Javier Ferreiros
A5028386517- Speech and dialogue systems
- Speech Recognition and Synthesis
- Natural Language Processing Techniques
- Speech and Audio Processing
- Music and Audio Processing
- Multi-Agent Systems and Negotiation
- Hand Gesture Recognition Systems
- Topic Modeling
- Genomics and Rare Diseases
- Advanced Data Compression Techniques
- Cancer Genomics and Diagnostics
- Phonetics and Phonology Research
- Hearing Impairment and Communication
- Service-Oriented Architecture and Web Services
- Social Robot Interaction and HRI
- AI in Service Interactions
- Emotion and Mood Recognition
- Genomics and Phylogenetic Studies
- Text Readability and Simplification
- Semantic Web and Ontologies
- Neural Networks and Applications
- DNA Repair Mechanisms
- Human Motion and Animation
- Experimental Learning in Engineering
- Authorship Attribution and Profiling
Genomics England
2017-2024
Universidad Politécnica de Madrid
2011-2021
Jackson Laboratory
2021
CODET Vision Institute
2018
Universidad de Sevilla
2009
SpeechTech (Czechia)
2008
International Computer Science Institute
2000
University of California, Berkeley
2000
Abstract The Cancer Programme of the 100,000 Genomes Project was an initiative to provide whole-genome sequencing (WGS) for patients with cancer, evaluating opportunities precision cancer care within UK National Healthcare System (NHS). Genomics England, alongside NHS analyzed WGS data from 13,880 solid tumors spanning 33 types, integrating genomic real-world treatment and outcome data, a secure Research Environment. Incidence somatic mutations in genes recommended standard-of-care testing...
The mutational landscape is shaped by many processes. Genic regions are vulnerable to mutation but preferentially protected transcription-coupled repair
In this article, we propose and evaluate a deep learning architecture based on convolutional neural networks for human stress detection using wearable sensors. This has first part that includes three layers features from several biosignals. The second is composed of fully connected detection. Additionally, analyze biosignal processing techniques to be applied before defining the inputs architecture: Fourier transform, cube root constant Q transform. analysis was performed public dataset,...
Maximizing the personal, public, research, and clinical value of genomic information will require reliable exchange genetic variation data. We report here Variation Representation Specification (VRS, pronounced "verse"), an extensible framework for computable representation that complements contemporary human-readable flat file standards representation. VRS provides semantically precise representations leverages this design to enable federated identification biomolecular with globally...
PurposeThis study aimed to undertake a multidisciplinary characterization of the phenotype associated with SOX11 variants.MethodsIndividuals protein altering variants in were identified through exome and genome sequencing international data sharing. Deep clinical phenotyping was undertaken by referring clinicians. Blood DNA methylation assessed using Infinium MethylationEPIC array. The expression pattern developing human brain defined RNAscope.ResultsWe reported 38 new patients variants....
The UK 100,000 Genomes Project offered participants screening for additional findings (AFs) in genes associated with familial hypercholesterolemia (FH) or hereditary cancer syndromes including breast/ovarian (HBOC), Lynch, adenomatous polyposis, MYH-associated multiple endocrine neoplasia (MEN), and von Hippel-Lindau. Here, we report disclosure processes, manifestation of AF-related disease, outcomes, costs.
This paper describes the development of a Spoken Spanish generator from sign-writing. The sign language considered was (LSE: Lengua de Signos Española). system consists an advanced visual interface (where deaf person can specify sequence signs in sign-writing), translator (for generating words Spanish), and finally, text to speech converter. allows be defined using several sign-writing alternatives. details process for designing proposing solutions HCI-specific challenges when working with...
Genome sequencing (GS) for diagnosis of rare genetic disease is being introduced into the clinic, but complexity data poses challenges developing pipelines with high diagnostic sensitivity. We evaluated performance Genomics England 100,000 Genomes Project (100kGP) panel-based pipelines, using craniosynostosis as a test disease.GS from 114 probands and their relatives (314 samples), negative on routine testing, were scrutinized by specialized research team, diagnoses compared those made...
Background Genomic variant prioritisation is one of the most significant bottlenecks to mainstream genomic testing in healthcare. Tools improve precision while ensuring high recall are critical successful clinical testing, particular for whole genome sequencing where millions variants must be considered each patient. Methods We developed EyeG2P, a publicly available database and web application using Ensembl Variant Effect Predictor. EyeG2P tailored efficient individuals with inherited...
Abstract Background The diagnostic rate of Mendelian disorders in sequencing studies continues to increase, along with the pace novel disease gene discovery. However, variant interpretation genes not currently associated is particularly challenging and strategies combining functional evidence approaches that evaluate phenotypic similarities between patients model organisms have proven successful. A full spectrum intolerance loss-of-function variation has been previously described, providing...
This paper describes the first experiments of a speech to sign language translation system in real domain. The developed is focused on sentences spoken by an officer when assisting people applying for, or renewing National Identification Document (NID) and Passport. translates explanations into for deafmute people. composed recognizer (for decoding utterance word sequence), natural translator converting sequence gestures belonging language), 3D avatar animation module playing gestures)....
The time delay of arrival (TDOA) between multiple microphones has been used since 2006 as a source information (localization) to complement the spectral features for speaker diarization. In this paper, we propose new localization feature, intensity channel contribution (ICC) based on relative energy signal arriving at each compared sum all channels. We have demonstrated that by joining ICC and TDOA features, robustness is improved diarization error rate (DER) complete system (using features)...