Speaker: Alejandro Delgado Montero Abstract: This presentation explores the critical challenge of detecting audio deepfakes and defending speaker verification systems against voice spoofing attacks, evaluated within the frameworks of the ASVspoof 5 and ESDD2 international challenges. We examine the design… Read More
Review of the paper “CrisperWhisper: Accurate Timestamps on Verbatim Speech Transcriptions”
Speaker: Clara Adsuar Ávila. Abstract of the paper: We demonstrate that carefully adjusting the tokenizer of the Whisper speech recognition model significantly improves the precision of word-level timestamps when applying dynamic time warping to the decoder’s cross-attention scores. We finetune… Read More
TabImpute: The Quest to Improving Regression Results with Data Imputation
Speaker: Santiago Rattenbach Paliza Bartolomé. Abstract: In this talk, an innovative approach to data imputation with TabImpute is presented, leveraging the regression capabilities of TabPFN. Specifically, the comparison between TabImpute and the previous approach to data imputation using TabPFN is… Read More
Predictive Modeling of Gene Regulation: From Basic Genetics to Multi-Omic Machine Learning
Speaker: Alfonso Rincón Pérez. Abstract: Understanding the underlying genetic and epigenetic mechanisms that govern gene expression remains a fundamental challenge in molecular biology. This seminar presents a comprehensive data-driven approach to deciphering these regulatory layers, starting from the foundational genetics… Read More
From Clinical Prediction to Audio Analysis: Sleep Apnea Prediction and use of Audio-LLMs for speech diarization
Speaker: Unax Murua Urizarbarrena. Abstract: This presentation covers two different projects using data and speech analysis. The first half focuses on building a machine learning model to predict sleep apnea within the INSPIRA project (Colaboration Network funded by the Comunidad… Read More
From Coding to Orchestration: Generative AI and the Changing Nature of Software Engineering Expertise
Speaker: Pilar Fernández Gallego. Abstract: Debates about the future of generative AI increasingly focus on its capacity to reshape economic and social structures by making complex, effort-intensive tasks more accessible, automated, and scalable. As with previous technological revolutions, these shifts… Read More
DISPLACE-M 2026 Challenge and the AUDIAS-UAM Speaker Diarization Systems
Speaker: Alicia Lozano Díez. Abstract: In this talk, I will present the main challenges faced when addressing the recent DISPLACE-M 2026 challenge. In particular, I will focus on Track 1, which addresses speaker diarization on a multilingual, code-mixed conversations between… Read More
DNA Cryptography, Fish Welfare, and HIF Binding Prediction. Three Topics, No Obvious Connection
Speaker: Elias Boudjella. Abstract: This presentation brings together intentionally distinct topics spanning computational biology and experimental systems. We first explore DNA-based cryptography through the use of a one-time pad, leveraging synthetic DNA as a medium for secure information storage and… Read More
Machine Learning for Hematological Data Modeling in Platelet-Rich Plasma
Speaker: Pedro Martí Picó Abstract: This presentation shares research results regarding the use of machine learning models for modeling Platelet-Rich Plasma data, conducted within the framework of the UAM-BioSmartData Chair.
Benchmarking Automatic Speech Recognition Tools for a Set of Languages
Speaker: William Fernando López Gavilánez. Abstract: Automatic speech recognition has advanced rapidly in recent years, yet fine-grained evaluation for Iberian languages remains limited. In this work, we benchmark several open-weights speech-to-text models across multiple Iberian languages (Basque, Catalan, Galician, Portuguese,… Read More