dehak, Raghavendra Pappagari, 2020, ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Align-Denoise: Single-Pass Non-Autoregressive Speech Recognition

Piotr Żelasko, J. Villalba, Nanxin Chen, 2021, Interspeech.

Listen and Fill in the Missing Letters: Non-Autoregressive Transformer for Speech Recognition

Shinji Watanabe, J. Villalba, Nanxin Chen, 2019, ArXiv.

CopyPaste: An Augmentation Method for Speech Emotion Recognition

Jes'us Villalba, Najim Dehak, Raghavendra Pappagari, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Focus on the Present: A Regularization Method for the ASR Source-Target Attention Layer pdf

Nanxin Chen, Jes'us Villalba, Najim Dehak, 2020, ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Adversarial Attacks and Defenses for Speech Recognition Systems pdf

Sanjeev Khudanpur, Najim Dehak, Sonal Joshi, 2021, ArXiv.

Segmental Contrastive Predictive Coding for Unsupervised Word Segmentation pdf

Jes'us Villalba, Najim Dehak, Piotr .Zelasko, 2021, Interspeech.

Defense against Adversarial Attacks on Hybrid Speech Recognition using Joint Adversarial Fine-tuning with Denoiser

S. Khudanpur, Piotr Żelasko, J. Villalba, 2022, ArXiv.

AdvEst: Adversarial Perturbation Estimation to Classify and Detect Adversarial Attacks against Speaker Identification

J. Villalba, Saurabh Kataria, Sonal Joshi, 2022, INTERSPEECH.

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

Jes'us Villalba, Najim Dehak, Sonal Joshi, 2021, Interspeech.

Adversarial Attacks and Defenses for Speaker Identification Systems

Najim Dehak, Sonal Joshi, Piotr .Zelasko, 2021, ArXiv.

x-Vectors Meet Adversarial Attacks: Benchmarking Adversarial Robustness in Speaker Verification

Yuekai Zhang, Najim Dehak, Jesús Villalba, 2020, INTERSPEECH.

Black-Box Attacks on Spoofing Countermeasures Using Transferability of Adversarial Examples

Yuekai Zhang, Najim Dehak, Jesús Villalba, 2020, INTERSPEECH.

Multilingual evaluation of interpretable biomarkers to represent language and speech patterns in Parkinson's disease

R. Stevens, J. Villalba, Tianyu Cao, 2023, Frontiers in Neurology.

Deep Neural Networks for Emotion Recognition Combining Audio and Transcripts

Najim Dehak, Raghavendra Pappagari, Jesús Villalba, 2018, INTERSPEECH.

Bottom-Up Unsupervised Word Discovery via Acoustic Units

Sanjeev Khudanpur, Najim Dehak, Chunxi Liu, 2019, 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

Automatic Detection and Assessment of Alzheimer Disease Using Speech and Language Technologies in Low-Resource Scenarios

Najim Dehak, Raghavendra Pappagari, Jesús Villalba, 2021, Interspeech.

Regularizing Contrastive Predictive Coding for Speech Applications

Piotr Żelasko, J. Villalba, N. Dehak, 2023, 2304.05974.

Self-Expressing Autoencoders for Unsupervised Spoken Term Discovery

Jes'us Villalba, Najim Dehak, Piotr .Zelasko, 2020, INTERSPEECH.

Investigation on Neural Bandwidth Extension of Telephone Speech for Improved Speaker Recognition

Najim Dehak, Jesús Villalba, Phani Sankar Nidadavolu, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

LSTM Siamese Network for Parkinson’s Disease Detection from Speech

Najim Dehak, Jesús Villalba, Laureano Moro-Velázquez, 2019, 2019 IEEE Global Conference on Signal and Information Processing (GlobalSIP).

Cycle-GANs for Domain Adaptation of Acoustic Features for Speaker Recognition

Najim Dehak, Jesús Villalba, Phani Sankar Nidadavolu, 2019, ICASSP 2019 - 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Interpretable Speech Features vs. DNN Embeddings: What to Use in the Automatic Assessment of Parkinson's Disease in Multi-lingual Scenarios

J. Villalba, A. Butala, N. Dehak, 2023, medRxiv.

Non-Autoregressive Transformer Automatic Speech Recognition

Shinji Watanabe, Nanxin Chen, Jes'us Villalba, 2019, 1911.04908.

Learning Speaker Embedding from Text-to-Speech pdf

Shinji Watanabe, Najim Dehak, Jesus Villalba, 2020, INTERSPEECH.

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

Nanxin Chen, Najim Dehak, Jesús Villalba, 2019, INTERSPEECH.

A Multi-Modal Array of Interpretable Features to Evaluate Language and Speech Patterns in Different Neurological Disorders

R. Stevens, J. Villalba, Tianyu Cao, 2023, 2022 IEEE Spoken Language Technology Workshop (SLT).

Study of Pre-Processing Defenses Against Adversarial Attacks on State-of-the-Art Speaker Recognition Systems

Piotr Żelasko, J. Villalba, Sonal Joshi, 2021, IEEE Transactions on Information Forensics and Security.

Joint Verification-Identification in end-to-end Multi-Scale CNN Framework for Topic Identification

Najim Dehak, Raghavendra Pappagari, Jesús Villalba, 2018, 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).

Analysis of speaker recognition methodologies and the influence of kinetic changes to automatically detect Parkinson's Disease

Juan Ignacio Godino-Llorente, Juan R. Orozco-Arroyave, Najim Dehak, 2018, Appl. Soft Comput..

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

J. Villalba, N. Dehak, L. Moro-Velázquez, 2023, ArXiv.

Segmental SpeechCLIP: Utilizing Pretrained Image-text Models for Audio-Visual Learning

J. Villalba, N. Dehak, L. Moro-Velázquez, 2023, INTERSPEECH 2023.

Non-Contrastive Self-Supervised Learning for Utterance-Level Information Extraction From Speech

J. Villalba, Jaejin Cho, N. Dehak, 2022, IEEE Journal of Selected Topics in Signal Processing.

End-to-End Neural Speaker Diarization with an Iterative Refinement of Non-Autoregressive Attention-based Attractors

J. Villalba, K. Kowalczyk, N. Dehak, 2022, INTERSPEECH.

Beyond Isolated Utterances: Conversational Emotion Recognition pdf

Jes'us Villalba, Najim Dehak, Raghavendra Pappagari, 2021, 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Chunking Defense for Adversarial Attacks on ASR

S. Khudanpur, J. Villalba, Saurabh Kataria, 2022, INTERSPEECH.

Investigation on Bandwidth Extension for Speaker Recognition

Najim Dehak, Jesús Villalba, Phani Sankar Nidadavolu, 2018, INTERSPEECH.

Joint Energy-Based Model for Robust Speech Classification System Against Dirty-Label Backdoor Poisoning Attacks

S. Khudanpur, J. Villalba, Martin Sustek, 2023, 2023 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU).

Unsupervised adaptation of PLDA models for broadcast diarization

Eduardo Lleida, Antonio Miguel, Jesús Villalba, 2019, EURASIP Journal on Audio, Speech, and Music Processing.

Vsameter: Evaluation of a New Open-Source Tool to Measure Vowel Space Area and Related Metrics

Piotr Żelasko, J. Villalba, Tianyu Cao, 2023, 2022 IEEE Spoken Language Technology Workshop (SLT).