Fernando Garcia de la Cruz

Research engineer, signal processing and machine learning for audio and music

Barcelona, Spain

Experience

  1. Independent practice

    Research engineer

  2. Sony Computer Science Laboratories (CSL)

    Research Scientist Intern

    • Machine learning and signal processing research for music and audio applications.
  3. Music Technology Group, Universitat Pompeu Fabra

    Research Assistant, IA y Música: Cátedra ENIA 2022 (TSI-100929-2023-1)

    • Research on detecting and quantifying AI-generated music in real broadcast monitoring scenarios, in collaboration with BMAT Music Innovators; published as two papers at ISMIR 2026.
    • Data pipelines and ML workflows: integrating multiple AI music generators, improving automated audio reference pipelines, and training detection models on real-world data.
    • Integrated the Essentia library into real-time audio plug-ins with JUCE; led the essentia-plugins repository.
    • Project funded by the Spanish Ministry for Digital Transformation and the Civil Service, with European Commission participation.
  4. Dolby Laboratories

    Software Developer, Entertainment Tech (internship)

    • C and C++ libraries for audio and signal processing for internal use.
    • Audio plug-in development and internal research projects using AI models.
  5. Ear Candy Technologies

    Audio Developer, DSP Engineer

  6. Globant

    Python Data Engineer, Data & Artificial Intelligence Studio

  7. Everis

    Python Engineer, Data & Analytics

Education

  1. MSc Sound and Music Computing

    Universitat Pompeu Fabra, Music Technology Group

  2. BSc Electronics and Communications Engineering, specialising in acoustics

    Instituto Politécnico Nacional (ESIME)

Publications

  1. How Much AI Is in This Track? Quantifying the Proportion of AI-Generated Stems in Hybrid Music Mixtures

    F. Garcia de la Cruz, D. López-Ayala, P. Zinemanas, E. Molina, M. Rocamora

  2. Assessing AI-Generated Music Detection in Real-World Broadcast Monitoring

    D. López-Ayala, F. Garcia de la Cruz, P. Zinemanas, E. Molina, M. Rocamora

  3. From Words to Sound: Neural Audio Synthesis of Guitar Sounds with Timbral Descriptors

    The Sound of AI Community

Teaching and community

  • Music Technology Group, UPF

    Teaching assistant, Generative Music AI workshop

    2025 – present

  • The Sound of AI

    Assistant director of the first Sound of AI Accelerator, a startup programme in music and audio AI

    Apr 2023 – Jul 2023

  • The Sound of AI

    Organiser and participant, first Sound of AI Hackathon; my team built Modelizer

    Jul 2022

  • The Sound of AI

    Project manager, Open Source Research project (200+ contributors), co-author of the AIMC 2022 paper

    Sept 2022

  • Ciencia desde Cero

    Science communicator

    Aug 2017 – Jan 2023

  • Guit-Art Music School

    Guitar teacher and audio engineer

    Nov 2013 – Jun 2019

Technical skills

Audio and DSP
JUCE (C++), Essentia, Pure Data, Matlab
Languages
Python, C/C++, Go, Cmajor, Matlab
Machine learning
PyTorch, TensorFlow, Keras, scikit-learn, librosa, torchaudio
Data engineering
Apache Beam, Airflow, Kafka, Spark
Cloud and DevOps
GCP, Docker, Kubernetes, Jenkins, Travis CI
Databases
PostgreSQL, MySQL, BigQuery, MongoDB
Web and APIs
FastAPI, Flask, Django

Languages

Spanish
Native
English
Fluent, professional proficiency