Search Results for author:
Found 15 papers, 7 papers with code
Deep learning-based electroencephalography analysis: a systematic review
To help the field progress, we provide a list of recommendations for future studies and we make our summary table of DL and EEG papers available and invite the community to contribute.
Generalizing to unseen domains via distribution matching
In this work, we tackle such problem by focusing on domain generalization: a formalization where the data generating process at test time may yield samples from never-before-seen domains (distributions).
Ranked #61 on
Domain Generalization
on PACS
An Efficient End-to-End Approach to Noise Invariant Speech Features via Multi-Task Learning
Lastly, we show that the proposed recipe can be applied to other distillation methodologies, such as the recent DPWavLM.
Characterizing the temporal dynamics of universal speech representations for generalizable deepfake detection
Existing deepfake speech detection systems lack generalizability to unseen attacks (i. e., samples generated by generative algorithms not seen during training).
Generalizable Adversarial Examples Detection Based on Bi-model Decision Mismatch
Non-linear binary classifiers trained on top of our proposed features can achieve a high detection rate (>90%) in a set of white-box attacks and maintain such performance when tested against unseen attacks.
Learning to navigate image manifolds induced by generative adversarial networks for unsupervised video generation
Afterwards, a recurrent model is trained with the goal of providing a sequence of inputs to the previously trained frames generator, thus yielding scenes which look natural.
Cross-Subject Statistical Shift Estimation for Generalized Electroencephalography-based Mental Workload Assessment
Besides shedding light on the assumptions that hold for a particular dataset, the estimates of statistical shifts obtained with the proposed approach can be used for investigating other aspects of a machine learning pipeline, such as quantitatively assessing the effectiveness of domain adaptation strategies.
TILES-2018, a longitudinal physiologic and behavioral data set of hospital workers
We designed the study to investigate the use of off-the-shelf wearable and environmental sensors to understand individual-specific constructs such as job performance, interpersonal interaction, and well-being of hospital workers over time in their natural day-to-day job settings.
Improving the Robustness of DistilHuBERT to Unseen Noisy Conditions via Data Augmentation, Curriculum Learning, and Multi-Task Enhancement
Self-supervised speech representation learning aims to extract meaningful factors from the speech signal that can later be used across different downstream tasks, such as speech and/or emotion recognition.
RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment Robustness
The proposed layer-wise distillation recipe is evaluated on top of three well-established universal representations, as well as with three downstream tasks.
On the Impact of Voice Anonymization on Speech-Based COVID-19 Detection
With advances seen in deep learning, voice-based applications are burgeoning, ranging from personal assistants, affective computing, to remote disease diagnostics.
An Exploration into the Performance of Unsupervised Cross-Task Speech Representations for "In the Wild'' Edge Applications
Later, these representations serve as input to downstream models to solve a number of tasks, such as keyword spotting or emotion recognition.
VIC-KD: Variance-Invariance-Covariance Knowledge Distillation to Make Keyword Spotting More Robust Against Adversarial Attacks
Keyword spotting (KWS) refers to the task of identifying a set of predefined words in audio streams.
On the Impact of Quantization and Pruning of Self-Supervised Speech Models for Downstream Speech Recognition Tasks "In-the-Wild''
Recent advances with self-supervised learning have allowed speech recognition systems to achieve state-of-the-art (SOTA) word error rates (WER) while requiring only a fraction of the labeled training data needed by its predecessors.
MSPB: a longitudinal multi-sensor dataset with phenotypic trait measurements from honey bees
We then provide an overview of the phenotypic data distribution as well as a visualization of the sensor data patterns.
