About me
Pablo Delgado is part of the scientific staff of the Advanced Audio Research Group at the Fraunhofer Institute for Integrated Circuits (IIS) in Erlangen, Germany. He specializes in psychoacoustics applied to audio and speech coding, as well as machine learning applications in audio. He holds an Electronics Engineering degree from the University of Buenos Aires and earned his PhD in psychoacoustics, machine learning and audio signal processing from the University of Erlangen-Nuremberg, under the supervision of Jürgen Herre, a key figure in the development of the MP3 and AAC audio coding formats.
He has contributed to several technologies during his work at Fraunhofer IIIS and International Audio Laboratories Erlangen (AudioLabs), including the MPEG-H standard for 3D Audio Coding, and extending ITU-R algorithmic audio quality assessment methods such as PEAQ (Perceptual Evaluation of Audio Quality). His current projects involve developing audio solutions for virtual reality as a member of the standardization team of MPEG-I, and using human auditory models to inform deep learning audio tasks. He has also worked researching audio processing algorithms for embedded devices and digital signal processors, and collaborating with global tech leaders such as Google, Apple, Amazon, and NHK Japan. Additionally, he has focused on the design, development, and optimization of cross-platform audio coding software in line with MPEG and 3GPP standards.