News

Sergio Álvarez-Balanya has recently been hired at Amazon (Barcelona) as an Applied Scientist. Pablo Ramírez-Hereza has recently been hired at the company Atos, in Madrid (Spain) as a full-time researcher working on Horizon Europe projects. Both started on late 2022. Congratulations!

A new research project from the Spanish Research Agency has been (provisionally) granted to AUDIAS. The project is entitled “DeepMUSE: Multi-task and Semi-supervised Deep Learning for Speech and Audio Processing”. It starts in 2022 and will end by the end of 2024. The project builds on the success of a consecutive series of six R&D projects since 2003, and aims at exploring and developing new algorithms focusing on two main research directions: semi-supervised or unsupervised training, and Multi-task or multi-level deep learning models.

Sergio Álvarez Balanya has been recently selected for a summer internship at Amazon, Barcelona, Spain. He will be starting the internship in June and returning to Madrid in December.

Beltrán Labrador Serrano has been recently selected for a summer internship at the Speech Processing group of Google Research in New York, USA. He will be starting the internship in May and returning to Madrid in September.

Diego de Benito Gorrón has been doing a research stay at the prestigious Speech@FIT group of Brno University of Technology (BUT) in the Czech Republic from September 2021 to December 2021. He has been doing research in acoustic source separation in combination with audio event detection in the context of DCASE evaluations. After his return to UAM, he plans to continue his research in this line and his collaboration with BUT.

Alicia has made a postdoctoral research stay funded by the European Union under program H2020 Marie Slodowska-Curie Individual Fellowship. The project “Robust End-To-End SPEAKER recognition based on deep learning and attention models” (ETE SPEAKER, 843627) she has developed between 2019 and 2021 has contributed to the improvement of the automatic speaker recogntion systems using deep learning techniques.

More information about Alicia’s project in this link of CORDIS-EU.

Beltran Labrador has been selected as a Pre-doctoral fellow by the Spanish Ministry of Education (FPI PhD Grant), to work with AUDIAS towards his PhD degree.

The AUDIAS research group is organizing the fifth ALBAYZIN Search-on-Speech challenge in collaboration with University CEU San Pablo. The challenge will take place in the context of the next IberSPEECH conference.

Beltrán Labrador has returned on Feb. 7th 2020 from his short stay in Brno University of Technology. He has been conducting research on semi-supervised end-to-end ASR training.

Juan Maroñas did a research stay in the Alan Turing Institute, London, Uk from February to May 2020. He worked in machine learning with deep Gaussian processes.

Alicia Lozano Diez was awarded with a H2020 Marie Slodowska Curie Grant from the EU Comission for the project “Robust End-To-End SPEAKER recognition based on deep learning and attention models” to do a post-doc stay at the Speech@FIT Group of BUT, Czech Republic. She will work on deep learning approaches for speaker diarization and recognition.

Beltran Labrador-Serrano starts a research stay at the Speech@FIT Group in Brno University of Technology, for three months, to work on deep learning approaches for speech recognition.

Pablo Ramirez-Hereza has joined AUDIAS as a PhD Student.

Juan Maroñas did a research stay in the University of Modena and Reggio Emilia, Italy from. He worked in deep learning approaches for image classification in medical applications.

Daniel Ramos visited the Machine Learning Group at the University of Cambridge for a research stay from January to May 2019 funded by the Spanish Ministry of Education, to work on probabilistic approaches to likelihood ratio computation in forensic glass comparison.

AUDIAS starts the new project “Aprendizaje Profundo en Voz para Aplicaciones Forenses y de Seguridad“, funded by the Spanish Ministry of Science, Innovation and Universities under grant RTI2018-098091-B-I00. The project will run from Jan. 2019 to Dec. 2021.

One article from AUDIAS selected as finalist for the Best Journal Article Award 2018 from the Spanish Speech Technologies Network (Red Temática en Tecnologías del Habla, RTTH):

A. Lozano-Diez, R. Zazo, D. T. Toledano and J. Gonzalez-Rodriguez, “An analysis of the influence of deep neural network (DNN) topology in bottleneck feature based language recognition”, PLoS ONE 12(8): e0182580, August 2017.

Alicia Lozano-Diez won the “Best PhD Thesis Award” from the IberSPEECH 2018 Conference. This award recognizes the best of emerging academic work on processing of the Iberian languages and related issues, concluded in the three years preceding the submission deadline

Diego de Benito Gorron starts his PhD Fellowship at AUDIAS. He has been awarded a FPI PhD Grant from Autonomous University of Madrid in Nov. 2018.