International Audio Laboratories Erlangen

Publications

Research Papers

  1. Hans-Ulrich Berendes, Simon Schwär, and Meinard Müller
    Lyrics Transcription in Western Classical Music with Whisper: A Case Study on Schubert's Winterreise
    In Workshop on NLP for Music and Audio (NLP4MUSA), 2024. PDF DOI 
    @inproceedings{BerendesSM24_Whisper_NLP4MUSA,
author    = {Hans-Ulrich Berendes and Simon Schw{\"a}r and Meinard M{\"u}ller},
title     = {Lyrics Transcription in {W}estern Classical Music with {W}hisper: {A} Case Study on {S}chubert's {W}interreise},
booktitle = {Workshop on {NLP} for Music and Audio ({NLP4MUSA})},
address   = {Oakland, CA, United States},
year      = {2024},
pages     = {},
doi       = {},
url-pdf   = {https://www.audiolabs-erlangen.de/fau/assistant/berendes/publications/2024_BerendesSM_LyricsTranscription_NLP4MUSA.pdf}
}
  2. Yigitcan Özer, Simon Schwär, and Meinard Müller
    Piano Concerto Accompaniment Creation
    In Late-Breaking Demos of the International Society for Music Information Retrieval Conference (ISMIR), 2024. Demo 
    @inproceedings{OezerSM24_PianoConcertoAcc_ISMIR-LBD,
author      = {Yigitcan {\"O}zer and Simon Schw{\"a}r and Meinard M{\"u}ller},
title       = {Piano Concerto Accompaniment Creation},
booktitle   = {Late-Breaking Demos of the International Society for Music Information Retrieval Conference ({ISMIR})},
address     = {San Francisco, USA},
year        = {2024},
url-demo    = {https://www.audiolabs-erlangen.de/resources/MIR/PCD_AudioLabs/}
}
  3. Peter Meier, Simon Schwär, and Meinard Müller
    A Real-Time Approach for Estimating Pulse Tracking Parameters for Beat-Synchronous Audio Effects
    In Proceedings of the International Conference on Digital Audio Effects (DAFx): 314–321, 2024. PDF Demo 
    @inproceedings{MeierSM24_RealTimePLP_DAFx,
author    = {Peter Meier and Simon Schw{\"a}r and Meinard M{\"u}ller},
title     = {A Real-Time Approach for Estimating Pulse Tracking Parameters for Beat-Synchronous Audio   Effects},
booktitle = {Proceedings of the International Conference on Digital Audio Effects ({DAFx})},
address   = {Guildford, Surrey, {UK}},
year      = {2024},
pages     = {314--321},
url-demo    = {https://audiolabs-erlangen.de/resources/MIR/2024-DAFx-RealTimePLP},
url-pdf   = {https://www.audiolabs-erlangen.de/content/05_fau/professor/00_mueller/03_publications/2024_MeierSM_RealTimePLP_DAFx.pdf}
}
  4. Yigitcan Özer, Leo Brütting, Simon Schwär, and Meinard Müller
    libsoni: A Python Toolbox for Sonifying Music Annotations and Feature Representations
    Journal of Open Source Software (JOSS), 9(96): 1–6, 2024. DOI 
    @article{OezerBSM24_SonificationToolbox_JOSS,
author    = {Yigitcan {\"O}zer and Leo Br{\"u}tting and Simon Schw{\"a}r and Meinard M{\"u}ller},
title     = {libsoni: {A} {P}ython Toolbox for Sonifying Music Annotations and Feature Representations},
journal   = {Journal of Open Source Software ({JOSS})},
volume    = {9},
number    = {96},
year      = {2024},
pages     = {1--6},
doi       = {10.21105/joss.06524}
}
  5. Simon Schwär, Michael Krause, Michael Fast, Sebastian Rosenzweig, Frank Scherbaum, and Meinard Müller
    A Dataset of Larynx Microphone Recordings for Singing Voice Reconstruction
    Transaction of the International Society for Music Information Retrieval (TISMIR), 7(1): 30–43, 2024. PDF Details DOI 
    @article{SchwaerKFRSM24_LarynxMicSVR_TISMIR,
author  = {Simon Schw{\"a}r and Michael Krause and Michael Fast and Sebastian Rosenzweig and Frank Scherbaum and Meinard M{\"u}ller},
title   = {A Dataset of Larynx Microphone Recordings for Singing Voice Reconstruction},
journal = {Transaction of the International Society for Music Information Retrieval ({TISMIR})},
year    = {2024},
volume  = {7},
number  = {1},
pages   = {30--43},
doi     = {10.5334/tismir.166},
url-pdf = {2024_SchwaerKFRSM_LarynxMicSVR_TISMIR.pdf},
url-details = {https://www.audiolabs-erlangen.de/resources/MIR/LM-SVR/}
}
  6. Simon Schwär and Meinard Müller
    Multi-Scale Spectral Loss Revisited
    IEEE Signal Processing Letters, 30: 1712–1716, 2023. PDF DOI 
    @article{SchwaerM23_MultiScaleSpecLoss_IEEE-SPL,
author  = {Simon Schw{\"a}r and Meinard M{\"u}ller},
title   = {Multi-Scale Spectral Loss Revisited},
journal = {{IEEE} Signal Processing Letters},
year    = {2023},
volume  = {30},
number  = {},
pages   = {1712-1716},
doi     = {10.1109/LSP.2023.3333205},
url-pdf = {2023_SchwaerM_MultiScaleSpecLoss_IEEE-SPL.pdf}
}
  7. Hans-Ulrich Berendes, Simon Schwär, Maximilian Schäfer, and Meinard Müller
    Towards Differentiable Piano Synthesis Based On Physical Modeling
    In Late-Breaking Demos of the International Society for Music Information Retrieval Conference (ISMIR), 2023. Details 
    @inproceedings{BerendesSSM_DifferentiablePiano_ISMIR-LBD,
author      = {Hans-Ulrich Berendes and Simon Schw{\"a}r and Maximilian Sch{\"a}fer and Meinard M{\"u}ller},
title       = {Towards Differentiable Piano Synthesis Based On Physical Modeling},
booktitle   = {Late-Breaking Demos of the International Society for Music Information Retrieval Conference ({ISMIR})},
address     = {Milano, Italy},
year        = {2023},
url-details = {https://audiolabs-erlangen.de/resources/MIR/2023-ISMIR-PianoSynth/}
}
  8. Yigitcan Özer, Simon Schwär, Vlora Arifi-Müller, Jeremy Lawrence, Emre Sen, and Meinard Müller
    Piano Concerto Dataset (PCD): A Multitrack Dataset of Piano Concertos
    Transactions of the International Society for Music Information Retrieval (TISMIR), 6(1): 75–88, 2023. Demo DOI 
    @article{OezerSALSM23_PCD_TISMIR,
title     = {Piano Concerto Dataset (PCD): A Multitrack Dataset of Piano Concertos},
author    = {Yigitcan {\"O}zer and Simon Schw{\"a}r and Vlora Arifi-M{\"u}ller and Jeremy Lawrence and Emre Sen and Meinard M{\"u}ller},
journal   = {Transactions of the International Society for Music Information Retrieval ({TISMIR})},
volume    = {6},
number    = {1},
year      = {2023},
pages     = {75--88},
doi       = {10.5334/tismir.160},
url-demo  = {https://www.audiolabs-erlangen.de/resources/MIR/PCD}
}
  9. Peter Meier, Simon Schwär, Gerhard Krump, and Meinard Müller
    Evaluating Real-Time Pitch Estimation Algorithms for Creative Music Game Interaction
    In Proceedings of the GI Jahrestagung, 2023. 
    @inproceedings{MeierSKM23_PitchEstimationGames_GI,
author    = {Peter Meier and Simon Schw{\"a}r and Gerhard Krump and Meinard M{\"u}ller},
title     = {Evaluating Real-Time Pitch Estimation Algorithms for Creative Music Game Interaction},
booktitle = {Proceedings of the GI Jahrestagung},
address   = {Berlin, Germany},
year      = {2023},
pages     = {},
url-pdf   = {}
}
  10. Simon Schwär, Meinard Müller, and Sebastian J. Schlecht
    Modifying Partials for Minimum-Roughness Sound Synthesis
    In Proceedings of the 3rd International Conference on Timbre: 130–134, 2023. Demo 
    @inproceedings{SchwaerMS_AdaptiveTimbre_TIMBRE,
author    = {Simon Schw{\"a}r and Meinard M{\"u}ller and Sebastian J. Schlecht},
title     = {Modifying Partials for Minimum-Roughness Sound Synthesis},
booktitle = {Proceedings of the 3rd International Conference on Timbre},
address   = {Thessaloniki, Greece},
year      = {2023},
pages     = {130 -- 134}
url-demo  = {https://www.audiolabs-erlangen.de/resources/2023-TIMBRE-AdaptiveTimbre},
}
  11. Peter Meier, Simon Schwär, Gerhard Krump, and Meinard Müller
    Real-Time Pitch Estimation for Creative Music Game Interaction
    In Proceedings of the Deutsche Jahrestagung für Akustik (DAGA): 1346–1349, 2023. PDF 
    @inproceedings{MeierSKM23_MusicGame_DAGA,
author    = {Peter Meier and Simon Schw{\"a}r and Gerhard Krump and Meinard M{\"u}ller},
title     = {Real-Time Pitch Estimation for Creative Music Game Interaction},
booktitle = {Proceedings of the {D}eutsche {J}ahrestagung f{\"u}r {A}kustik ({DAGA})},
address   = {Hamburg, Germany},
year      = {2023},
pages     = {1346--1349},
url-pdf   = {https://www.audiolabs-erlangen.de/fau/professor/mueller/publications/2023_MeierSKM_PitchGame_DAGA_ePrint.pdf}
}
  12. Sebastian Rosenzweig, Simon Schwär, and Meinard Müller
    libf0: A Python Library for Fundamental Frequency Estimation
    In Late Breaking Demos of the International Society for Music Information Retrieval Conference (ISMIR), 2022. PDF 
    @inproceedings{RosenzweigSM22_libf0_ISMIR-LBD,
author    = {Sebastian Rosenzweig and Simon Schw{\"a}r and Meinard M{\"u}ller},
title     = {libf0: A Python Library for Fundamental Frequency Estimation},
booktitle = {Late Breaking Demos of the International Society for Music Information Retrieval Conference ({ISMIR})},
address   = {Bengaluru, India},
year      = {2022},
url-pdf   = {https://archives.ismir.net/ismir2022/latebreaking/000003.pdf},
url-code  = {https://github.com/groupmm/libf0/}
}
  13. Simon Schwär, Meinard Müller, and Sebastian J. Schlecht
    A Variational Y-Autoencoder for Disentangling Gesture and Material of Interaction Sounds
    In AES 4th International Conference on Audio for Virtual and Augmented Reality (AES AVAR), 2022. PDF Demo 
    @inproceedings{SchwaerMS_InteractionSounds_AVAR,
author    = {Simon Schw{\"a}r and Meinard M{\"u}ller and Sebastian J. Schlecht},
title     = {A Variational Y-Autoencoder for Disentangling Gesture and Material of Interaction Sounds},
booktitle = {{AES} 4th International Conference on Audio for Virtual and Augmented Reality ({AES AVAR})},
address   = {Redmond, WA, USA},
year      = {2022},
url-demo  = {https://www.audiolabs-erlangen.de/resources/2022-AVAR-InteractionSounds},
url-code  = {https://github.com/simonschwaer/adagio-for-things},
url-pdf   = {2022_SchwaerMS_VYAE_AVAR.pdf}
}
  14. Peter Meier, Simon Schwär, Sebastian Rosenzweig, and Meinard Müller
    Real-Time MIR Algorithms for Music-Reactive Game World Generation
    In Mensch und Computer 2022 - Workshop für Innovative Computerbasierte Musikinterfaces (ICMI), 2022. DOI 
    @inproceedings{MeierSRM22_MIRGames_ICMI,
author    = {Peter Meier and Simon Schw\"ar and Sebastian Rosenzweig and Meinard M\"uller},
title     = {Real-Time {MIR} Algorithms for Music-Reactive Game World Generation},
booktitle = {Mensch und Computer 2022 - Workshop für Innovative Computerbasierte Musikinterfaces ({ICMI})},
year      = {2022},
publisher = {Gesellschaft für Informatik e.V.},
address   = {Darmstadt, Germany},
doi       = {10.18420/muc2022-mci-ws03-225},
}
  15. Simon Schwär, Sebastian Rosenzweig, and Meinard Müller
    A Differentiable Cost Measure for Intonation Processing in Polyphonic Music
    In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 2021. PDF Demo 
    @inproceedings{SchwaerRM_Intonation_ISMIR,
author    = {Simon Schw{\"a}r and Sebastian Rosenzweig and Meinard M{\"u}ller},
title     = {A Differentiable Cost Measure for Intonation Processing in Polyphonic Music},
booktitle = {Proceedings of the International Society for Music Information Retrieval Conference ({ISMIR})},
address   = {Online},
year      = {2021},
url-pdf   = {https://archives.ismir.net/ismir2021/paper/000078.pdf},
url-demo  = {https://www.audiolabs-erlangen.de/resources/MIR/2021-ISMIR-IntonationCostMeasure},
url-code  = {https://github.com/simonschwaer/differentiable-intonation-tools/}
}
  16. Sebastian Rosenzweig, Simon Schwär, Jonathan Driedger, and Meinard Müller
    Adaptive Pitch-Shifting with Applications to Intonation Adjustment in A Capella Recordings
    In Proceedings of the International Conference on Digital Audio Effects (DAFx), 2021. PDF Demo 
    @inproceedings{RosenzweigSDM_PitchShifting_DAFx,
author    = {Sebastian Rosenzweig and Simon Schw{\"a}r and Jonathan Driedger and Meinard M{\"u}ller},
title     = {Adaptive Pitch-Shifting with Applications to Intonation Adjustment in A Capella Recordings},
booktitle = {Proceedings of the International Conference on Digital Audio Effects ({DAFx})},
address   = {Vienna, Austria},
year      = {2021},
url-pdf   = {https://www.dafx.de/paper-archive/2021/proceedings/papers/DAFx20in21_paper_11.pdf},
url-demo  = {https://www.audiolabs-erlangen.de/resources/MIR/2021-DAFX-AdaptivePitchShifting},
url-code  = {https://github.com/meinardmueller/libtsm}
}

Patents & Patent Applications

  1. Sascha Disch, Simon Schwär, and Kahleel Porter Hassan
    Audio Decoder, Audio Encoder, Method for Decoding, Method for Encoding and Bitstream, Using a Plurality of Packets, the Packets Comprising One or More Scene Configuration Packets, One or More Scene Update Packets, One or More Scene Payload Packets
    Patent App. 18/659947, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{DischSH24_BitstreamPackets_Patent,
author      = {Sascha Disch and Simon Schwär and Kahleel Porter Hassan},
title       = {Audio Decoder, Audio Encoder, Method for Decoding, Method for Encoding and Bitstream, Using a Plurality of Packets, the Packets Comprising One or More Scene Configuration Packets, One or More Scene Update Packets, One or More Scene Payload Packets},
number      = {App. 18/659947},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  2. Sascha Disch, Simon Schwär, and Kahleel Porter Hassan
    Audio Decoder, Audio Encoder, Method for Decoding, Method for Encoding and Bitstream, Using Scene Configuration Packet a Cell Information Defines an Association Between the One or More Cells and Respective One or More Data Structures
    Patent App. 18/659992, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{DischSH24_BitstreamCells_Patent,
author      = {Sascha Disch and Simon Schwär and Kahleel Porter Hassan},
title       = {Audio Decoder, Audio Encoder, Method for Decoding, Method for Encoding and Bitstream, Using Scene Configuration Packet a Cell Information Defines an Association Between the One or More Cells and Respective One or More Data Structures},
number      = {App. 18/659992},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  3. Yun-Han Wu, Jürgen Herre, Mikhail Korotiaev, Matthias Geier, Simon Schwär, and Alexander Adami
    Apparatus, Method or Computer Program for Synthesizing a Spatially Extended Sound Source Using Modification Data on a Potentially Modifying Object
    Patent App. 18/647111, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{WuHKGSA24_SESSModification_Patent,
author      = {Yun-Han Wu and Jürgen Herre and Mikhail Korotiaev and Matthias Geier and Simon Schwär and Alexander Adami},
title       = {Apparatus, Method or Computer Program for Synthesizing a Spatially Extended Sound Source Using Modification Data on a Potentially Modifying Object},
number      = {App. 18/647111},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  4. Simon Schwär, Jürgen Herre, Matthias Geier, and Mikhail Korotiaev
    Renderers, Decoders, Encoders, Methods and Bitstreams Using Spatially Extended Sound Sources
    Patent App. 18/660059, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{SchwaerHGK24_SESSRenderer_Patent,
author      = {Simon Schwär and Jürgen Herre and Matthias Geier and Mikhail Korotiaev},
title       = {Renderers, Decoders, Encoders, Methods and Bitstreams Using Spatially Extended Sound Sources},
number      = {App. 18/660059},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  5. Jürgen Herre, Vensan Mazmanyan, Alexander Adami, Nils Peters, Simon Schwär, Kahleel Porter Hassan, Matthias Geier, Sujeet Mate, Antti Eronen, and Otto Harju
    Apparatus and Method for Rendering a Virtual Audio Scene Employing Information on a Default Acoustic Environment
    Patent App. 18/659897, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{HerreEtAl24_DefaultAcousticEnv_Patent,
author      = {Jürgen Herre and Vensan Mazmanyan and Alexander Adami and Nils Peters and Simon Schwär and Kahleel Porter Hassan and Matthias Geier and Sujeet Mate and Antti Eronen and Otto Harju},
title       = {Apparatus and Method for Rendering a Virtual Audio Scene Employing Information on a Default Acoustic Environment},
number      = {App. 18/659897},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  6. Yun-Han Wu, Jürgen Herre, Mikhail Korotiaev, Matthias Geier, Simon Schwär, Alexander Adami, and Carlotta Anemüller
    Apparatus, Method or Computer Program for Synthesizing a Spatially Extended Sound Source Using Variance or Covariance Data
    Patent App. 18/651270, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{WuEtAl24_SESSCovariance_Patent,
author      = {Yun-Han Wu and Jürgen Herre and Mikhail Korotiaev and Matthias Geier and Simon Schwär and Alexander Adami and Carlotta Anemüller},
title       = {Apparatus, Method or Computer Program for Synthesizing a Spatially Extended Sound Source Using Variance or Covariance Data},
number      = {App. 18/651270},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  7. Jürgen Herre, Mikhail Korotiaev, Matthias Geier, Simon Schwär, Alexander Adami, and Carlotta Anemüller
    Apparatus, Method and Computer Program for Synthesizing a Spatially Extended Sound Source Using Elementary Spatial Sectors
    Patent App. 18/637801, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2024. 
    @patent{HerreKGSAA24_SESSSectors_Patent,
author      = {Jürgen Herre and Mikhail Korotiaev and Matthias Geier and Simon Schwär and Alexander Adami and Carlotta Anemüller},
title       = {Apparatus, Method and Computer Program for Synthesizing a Spatially Extended Sound Source Using Elementary Spatial Sectors},
number      = {App. 18/637801},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2024}
}
  8. Frank Wefers and Simon Schwär
    Apparatus and Method for Rendering a Sound Scene Using Pipeline Stages
    Patent App. 17/940871, Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.. 2023. 
    @patent{WefersS24_SESSSectors_Patent,
author      = {Frank Wefers and Simon Schwär},
title       = {Apparatus and Method for Rendering a Sound Scene Using Pipeline Stages},
number      = {App. 17/940871},
assignee    = {Fraunhofer-Gesellschaft zur Förderung der angewandten Forschung e.V.},
year        = {2023}
}