Speaker: José Manuel de Frutos Porras. Abstract: Comparing probability distributions from samples is a fundamental problem in statistics and machine learning, particularly when working with implicit generative models whose densities cannot be evaluated. In this talk, I will present an… Read More
Fused Semantic-Speaker Retrieval from Speech Databases
Speaker: Jan Zdenek. Abstract: Semantic speech retrieval systems typically focus on semantic relevance, while speaker identity can provide an additional retrieval constraint in scenarios where users seek semantically relevant speech from a specific speaker. This paper investigates speaker-conditioned semantic speech… Read More
From Audio to Trustworthy AI: A Research Journey
Speaker: Patricia Alonso de Apellaniz Abstract: This talk traces a research journey from signal processing and audio-based machine learning to generative modeling, survival analysis, and trustworthy AI. It begins by exploring how early work on voice activity detection and audiovisual… Read More
Real-Time Room Acoustics Simulation Using Hybrid Wave-Based, Geometric, and Stochastic Models
Speaker: Maya Tia Kanani. Abstract: Real-time acoustic simulation remains a significant challenge due to the high computational cost of accurately modelling sound propagation across the full audible frequency range. Building on previous work on perceptually optimised hybrid acoustic simulation, this… Read More
Semi-supervised sound event detection for AnuraSet using a mean teacher framework
Speaker: Vicente Jose Escarigo Miranda Abstract: Anuran vocalizations are valuable for biodiversity monitoring, but their automatic analysis is challenging because multiple species often vocalize simultaneously and class distributions are highly imbalanced. AnuraSet provides expert annotations for 42 Neotropical species together… Read More
Prediction of HIF Binding Sites
Speaker: Elias Boudjella. Abstract: This presentation describes a deep learning approach for predicting HIF binding sites from DNA sequences. It begins with the biological background and the construction of the datasets using ATAC-seq and ChIP-seq data from different cell types.… Read More
Rigorous Forensic Automatic Speaker Recognition: Bayesian Decision Theory, Probabilistic Calibration and Case-Specific Validation
Speaker: Daniel Ramos. Abstract: The use of automatic speaker recognition systems in forensic science has undergone a dramatic improvement in recent years in terms of scientific rigor, objectivity, and consensus. As a result, the discipline has become strongly aligned with… Read More
FiLM-Based Speaker Conditioning of a SpeechLLM for Pathological Speech Recognition
Speaker: William Fernando López Gavilanez. Abstract: Automatic speech recognition (ASR) has advanced remarkably for standard speech; however, pathological speech from neurological conditions remains a significant challenge. We investigate speaker conditioning via Feature-wise Linear Modulation (FiLM), injecting x-vector-derived information into each… Read More
Automatic Classification of Classical Music Composers from Audio Signals
Speaker: Sonia Aoi García Shida. Abstract: Automatic composer classification is a challenging task within the field of Music Information Retrieval, as it requires identifying compositional styles between composers from the same musical period, unlike genre classification where differences between classes… Read More
Detection and Grouping of Accents within Rural Spanish
Speaker: Koral Tubia. Abstract: Rural Spanish preserves a rich dialectal diversity that has received little attention form a computational point of view, partly because most speech processing systems are trained on standard, urban speech. In this work, we use the… Read More