International Audio Laboratories Erlangen

Dr.-Ing. Pablo Delgado

Current offerings

  • Currently offering master thesis, research internship and student job opportunities.
  • PhD and Postdoc positions also available.

Research Interests

  • Audio quality assessment

    • Perceptual audio quality metrics (PEAQ, PESQ, POLQA, and other ITU-R/ITU-T methods)
    • Perceptual models of human hearing (peripheral and cognitive)
    • Psychoacoustics
    • Machine learning for audio quality assessment
    • Subjective assessment of audio quality (spatial and timbre)

  • Machine learning and deep learning in audio

    • Neural audio coding
    • Perceptual loss functions for deep learning in audio
    • Machine learning based incorporation of subjective data into perceptual models

  • Perceptual audio coding

    • Low and high bitrate music and speech coding
    • Multichannel and object-oriented reproduction formats
    • Binaural audio reproduction and coding

  • Audio signal processing

    • Musical applications
    • Virtual reality
    • Spatial audio reproduction
    • Human machine interaction
    • Embedded/low-power systems

Teaching

  • Current

    • 2018-2025: Audio Processing Seminar (Prof. Jürgen Herre, FAU)
    • 2018-2023: Audio Processing Laboratory, Statistical Methods for Audio Experiments (Prof. Jürgen Herre, FAU)

  • Previous

    • 2012: Introductory Mathematics (National University of Avellaneda)
    • 2009-2012: Algebra II. Linear algebra. (University of Buenos Aires)
    • 2007-2008: Mathematical Analysis III. Complex variable calculus, integral transforms and deterministic signal processing. (University of Buenos Aires)

Research Supervision

  • Master Thesis: "Investigations on Neural Audio Coding", Alexander Heinmüller, 2024

  • Master Thesis: “Models of Cognitive Effects for Auditory Salience in Objective Quality Measurement”, Aalok Gupta, 2022.

  • Master Thesis: “Improved Cognitive Model for a Perceptual Evaluation of Audio Quality Method”, Stefan Emmert, 2021.

  • Research Internship: “Influence of Combined Inter-Aural Cue distortions on Overall Audio Quality in Spatial Audio Telecommunications”, Slavica Subič, 2019.

  • Master Thesis: “Overview of State-of-the-Art Binaural Feature Extraction for Objective Quality Estimation of Parametric Spatial Audio”, Meng Chen, 2018.

Workshops/Keynote Talks

  • Keynote: Invited talk at the University of Oldenburg's Collaborative Research Centre SFB 1330 of Hearing Acoustics (HAPPAA): Current advances in objective quality assessment of perceptually coded audio signals 02-Dec-2025

  • Panel Discussion (Organizer): “MPEG-I Immersive Audio: Shaping the Future of VR/AR Sound” on 159th Audio Engineering Society (AES) Conventions, Long Beach, CA, 202t5 tohhether with Leon Terenti (Dolby Germany), Tommy Falk (Ericsson), Isaac Munoz (Qualcomm Technologies, Inc.), Sascha Disch (Fraunhofer IIS), Sujeet Mate (Nokia, Nokia),

  • Panel Discussion (Chair): "Neural Audio Coding Techniques and Their Evaluation" (Audio Engineering Society Artificial Intelligence and Machine Learning for Audio Conference 2025 Sept 8-10, London, UK) Together with Jan Skoglund (Google LLC), Jürgen Herre (Fraunhofer IIS/Audiolabs Erlangen), Julian Parker (Stability AI) and Stéphane Ragot (Orange Labs)

  • Workshop: "Applications of Artificial Intelligence and Machine Learning in Audio Quality Models" Parts I and II, (on 156th and 157th Audio Engineering Society (AES) Conventions, Madrid and NYC, 2024) Together with Jan Skoglund (Google LLC), Phill Williams (Netflix), Arijit Biswas (Dolby Germany GmbH), Hannes Gamper (Microsoft Research) and Sascha Dick (Fraunhofer IIS).

  • Keynote: “To PEAQ or Not to PEAQ? - BS.1387 Revisited” w/Prof. Thomas Sporer, 147th Audio Engineering Society (AES) Convention, 2019.

Memberships

  • Member; IEEE, Institute of Electrical and Electronics Engineers
    • Reviewer: Signal Processing Society (IEEE SPS) Signal Processing Letters (SPL).
    • Reviewer: Transactions on Speech, Audio and Language Processing (IEEE-TASL).
    • Reviewer: IEEE ARGENCON.
  • Member: AES, Audio Engineering Society
    • Reviewer: Journal of the Audio Engineering Society (JAES).
    • Member: AES Technical Committee on Perception and Subjective Evaluation of Audio Signals.
    • Member: AES Technical Committee on Coding of Audio Signals.
    • Member: AES Technical Committee on Machine Learning and Artificial Intelligence in Audio.

CV

Industry Projects (selected)

  • Senior Scientist, Fraunhofer IIS Advanced Audio Research Group

    • Audio for VR and AR: MPEG-I International Standard for Immersive Audio
    • Referent for machine learning and psychoacoustics research in audio and speech codecs
    • Referent for perceptual models
    • Referent for subjective and objective evaluation of audio quality

  • Research Scientist (Fraunhofer IIS Advanced Audio Research Group)

  • Fraunhofer IIS, Audio and Multimedia Technologies

    • Research and design of audio processing algorithms with emphasis on embedded devices and digital signal processors - Core Development Kit
    • Cooperation with international partners, deployment support.
    • Development, implementation, optimization, and testing of cross-platform audio coding software, MPEG and 3GPP standards.
    • Design and development of automated software tests. Deployment planning and support.

  • MPEG-H (Fraunhofer IIS Multimedia Realtime Department)

  • Fraunhofer IIS, Multimedia Realtime Department

    • Performance evaluation of MPEG audio codecs on state of the art low power embedded processors with mixed fix/float point handling capabilities.

Education

  • Doctor of Engineering (Dr.-Ing) – Friedrich-Alexander-Universität Erlangen-Nürnberg. Perceptual coding of audio signals. Models of human auditory perception. Psychoacoustics. Machine Learning.

  • Electrical/Electronics Engineer (M.S.E.E.) – University of Buenos Aires.

  • EE, and App. Physics, Signal Processing, Embedded Systems, Telecom and Automation Engineering – École Nationale Supérieure d’Ingénieurs de Caen (ENSICAEN), France.

Further Specialization

  • Statistical methods for data analysis (Dr. Felix Bauer, Prof. Dr. Sebastian Sauer)
  • Filter banks for audio analysis and coding (Prof. Dr.-Ing Bernd Edler)
  • Auditory models (Prof. Dr.-Ing Bernd Edler)
  • Perceptual audio coding techniques and technology (Prof. Dr.-Ing. Jürgen Herre)
  • C/C++ language development techniques for advanced users (Jörg Fasching- bauer)
  • Python for advanced users (Bernd Klein)
  • Scientific writing (Elisabeth Grenzebach)

Multimedia

  • A Data-Driven Cognitive Salience Model for Objective Perceptual Audio Quality Assessment

  • Objective Quality Assessment of Perceptually Coded Audio Signals

Website