Abstract
Acoustic monitoring of road traffic events is an indispensable element of Intelligent Transport Systems to increase their effectiveness. It aims to detect the temporal activity of sound events in road traffic auditory scenes and classify their occurrences. Current state-of-the-art algorithms have limitations in capturing long-range dependencies between different audio features to achieve robust performance. Additionally, these models suffer from external noise and variation in audio intensities. Therefore, this study proposes a spectrogram-specific transformer model employing a multi-head attention mechanism using the scaled product attention technique based on softmax in combination with Temporal Convolutional Networks to overcome these difficulties with increased accuracy and robustness. It also proposes a unique preprocessing step and a Deep Linear Projection method to reduce the dimensions of the features before passing them to the learnable Positional Encoding layer. Rather than monophonic audio data samples, stereophonic Mel-spectrogram features are fed into the model, improving the model's robustness to noise. State-of-the-art One-dimensional Convolutional Neural Networks and Long Short-term Memory models were used to compare the proposed model's performance on two well-known datasets. The results demonstrated its superior performance by achieving an improvement in accuracy of 1.51 to 3.55% compared to the studied baselines.

Abstract

Abstract
The need for real-time and scalable oceanographic monitoring has become crucial for coastal management, marine traffic control and environmental sustainability. This study investigates the integration of sensor technology into marine cables to enable real-time monitoring, focusing on tidal cycles and wave characteristics. A 2000 m cable demonstrator was deployed off the coast of Portugal, featuring three active repeater nodes equipped with pressure sensors at varying depths. The goal was to estimate hourly wave periods using fast Fourier transform and calculate significant wave height via a custom peak detection algorithm. The results showed strong coherence with tidal depth variations, with wave period estimates closely aligning with forecasts. The wave height estimations exhibited a clear relationship with tidal cycles, which demonstrates the system's sensitivity to coastal hydrodynamics, a factor that numerical models designed for open waters often fail to capture. The study also highlights challenges in deep-water monitoring, such as signal attenuation and the need for high sampling rates. Overall, this research emphasises the scalability of sensor-integrated smart marine cables, offering a transformative opportunity to expand oceanographic monitoring capabilities. The findings open the door for future real-time ocean monitoring systems that can deliver valuable insights for coastal management, environmental monitoring and scientific research.

Abstract
This paper describes Task 2 of the CLEF 2025 JOKER track on the translation of puns from English into French. We outline the overall structure and setup of the shared task, discuss the approaches employed by the participants, and present and analyse the results they achieved. We also describe experiments with a promising new approach for the automatic evaluation of pun translation. Despite the significant improvements observed this year by participating systems, most of which used state-of-the-art large language models, we find wordplay translation to remain a complex and demanding task. Among the manually evaluated translations, 37.5% successfully preserved the meaning and involved wordplay, with success rates per English pun varying widely.

Abstract

Abstract
Pulmonary hypertension (PH) is a hemodynamic condition describing elevated pulmonary artery pressure. To date, right heart catheterism is the gold standard diagnostic test for PH, but it is an invasive and expensive procedure. Deep learning (DL) techniques applied to heart sounds have previously shown promising performances for PH screening. In this work, we analyze the impact of different input representations for PH detection with convolutional neural networks (CNNs). We found that considering each heartbeat as an independent input yielded systematically lower performance than considering the recordings as a whole: preserving the information about the variability over the heartbeats is key. Time-domain feature maps outperformed handcrafted features and combining the time- and frequency-domain proved consistently most effective. Reducing the number of heartbeats to 30 did not affect the performance, and even reducing to 10 beats preserves the diagnostic value. The proposed analysis moves one step further the applicability of DL for PH detection from heart sounds in the clinical practice. © 2025 IEEE Computer Society. All rights reserved.