CV


Education

  1. Ph.D. Candidate in Intelligent Systems Engineering and Computer Science

    Luddy School of Informatics, Computing, and Engineering, Indiana University (GPA: 4.0 / 4.0)
    2021 — 2024 (Expected)

    1. Selected Coursework: Machine Learning for Signal Processing, Deep Learning, Computer Vision, Applied Machine Learning

    2. Research Group: Signals and AI Group in Engineering (SAIGE)

    3. Advisor: Prof. Minje Kim

  2. M.Sc. in Information and Communication Engineering

    Dept. of Information and Communication Technologies, Universitat Pompeu-Fabra (GPA: 9.5 / 10.0)
    2019 — 2020

    1. Selected Coursework: Music Information Retrieval, System Design, Audio Signal Processing, ML for Audio, Research Methods, Reinforcement Learning

    2. Thesis: “SATB Voice Segregation for Monaural Recordings”

    3. Advisor: Dr. Pritish Chandna

  3. B.M. in Electronic Production & Design

    Electronic Production & Design Dept, Berklee College of Music (GPA: 3.8 / 4.0)
    2013 — 2016

    1. Selected Coursework: Digital Signal Processing, Physical Computing, Audio Programming in C, Principles of Audio Electronics, Music Acoustics

    2. Thesis: “A Deep Look at Spectral Synthesis Techniques Through csConvolve”

    3. Advisor: Dr. Richard Boulanger

Experience

  1. Amazon

    Applied Scientist
    March 2025 — Present Seattle WA

    1. Audio Foundation Model Team

  2. Netflix

    Machine Learning Research Intern
    Jun 2024 — Nov 2024 Los Gatos CA

    1. Supervised by Dr. Mahdi Kalayeh

    2. Working on multimodal (audio-visual) generative AI problems

  3. Google Research

    Student Researcher
    May 2023 — Oct 2023 Cambridge MA

    1. Supervised by Dr. Hakan Erdogan, Dr. John Herhsey, and Dr. Scott Wisdom

    2. Working on next-level unsupervised audio source separation problems

  4. Mitsubishi Electric Research Labs (MERL)

    Research Intern
    Summers in 2021, 2022 Cambridge MA

    1. Received $15'000 of gift-money from MERL to work on the “Cocktail Fork Problem”

    2. Hosted by Dr. Gordon Wichern and Dr. Jonathan Le Roux

    3. Derived and implemented new models and optimization methods for audio analysis with applications to source separation in challenging multi-source environments and using advanced machine learning techniques

  5. Signals and AI Group in Engineering (SAIGE), Indiana University

    Research Assistant
    Jan 2021 — Present Bloomington IN

    1. Conducting research pertaining to neural audio coding and audio source separation problems

    2. Supervised by Prof. Minje Kim

  6. Senseable Intelligence Group, Massachusetts Institute of Technology (MIT)

    Technical Lab Assistant
    Nov 2020 - Apr 2021 Cambridge MA

    1. Contractor for Senseable Intelligence Group, McGovern Institute for Brain Research, led by Dr. Satrajit Gosh

  7. Apple Inc.

    Content Engineer
    Jun 2016 — Jul 2019 Cupertino CA

    1. Software engineer for Apple's pro Audio & Music Apps (LogicPro, GarageBand)

    2. Designed real-time MIDI processing systems in C++ for Apple’s virtual musical instruments

  8. Electronic Production & Design Dept, Berklee College of Music

    Programming Tutor
    Sep 2015 — May 2016 Boston MA

    1. Tutored and mentored EPD students for technical classes: “Audio Programming in C”, “Digital Signal Processing”, “Csound”, “Max/MSP”

Publications

  1. D. Petermann and M. Kim, “Hyperbolic distance-based speech separation,” in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2024, (to appear).

  2. D. Petermann, I. Jang, and M. Kim, “Native multi-band audio coding within hyper-autoencoded reconstruction propagation networks,” in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023, pp. 1-5.

  3. D. Petermann, G. Wichern, A. Subramanian, and J. L. Roux, “Hyperbolic audio source separation,” in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2023, pp. 1-5.[Best Student Paper Award & Top 3% Papers]

  4. D. Petermann and M. Kim, “SpaIn-Net: Spatially-informed stereophonic music source separation,” in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022, pp. 106-110.

  5. D. Petermann, G. Wichern, Z.-Q. Wang, and J. L. Roux, “The cocktail fork problem: Three-stem audio separation for real-world soundtracks,” in Proc. of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 2022, pp. 526-530.

  6. D. Petermann, S. Beack, and M. Kim, “Harp-net: Hyper-autoencoded reconstruction propagation for scalable neural audio coding,” in Proc. of the IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA), 2021, pp. 316-320.

  7. D. Petermann, P. Chandna, H. Cuesta, J. Bonada, and E. Gomez, “Deep learning based source separation applied to choir ensembles,” in Proc. of the International Society for Music Information Retrieval Conference (ISMIR), 2020, pp. 733-739.

Journal Articles

  1. D. PetermannG. Wichern, A. S. Subramanian, Z.-Q. Wang, and J. L. Roux, “Tackling the cocktail fork problem for separation and transcription of real-world soundtracks,” IEEE/ACM Transactions on Audio, Speech, and Language Processing, vol. 31, pp. 2592-2605, 2023.

  2. P. Chandna, H. Cuesta, D. Petermann, and E. G ́omez, “A deep-learning based framework for source separation, analysis, and synthesis of choral ensembles,” Frontiers in Signal Processing, vol. 2, 2022.

Patents

  1. S. K. Beack, W. Lim, I. Jang, et al., Audio signal encoding/decoding methods and apparatus for performing the same, US Patent App. 63/420 405, 2023.

  2. D. Petermann, G. Wichern, A. Subramanian, and J. L. Roux, Audio source separation using hyperbolic embeddings, US Patent App. 18/191 417, 2023.