Skip to content
Main Menu
  • Home
  • News
  • Seminars
  • People
    • Staff
    • Ph.D. Students
    • Students
    • AUDIAS Alumni
  • Publications
  • Projects & Industry
    • Projects
    • Industry
  • Evaluations
  • For Students
    • Master’s Thesis Proposals
    • Study Grants and Opportunities
    • Teaching
  • Contact
AUDIAS-UAM
  • Home
  • News
  • Seminars
  • People
    • Staff
    • Ph.D. Students
    • Students
    • AUDIAS Alumni
  • Publications
  • Projects & Industry
    • Projects
    • Industry
  • Evaluations
  • For Students
    • Master’s Thesis Proposals
    • Study Grants and Opportunities
    • Teaching
  • Contact

Category: AUDIAS Seminars

  • Home
  • AUDIAS Seminars
  • Page 12

data2vec: A General Framework for Self-supervised Learning in Speech, Vision and Language

March 24, 2022May 19, 2022 daniel

Speaker: Sergio Segovia. Abstract: The core idea is to predict latent representations of the full input data based on a masked view of the input in a self-distillation setup using a standard Transformer architecture. Instead of predicting modality-specific targets such… Read More

AUDIAS Seminars

Data Augmentation for Decoupled Calibration of Deep Neural Network Classifiers

March 17, 2022May 19, 2022 daniel

Speaker: Sergio Márquez Carrero. Abstract: Modern Deep Neural Networks (DNN) have significantly outperformed those employed over a decade ago in terms of accuracy. Nonetheless, the outputs generated by these models are poorly calibrated, causing substantial issues in a variety of… Read More

AUDIAS Seminars

Connectionist Temporal Classification (CTC) Speech Segmentation

March 10, 2022March 11, 2022 daniel

Speaker: W. Fernando López Gavilanez. Abstract: Motivated by the lack of high-quality labeled data for specific scenarios, such as emergencies in the home environment, we explored a CTC-segmentation method to generate a specific-purpose speech dataset. The project seeks the quality improvement of… Read More

AUDIAS Seminars

BigSSL: Large-Scale Semi-Supervised Learning for ASR

March 3, 2022March 4, 2022 audias

Speaker: Laura Herrera Abstract: This paper deals with results obtained on very large automatic speaker recognition models.A large amount of labelled data is not always available and sometimes they do not generalize enough. Consequently, the authors propose to use pre-trained… Read More

AUDIAS Seminars

Efficient Neural Approaches for Automatic Speech Recognition

February 24, 2022March 4, 2022 audias

Speaker: Doroteo Torre Toledano Abstract: Many different end-to-end neural approaches have been proposed in the last years in the field of automatic speech recognition (ASR). However, most of the research available compares systems only in terms of accuracy (word error… Read More

AUDIAS Seminars

Structured Output Learning

February 10, 2022March 4, 2022 audias

Speaker: María Pilar Fernández Rodríguez Abstract: Speech applications dealing with conversations require not only recognizing the spoken words, but also determining who spoke when, the language, punctuation, capitalization… To deal with it, it is typically addressed by merging the outputs… Read More

AUDIAS Seminars

Voxceleb Experiment: fairness

January 27, 2022March 4, 2022 audias

Speaker: Almudena Aguilera Abstract: The experiment is based on the dataset from Voxceleb [1], using the two pre-trained models. The main idea of these experiments was to study the fairness problems in different demographic groups present in the data base… Read More

AUDIAS Seminars

Semi-Supervised Music Tagging Transformer

December 16, 2021March 4, 2022 audias

Speaker: David Martín Abstract: Music Tagging Transformer (MTT) was recently released in the latest ISMIR 2021 Conference as one of the most erupting deep learning approaches for Music Information Retrieval. It consists of a semi-supervised approach where the model captures… Read More

AUDIAS Seminars

Encoder-Decoder Based Attractor Calculation for End-to-End Neural Diarization

December 9, 2021March 7, 2022 audias

Speaker: Alicia Lozano Díez Abstract: In this talk, we will deeply review the algorithms behind end-to-end systems for speaker diarization based on neural networks. In particular, we will describe how the encoder-decoder part of the model calculates “attractors” that capture… Read More

AUDIAS Seminars

Unsupervised Sound Separation Using Mixture Invariant Training

November 18, 2021March 7, 2022 audias

Speaker: Diego de Benito Gorrón Abstract: In recent years, rapid progress has been made on the problem of single-channel sound separation using supervised training of deep neural networks. In such supervised approaches, a model is trained to predict the component… Read More

AUDIAS Seminars

Posts navigation

Previous 1 … 11 12 13 14 Next

AUDIAS Seminars

Optimization of a Deep Learning Model for DNA Analysis under Hypoxemic Conditions

July 2, 2025

Speaker: Paloma Villanueva Fuster. Abstract: This study focuses on predicting…

Detection and classification of plants and their condition based on ultrasound patterns generated under abiotic stress

June 25, 2025

Speaker: Fernando David Modrego Arceo Abstract: Plant bioacoustics is an…

News & Events

Alicia Lozano-Diez selected for a MSCA grant for an intership at MIT

April 14, 2023

AUDIAS PhD Students hired!

February 2, 2023

About AUDIAS

AUDIAS is a solid research group addressing challenging problems in speech, audio and temporal signals from deep foundations in machine learning and signal processing.

Quick Links

  • Home
  • News
  • People
  • Publications
  • Industry
  • Evaluations
  • For Students
  • Contact

Highlights

DeepMUSE Research Project granted to AUDIAS

June 24, 2022

Sergio Álvarez Balanya selected for an intership in Amazon

April 23, 2022
Copyright © AUDIAS-UAM All rights reserved.
Education Mind by Axle Themes