Publications associées à Cross-transfer Knowledge between Speech and Text Encoders to Evaluate Customer Satisfaction

Publications associées (22)

Unsupervised Multi-view UAV Image Geo-localization via Iterative Rendering

Unmanned Aerial Vehicle (UAV) Cross-View Geo-Localization (CVGL) poses significant challenges due to the substantial view discrepancies between oblique UAV images and overhead satellite images. Existing methods heavily rely on supervised learning with labe ...

2025

Mitigating imaging systematics for DESI 2024 emission Line Galaxies and beyond

Jiaxi Yu

Emission Line Galaxies (ELGs) are one of the main tracers that the Dark Energy Spectroscopic Instrument (DESI) uses to probe the universe. However, they are afflicted by strong spurious correlations between target density and observing conditions known as ...

IOP Publishing2025

Auto-Bidding in Real-Time Auctions via Oracle Imitation Learning

Alberto Silvio Chiappa

Online advertising has become one of the most successful business models of the internet era. Impression opportunities are typically allocated through real-time auctions, where advertisers bid to secure advertisement slots. Deciding the best bid for an imp ...

ACM2025

Abstract B037: AI-powered virtual tissues from spatial proteomics for clinical diagnostics and biomedical discovery

Eeshaan Jain, Johann Clemens Werner Wenckstern, Charlotte Cäcilie Gertrud Bunne

Spatial proteomics technologies have transformed our understanding of complex tissue architectures by enabling simultaneous analysis of multiple molecular markers and their spatial organization. The high dimensionality of these data, varying marker combina ...

American Association for Cancer Research (AACR)2025

Physics-informed neural network estimation of material properties in soft tissue nonlinear biomechanical models

Alfio Quarteroni

The development of biophysical models for clinical applications is rapidly advancing in the research community, thanks to their predictive nature and their ability to assist the interpretation of clinical data. However, high-resolution and accurate multi-p ...

SPRINGER2024

Universal Neural-Cracking-Machines: Self-Configurable Password Models from Auxiliary Data

Carmela González Troncoso, Dario Pasquini

We introduce the concept of "universal"password model - a password model that, once pre-trained, can automatically adapt its guessing strategy based on the target system. To achieve this, the model does not need to access any plaintext passwords from the t ...

Institute of Electrical and Electronics Engineers Inc.2024

Where the White Continent Is Blue: Deep Learning Locates Bare Ice in Antarctica

Devis Tuia, Marc Conrad Russwurm

In some areas of Antarctica, blue-colored bare ice is exposed at the surface. These blue ice areas (BIAs) can trap meteorites or old ice and are vital for understanding the climatic history. By combining multi-sensor remote sensing data (MODIS, RADARSAT-2, ...

Amer Geophysical Union2024

Stabilization of nonlinear systems by neural Lyapunov approximators and Sontag's formula

Adriano Mele

This note describes a method to train a Neural Network so that it approximates a control Lyapunov function for a nonlinear system in affine form. The network is trained in a physics-informed fashion, as the training data are generated by enforcing the nega ...

Institute of Electrical and Electronics Engineers Inc.2024

WildCLIP: Scene and Animal Attribute Retrieval from Camera Trap Data with Domain-Adapted Vision-Language Models

Devis Tuia, Alexander Mathis, Marc Conrad Russwurm, Valentin Alexandre Guy Gabeff

Wildlife observation with camera traps has great potential for ethology and ecology, as it gathers data non-invasively in an automated way. However, camera traps produce large amounts of uncurated data, which is time-consuming to annotate. Existing methods ...

2024

Empirical Sample Complexity of Neural Network Mixed State Reconstruction

Giuseppe Carleo, Filippo Vicentini

Quantum state reconstruction using Neural Quantum States has been proposed as a viable tool to reduce quantum shot complexity in practical applications, and its advantage over competing techniques has been shown in numerical experiments focusing mainly on ...

Verein Forderung Open Access Publizierens Quantenwissenschaf2024

Regularization Techniques for Low-Resource Machine Translation

Alejandro Ramírez Atrio

Neural machine translation (MT) and text generation have recently reached very high levels of quality. However, both areas share a problem: in order to reach these levels, they require massive amounts of data. When this is not present, they lack generaliza ...

EPFL2023

Combining biophysical models and machine learning to optimize implant geometry and stimulation protocol for intraneural electrodes

Silvestro Micera, Simone Romeni

Objective. Peripheral nerve interfaces have the potential to restore sensory, motor, and visceral functions. In particular, intraneural interfaces allow targeting deep neural structures with high selectivity, even if their performance strongly depends upon ...

IOP Publishing Ltd2023

3D reconstruction of curvilinear one-dimensional objects viewed in transmission electron microscopy

Gulnaz Ganeeva

To obtain a more complete understanding of material microstructure at the nanoscale and to gain profound insights into their properties, there is a growing need for more efficient and precise methods that can streamline the process of 3D imaging using a tr ...

EPFL2023

Spatial-Temporal Graph Attention Fuser for Calibration in IoT Air Pollution Monitoring Systems

Olga Fink, Mengjie Zhao, Keivan Faghih Niresi

The use of Internet of Things (IoT) sensors for air pollution monitoring has significantly increased, resulting in the deployment of low-cost sensors. Despite this advancement, accurately calibrating these sensors in uncontrolled environmental conditions r ...

Institute of Electrical and Electronics Engineers2023

Low-Level Physiological Implications of End-to-End Learning of Speech Recognition

Philip Neil Garner

Current speech recognition architectures perform very well from the point of view of machine learning, hence user interaction. This suggests that they are emulating the human biological system well. We investigate whether the inference can be inverted to p ...

ISCA-INT SPEECH COMMUNICATION ASSOC2022

Artificial Intelligence Based Methods for Smart and Sustainable Urban Planning: A Systematic Survey

Jérôme Chenal

The world's cities are facing various challenges such as rapid urbanization, poverty, climate change, pollution, sustainable and inclusive development. Building futuristic smart and sustainable cities is proving to be a response to these challenges. Recent ...

SPRINGER2022

Investigation of effective processes parameters on lead (II) adsorption from wastewater by biochar in mild air oxidation pyrolysis process

Farzaneh Talebkeikhah, Mohsen Talebkeikhah

This study evaluates and compares several machine learning methods on the effects of different parameters in lead adsorption capacity. pH, contact time, adsorbent dosage and initial lead concentration were considered as inputs and adsorption capacity was r ...

TAYLOR & FRANCIS LTD2022

A Methodology for Evaluating the Robustness of Anomaly Detectors to Adversarial Attacks in Industrial Scenarios

Javier Alejandro Maroto Morales

Anomaly Detection systems based on Machine and Deep learning are the most promising solutions to detect cyberattacks in the industry. However, these techniques are vulnerable to adversarial attacks that downgrade prediction performance. Several techniques ...

IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC2022

Adversarial-Free Speaker Identity-Invariant Representation Learning for Automatic Dysarthric Speech Classification

Ina Kodrasi

Speech representations which are robust to pathology-unrelated cues such as speaker identity information have been shown to be advantageous for automatic dysarthric speech classification. A recently proposed technique to learn speaker identity-invariant re ...

ISCA-INT SPEECH COMMUNICATION ASSOC2022

Self-Attentive Spatial Adaptive Normalization for Cross-Modality Domain Adaptation

Jean-Philippe Thiran, Seyedbehzad Bozorgtabar, Guillaume Marc Georges Vray, Devavrat Tomar, Manana Lortkipanidze

Despite the successes of deep neural networks on many challenging vision tasks, they often fail to generalize to new test domains that are not distributed identically to the training data. The domain adaptation becomes more challenging for cross-modality m ...

Institute of Electrical and Electronics Engineers2021