Speaker: Manuel Otero González. Abstract: Description of VoxCeleb and its latest Challenges (2019-2022), elaboration and capture of audio database of celebrities of Spanish nationality, and preliminary evaluation of a pre-trained system with the acquired data.
MusicLM: Generating music from text
Speaker: Laura Herrera Alarcón Abstract: Based on https://arxiv.org/pdf/2301.11325.pdf. This paper presents a new model for generating high-fidelity music from text descriptions. It combines SoundStream, w2v-BERT and MuLan, 3 models that allow to obtain temporal coherence and high quality audios of… Read More
Iterative psuedo-forced alignment tool
Speaker: W. Fernando López Gavilánez. Abstract: High-quality data labeling from specific domains is costly and human time-consuming. In this work, we propose an iterative pseudo-forced alignment algorithm for long audio files with low-quality transcriptions. The alignments are iteratively done by… Read More
Differentially Private Fine-Tuning for Language Models
Speaker: Beltrán Labrador Serrano. Abstract: Based on https://arxiv.org/abs/2110.06500. In this talk we will comment the paper Differentially Private Fine-Tuning for Language Models, where the authors give simpler, sparser, and faster algorithms for differentially private fine-tuning of large-scale pre-trained language models,… Read More
Conformer Architecture for Sound Event Detection (DCASE)
Speaker: Sara Barahona Quirós. Abstract: Sound Event Detection is the task that is focused on automatizing the human’s ability of recognizing sound events in the environment. Over the last years, the creation of evaluations such as the Detection and Classification… Read More
MixMatch: A Holistic Approach to Semi-Supervised Learning
Speaker: Diego de Benito Gorrón. Abstract: This talk is an overview of a NIPS 2019 paper by David Berthelot et al. (Google Research) that proposes a novel method for Semi-supervised learning: MixMatch. “Semi-supervised learning has proven to be a powerful… Read More
Highly accurate protein structure prediction with AlphaFold
Speaker: Juan Ignacio Álvarez Trejos. Abstract: Based on https://www.nature.com/articles/s41586-021-03819-2. Proteins are essential to life, and understanding their structure can facilitate a mechanistic understanding of their function. Through an enormous experimental effort, the structures of around 100,000 unique proteins have been… Read More
Whisper: Robust Speech Recognition via Large-Scale Weak Supervision
Speaker: Doroteo Torre Toledano. Abstract: Very recently (in Sept 2022) OpenAI has made freely available a speech recognition neural network called Whisper. One of the main differences with respect to the current state of the art is the use of… Read More
Dynamic Bayesian Networks for Temporal Prediction of Chemical Radioisotope Levels in Nuclear Power Plant Reactors
Speaker: Daniel Ramos Castro. Abstract: Radiation dose in nuclear power plant reactors is known to be dominated by the presence of radioisotopes in the primary loop of the reactor. In order to strictly control it in normal operation (e.g., cleaning… Read More
Automatic adventitious respiratory sound analysis: A systematic review
Speaker: Miguel Ángel Martínez Pay. Abstract: Based on https://journals.plos.org/plosone/article?id=10.1371/journal.pone.0177926. Automatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease, and pneumonia. This article contains a compilation… Read More