Publikationen

2025

• Laurynas Zavistanavicius, Frank Zalkow, Christian Dittmar, and Robert L. Stevenson. Adapting the fréchet audio distance as an objective metric for text-to-speech quality evaluation. In Proceedings of the ITG Conference on Speech Communication. Berlin, Germany, 2025. accepted. doi:.
  PDF BibTeX▼

  @inproceedings{ZavistanaviciusZDS25_FAD_ITG,
      author = "Zavistanavicius, Laurynas and Zalkow, Frank and Dittmar, Christian and Stevenson, Robert L.",
      title = "Adapting the Fréchet Audio Distance as an Objective Metric for Text-to-Speech Quality Evaluation",
      booktitle = "Proceedings of the {ITG} Conference on Speech Communication",
      address = "Berlin, Germany",
      year = "2025",
      doi = "",
      pages = "",
      customlinkPDF = "",
      note = "accepted"
  }
  

• Frank Zalkow, Benedikt Schäfer, Thomas Moissl, Jonas Bücherl, Kerstin Markl, Sebastian Bothe, Francois Duchateau, Julia Dollase, Patric Kabus, Daniel Steinigen, Oliver Schmitt, and Fabian Küch. Generating search-engine-optimized headlines for sports news. In Proceedings of the Conference on Natural Language Processing (KONVENS), 59–65. Hildesheim, Germany, 2025.
  PDF BibTeX▼

  @inproceedings{ZalkowEtAl_SportsNews_KONVENS,
      author = "Zalkow, Frank and Schäfer, Benedikt and Moissl, Thomas and Bücherl, Jonas and Markl, Kerstin and Bothe, Sebastian and Duchateau, Francois and Dollase, Julia and Kabus, Patric and Steinigen, Daniel and Schmitt, Oliver and Küch, Fabian",
      title = "Generating Search-Engine-Optimized Headlines for Sports News",
      booktitle = "Proceedings of the Conference on Natural Language Processing ({KONVENS})",
      address = "Hildesheim, Germany",
      year = "2025",
      pages = "59--65",
      customlinkPDF = "https://aclanthology.org/2025.konvens-1.6/"
  }
  

• Judith Bauer, Frank Zalkow, Meinard Müller, and Christian Dittmar. Explicit emphasis control in text-to-speech synthesis. In Proceedings of the ISCA Speech Synthesis Workshop (SSW), 21–27. Leeuwarden, The Netherlands, 2025. doi:10.21437/SSW.2025-4.
  PDF BibTeX▼

  @inproceedings{BauerZMD25_EmphasisControl_SSW,
      author = "Bauer, Judith and Zalkow, Frank and Müller, Meinard and Dittmar, Christian",
      title = "Explicit Emphasis Control in Text-to-Speech Synthesis",
      booktitle = "Proceedings of the ISCA Speech Synthesis Workshop ({SSW})",
      address = "Leeuwarden, The Netherlands",
      year = "2025",
      pages = "21--27",
      doi = "10.21437/SSW.2025-4",
      customlinkPDF = "https://www.isca-archive.org/ssw\_2025/bauer25\_ssw.html"
  }
  

• Zahra Kolagar, Frank Zalkow, and Alessandra Zarcone. Investigating methods for mapping learning objectives to bloom's revised taxonomy in course descriptions for higher education. In Proceedings of the Workshop on Innovative Use of NLP for Building Educational Applications (BEA), 415–445. Vienna, Austria, 2025. doi:10.18653/v1/2025.bea-1.32.
  PDF BibTeX▼

  @inproceedings{KolagarZZ25_BloomsTaxonomy_BEA,
      author = "Kolagar, Zahra and Zalkow, Frank and Zarcone, Alessandra",
      title = "Investigating Methods for Mapping Learning Objectives to Bloom's Revised Taxonomy in Course Descriptions for Higher Education",
      booktitle = "Proceedings of the Workshop on Innovative Use of {NLP} for Building Educational Applications ({BEA})",
      address = "Vienna, Austria",
      year = "2025",
      pages = "415--445",
      doi = "10.18653/v1/2025.bea-1.32",
      customlinkPDF = "https://aclanthology.org/2025.bea-1.32/"
  }
  

• Subhayu Ghosh, Frank Zalkow, and Nanda Dulal Jana. Enhanced audio-visual speech synthesis via multi-discriminative learning. IEEE Transactions on Multimedia, ():, 2025. accepted. doi:.
  PDF BibTeX▼

  @article{GoshEtAl25_AudioVisualTTS_TMM,
      author = "Ghosh, Subhayu and Zalkow, Frank and Jana, Nanda Dulal",
      title = "Enhanced Audio-Visual Speech Synthesis via Multi-Discriminative Learning",
      journal = "{IEEE} Transactions on Multimedia",
      volume = "",
      number = "",
      year = "2025",
      pages = "",
      doi = "",
      customlinkPDF = "",
      note = "accepted"
  }
  

• Frank Zalkow, Paolo Sani, Kishor Kayyar Lakshminarayana, Emanuël A. P. Habets, Nicola Pia, and Christian Dittmar. Bridging the training–inference gap in TTS: Training strategies for robust generative postprocessing for low-resource speakers. In Proceedings of the Conference of the International Speech Communication Association (INTERSPEECH), 2470–2474. Rotterdam, The Netherlands, 2025. doi:10.21437/Interspeech.2025-854.
  PDF Details BibTeX▼

  @inproceedings{ZalkowSKHPD25_LowResourceGenerativePostprocessing_INTERSPEECH,
      author = {Zalkow, Frank and Sani, Paolo and Lakshminarayana, Kishor Kayyar and Habets, Emanu{\"e}l A. P. and Pia, Nicola and Dittmar, Christian},
      title = "Bridging the Training–Inference Gap in {TTS}: {T}raining Strategies for Robust Generative Postprocessing for Low-Resource Speakers",
      booktitle = "Proceedings of the Conference of the International Speech Communication Association (INTERSPEECH)",
      address = "Rotterdam, The Netherlands",
      year = "2025",
      pages = "2470--2474",
      doi = "10.21437/Interspeech.2025-854",
      customlinkPDF = "https://www.isca-archive.org/interspeech\_2025/zalkow25\_interspeech.html",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/NLUI/2025-Interspeech-LowResGen"
  }
  

• Kishor Kayyar Lakshminarayana, Frank Zalkow, Christian Dittmar, Nicola Pia, and Emanuël A. P. Habets. Low-resource text-to-speech synthesis using noise-augmented training of ForwardTacotron. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Hyderabad, India, 2025. doi:10.1109/ICASSP49660.2025.10890686.
  PDF BibTeX▼

  @inproceedings{KayyarZDPH25_LowResourceForwardTacotron_ICASSP,
      author = {Lakshminarayana, Kishor Kayyar and Zalkow, Frank and Dittmar, Christian and Pia, Nicola and Habets, Emanu{\"e}l A. P.},
      title = "Low-Resource Text-to-Speech Synthesis Using Noise-Augmented Training of {ForwardTacotron}",
      booktitle = "Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})",
      address = "Hyderabad, India",
      year = "2025",
      pages = "",
      doi = "10.1109/ICASSP49660.2025.10890686",
      customlinkPDF = "https://ieeexplore.ieee.org/document/10890686"
  }
  

2024

• Arunava Kr. Kalita, Christian Dittmar, Paolo Sani, Frank Zalkow, Emanuël A. P. Habets, and Rusha Patra. PAD-VC: A prosody-aware decoder for any-to-few voice conversion. In Proceedings of the International Workshop on Acoustic Signal Enhancement (IWAENC), 389–393. Aalborg, Denmark, 2024. doi:10.1109/IWAENC61483.2024.10694576.
  PDF Details BibTeX▼

  @inproceedings{KalitaDSZHP24_PAD-VC_IWAENC,
      author = {Kalita, Arunava Kr. and Dittmar, Christian and Sani, Paolo and Zalkow, Frank and Habets, Emanu\"{e}l A. P. and Patra, Rusha},
      title = "{PAD-VC}: {A} Prosody-Aware Decoder for Any-to-Few Voice Conversion",
      booktitle = "Proceedings of the International Workshop on Acoustic Signal Enhancement ({IWAENC})",
      address = "Aalborg, Denmark",
      year = "2024",
      pages = "389--393",
      doi = "10.1109/IWAENC61483.2024.10694576",
      customlinkPDF = "https://ieeexplore.ieee.org/document/10694576",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/NLUI/2024-PAD-VC"
  }
  

• Florian Lux, Sarina Meyer, Lyonel Behringer, Frank Zalkow, Phat Do, Matt Coler, Emanuël A. P. Habets, and Ngoc Thang Vu. Meta learning text-to-speech synthesis in over 7000 languages. In Proceedings of the Conference of the International Speech Communication Association (INTERSPEECH), 4958–4962. Kos, Greece, 2024. doi:10.21437/Interspeech.2024-1335.
  PDF Details BibTeX▼

  @inproceedings{LuxEtAl2024_TTS7000Lang_Interspeech,
      author = {Lux, Florian and Meyer, Sarina and Behringer, Lyonel and Zalkow, Frank and Do, Phat and Coler, Matt and Habets, Emanu\"{e}l A. P. and Vu, Ngoc Thang},
      address = "Kos, Greece",
      booktitle = "Proceedings of the Conference of the International Speech Communication Association (INTERSPEECH)",
      pages = "4958--4962",
      title = "Meta Learning Text-to-Speech Synthesis in over 7000 Languages",
      year = "2024",
      doi = "10.21437/Interspeech.2024-1335",
      customlinkPDF = "https://www.isca-archive.org/interspeech\_2024/lux24\_interspeech.html",
      customlinkDetails = "https://huggingface.co/spaces/Flux9665/MassivelyMultilingualTTS"
  }
  

• Subhayu Ghosh, Snehashis Sarkar, Sovan Ghosh, Frank Zalkow, and Nanda Dulal Jana. Audio-visual speech synthesis using vision transformer–enhanced autoencoders with ensemble of loss functions. Applied Intelligence, 54(6):4507–4524, 2024. doi:10.1007/s10489-024-05380-7.
  PDF Details BibTeX▼

  @article{GoshEtAl24_AudioVisualTTS_AppliedIntelligence,
      author = "Ghosh, Subhayu and Sarkar, Snehashis and Ghosh, Sovan and Zalkow, Frank and Jana, Nanda Dulal",
      title = "Audio-visual speech synthesis using vision transformer--enhanced autoencoders with ensemble of loss functions",
      journal = "Applied Intelligence",
      volume = "54",
      number = "6",
      year = "2024",
      pages = "4507--4524",
      doi = "10.1007/s10489-024-05380-7",
      customlinkPDF = "https://link.springer.com/article/10.1007/s10489-024-05380-7",
      customlinkDetails = "https://github.com/Subhayu-ghosh/ViTAE-AVSS"
  }
  

• Judith Bauer, Frank Zalkow, Meinard Müller, and Christian Dittmar. Evaluating the impact of prosody feature normalization on the controllability of pitch in speech synthesis. In Elektronische Sprachsignalverarbeitung (ESSV), 188–195. Regensburg, Germany, 2024. doi:10.35096/othr/pub-7097.
  PDF BibTeX▼

  @inproceedings{BauerEtAl2024_ProsodyNormalization_ESSV,
      author = {Bauer, Judith and Zalkow, Frank and M\"{u}ller, Meinard and Dittmar, Christian},
      address = "Regensburg, Germany",
      booktitle = "Elektronische Sprachsignalverarbeitung ({ESSV})",
      pages = "188--195",
      title = "Evaluating the Impact of Prosody Feature Normalization on the Controllability of Pitch in Speech Synthesis",
      year = "2024",
      doi = "10.35096/othr/pub-7097",
      customlinkPDF = "https://nbn-resolving.org/urn:nbn:de:bvb:898-opus4-70976"
  }
  

2023

• Christof Weiß, Vlora Arifi-Müller, Michael Krause, Frank Zalkow, Stephanie Klauk, Rainer Kleinertz, and Meinard Müller. Wagner Ring Dataset: A complex opera scenario for music processing and computational musicology. Transactions of the International Society for Music Information Retrieval (TISMIR), 6(1):135–149, 2023. doi:10.5334/tismir.161.
  PDF Details BibTeX▼

  @article{WeissEtAl23_WagnerRingDataset_TISMIR,
      author = {Weiß, Christof and Arifi-M{\"u}ller, Vlora and Krause, Michael and Zalkow, Frank and Klauk, Stephanie and Kleinertz, Rainer and M{\"u}ller, Meinard},
      title = "{W}agner {R}ing {D}ataset: {A} Complex Opera Scenario for Music Processing and Computational Musicology",
      journal = "Transactions of the International Society for Music Information Retrieval ({TISMIR})",
      volume = "6",
      number = "1",
      year = "2023",
      pages = "135--149",
      doi = "10.5334/tismir.161",
      customlinkPDF = "https://transactions.ismir.net/articles/10.5334/tismir.161",
      customlinkDetails = "https://zenodo.org/records/7672157"
  }
  

• Frank Zalkow, Paolo Sani, Michael Fast, Judith Bauer, Mohammad Joshaghani, Kishor Kayyar Lakshminarayana, Emanuël A. P. Habets, and Christian Dittmar. The AudioLabs system for the Blizzard Challenge 2023. In Proceedings of the Blizzard Challenge Workshop, 63–68. Grenoble, France, 2023. doi:10.21437/Blizzard.2023-8.
  PDF BibTeX▼

  @inproceedings{ZalkowEtAl23_AudioLabsBlizzard_Blizzard,
      author = {Zalkow, Frank and Sani, Paolo and Fast, Michael and Bauer, Judith and Joshaghani, Mohammad and Lakshminarayana, Kishor Kayyar and Habets, Emanu{\"e}l A. P. and Dittmar, Christian},
      title = "The {A}udio{L}abs System for the {B}lizzard {C}hallenge 2023",
      booktitle = "Proceedings of the Blizzard Challenge Workshop",
      address = "Grenoble, France",
      year = "2023",
      doi = "10.21437/Blizzard.2023-8",
      pages = "63--68",
      customlinkPDF = "https://www.isca-speech.org/archive/blizzard\_2023/zalkow23\_blizzard.html"
  }
  

• Paolo Sani, Judith Bauer, Frank Zalkow, Emanuël A. P. Habets, and Christian Dittmar. Improving the naturalness of synthesized spectograms for TTS using GAN-based post-processing. In Proceedings of the ITG Conference on Speech Communication, 270–274. Aachen, Germany, 2023. doi:10.30420/456164053.
  PDF Details BibTeX▼

  @inproceedings{SaniBZHD23_Postprocessing_ITG,
      author = {Sani, Paolo and Bauer, Judith and Zalkow, Frank and Habets, Emanu{\"e}l A. P. and Dittmar, Christian},
      title = "Improving the Naturalness of Synthesized Spectograms for {TTS} Using {GAN}-Based Post-Processing",
      booktitle = "Proceedings of the {ITG} Conference on Speech Communication",
      address = "Aachen, Germany",
      year = "2023",
      doi = "10.30420/456164053",
      pages = "270--274",
      customlinkPDF = "https://ieeexplore.ieee.org/document/10363041",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/NLUI/2023-ITG-postprocessing"
  }
  

• Meinard Müller and Frank Zalkow. FMP notebooks. In Peter Moormann and Nicolas Ruth, editors, Musik und Internet: Aktuelle Phänomene populärer Kulturen, Musik und Medien, pages 237–247. Springer VS, Wiesbaden, Germany, 2023. doi:10.1007/978-3-658-39145-4.
  BibTeX▼

  @incollection{MuellerZalkow_FMP_BOOKCHAP,
      author = {M{\"u}ller, Meinard and Zalkow, Frank},
      editor = "Moormann, Peter and Ruth, Nicolas",
      title = "{FMP} Notebooks",
      booktitle = {Musik und Internet: Aktuelle Phänomene popul{\"a}rer Kulturen},
      publisher = "Springer VS",
      address = "Wiesbaden, Germany",
      pages = "237--247",
      year = "2023",
      series = "Musik und Medien",
      doi = "10.1007/978-3-658-39145-4"
  }
  

• Frank Zalkow, Prachi Govalkar, Meinard Müller, Emanuël A. P. Habets, and Christian Dittmar. Evaluating speech–phoneme alignment and its impact on neural text-to-speech synthesis. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP). Rhodes Island, Greece, 2023. doi:10.1109/ICASSP49357.2023.10097248.
  PDF Details BibTeX▼

  @inproceedings{ZalkowGMHD23_EvalAlignmentTTS_ICASSP,
      author = {Zalkow, Frank and Govalkar, Prachi and M{\"u}ller, Meinard and Habets, Emanu{\"e}l A. P. and Dittmar, Christian},
      title = "Evaluating Speech--Phoneme Alignment and Its Impact on Neural Text-To-Speech Synthesis",
      booktitle = "Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})",
      address = "Rhodes Island, Greece",
      year = "2023",
      pages = "",
      doi = "10.1109/ICASSP49357.2023.10097248",
      customlinkPDF = "https://ieeexplore.ieee.org/document/10097248",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/NLUI/2023-ICASSP-eval-alignment-tts"
  }
  

2022

• Yi-Jen Shih, Shih-Lun Wu, Frank Zalkow, Meinard Müller, and Yi-Hsuan Yang. Theme transformer: Symbolic music generation with theme-conditioned transformer. IEEE Transactions on Multimedia, 25:3495–3508, 2022. doi:10.1109/TMM.2022.3161851.
  PDF Details BibTeX▼

  @article{ShihWZMY22_ThemeTransformer_TMM,
      author = {Shih, Yi{-}Jen and Wu, Shih{-}Lun and Zalkow, Frank and M{\"u}ller, Meinard and Yang, Yi{-}Hsuan},
      title = "Theme Transformer: {S}ymbolic Music Generation with Theme-Conditioned Transformer",
      journal = "{IEEE} Transactions on Multimedia",
      volume = "25",
      pages = "3495--3508",
      year = "2022",
      doi = "10.1109/TMM.2022.3161851",
      customlinkPDF = "https://ieeexplore.ieee.org/document/9740506",
      customlinkDetails = "https://atosystem.github.io/ThemeTransformer"
  }
  

2021

• Frank Zalkow and Meinard Müller. CTC-based learning of chroma features for score–audio music retrieval. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 29:2957–2971, 2021. doi:10.1109/TASLP.2021.3110137.
  PDF Details BibTeX▼

  @article{ZalkowMueller21_ChromaCTC_TASLP,
      author = {Zalkow, Frank and M{\"u}ller, Meinard},
      title = "{CTC}-Based Learning of Chroma Features for Score--Audio Music Retrieval",
      journal = "{IEEE}/{ACM} Transactions on Audio, Speech, and Language Processing",
      volume = "29",
      pages = "2957--2971",
      year = "2021",
      doi = "10.1109/TASLP.2021.3110137",
      customlinkPDF = "https://ieeexplore.ieee.org/document/9531521",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2021\_TASLP-ctc-chroma"
  }
  

• Meinard Müller and Frank Zalkow. libfmp: A Python package for fundamentals of music processing. Journal of Open Source Software (JOSS), 2021. doi:10.21105/joss.03326.
  PDF Details BibTeX▼

  @article{MuellerZalkow21_libfmp_JOSS,
      author = {M{\"u}ller, Meinard and Zalkow, Frank},
      title = "{libfmp}: {A} {P}ython Package for Fundamentals of Music Processing",
      journal = "Journal of Open Source Software ({JOSS})",
      volume = "6",
      number = "63",
      year = "2021",
      doi = "10.21105/joss.03326",
      customlinkPDF = "https://joss.theoj.org/papers/10.21105/joss.03326",
      customlinkDetails = "https://github.com/meinardmueller/libfmp"
  }
  

• Frank Zalkow. Learning Audio Representations for Cross-Version Retrieval of Western Classical Music. PhD thesis, Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU), Erlangen, Germany, 2021.
  PDF BibTeX▼

  @phdthesis{Zalkow21_Thesis_PhD,
      author = "Zalkow, Frank",
      title = "Learning Audio Representations for Cross-Version Retrieval of Western Classical Music",
      type = "PhD thesis",
      pages = "172",
      school = {Friedrich-Alexander-Universit{\"a}t Erlangen-N{\"u}rnberg (FAU)},
      address = "Erlangen, Germany",
      year = "2021",
      customlinkPDF = "https://nbn-resolving.org/urn:nbn:de:bvb:29-opus4-167774"
  }
  

• Frank Zalkow, Julian Brandner, and Meinard Müller. Efficient retrieval of music recordings using graph-based index structures. Signals, 2(2):336–352, 2021. doi:10.3390/signals2020021.
  PDF Details BibTeX▼

  @article{ZalkowBM21_Indexing_Signals,
      author = {Zalkow, Frank and Brandner, Julian and M{\"u}ller, Meinard},
      title = "Efficient Retrieval of Music Recordings Using Graph-Based Index Structures",
      journal = "Signals",
      volume = "2",
      number = "2",
      year = "2021",
      doi = "10.3390/signals2020021",
      pages = "336--352",
      customlinkPDF = "https://www.mdpi.com/2624-6120/2/2/21",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2020\_signals-indexing"
  }
  

• Christof Weiß, Frank Zalkow, Vlora Arifi-Müller, Meinard Müller, Hendrik Vincent Koops, Anja Volk, and Harald G. Grohganz. Schubert Winterreise dataset: A multimodal scenario for music analysis. ACM Journal on Computing and Cultural Heritage (JOCCH), 2021. doi:10.1145/3429743.
  PDF Details BibTeX▼

  @article{WeissZAMMKVG21_SWD_JOCCH,
      author = {Wei{\ss}, Christof and Zalkow, Frank and Arifi-M{\"u}ller, Vlora and M{\"u}ller, Meinard and Koops, Hendrik Vincent and Volk, Anja and Grohganz, Harald G.},
      title = "{S}chubert {W}interreise Dataset: {A} Multimodal Scenario for Music Analysis",
      journal = "{ACM} Journal on Computing and Cultural Heritage ({JOCCH})",
      volume = "14",
      number = "2",
      year = "2021",
      doi = "10.1145/3429743",
      customlinkPDF = "https://dl.acm.org/doi/10.1145/3429743",
      customlinkDetails = "https://doi.org/10.5281/zenodo.4431535"
  }
  

2020

• Frank Zalkow, Stefan Balke, Vlora Arifi-Müller, and Meinard Müller. MTD: a multimodal dataset of musical themes for MIR research. Transactions of the International Society for Music Information Retrieval (TISMIR), 3(1):180–192, 2020. doi:10.5334/tismir.68.
  PDF Details BibTeX▼

  @article{ZalkowBAM20_MTD_TISMIR,
      author = {Zalkow, Frank and Balke, Stefan and Arifi-M{\"{u}}ller, Vlora and M{\"{u}}ller, Meinard},
      title = "{MTD}: A Multimodal Dataset of Musical Themes for {MIR} Research",
      journal = "Transactions of the International Society for Music Information Retrieval ({TISMIR})",
      volume = "3",
      number = "1",
      year = "2020",
      pages = "180--192",
      doi = "10.5334/tismir.68",
      customlinkPDF = "https://transactions.ismir.net/articles/10.5334/tismir.68/",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/MTD"
  }
  

• Stephanie Klauk and Frank Zalkow. Methoden computergestützter melodischer Analyse am Beispiel italienischer Streichquartette. In Stephanie Klauk, editor, Instrumentalmusik neben Haydn und Mozart. Analyse, Aufführungspraxis und Edition, pages 151–168. Saarbrücker Studien zur Musikwissenschaft 20, Königshausen & Neumann, Saarbrücken, Germany, 2020.
  BibTeX▼

  @incollection{KlaukZalkow20_MelodischeAnalyseStreichquartette_SSM,
      author = "Klauk, Stephanie and Zalkow, Frank",
      editor = "Klauk, Stephanie",
      title = "{M}ethoden computergestützter melodischer {A}nalyse am {B}eispiel italienischer {S}treichquartette",
      booktitle = {{I}nstrumentalmusik neben {H}aydn und {M}ozart. {A}nalyse, {A}uff{\"u}hrungspraxis und {E}dition},
      pages = "151--168",
      year = "2020",
      publisher = {Saarbr{\"u}cker Studien zur Musikwissenschaft 20, K{\"o}nigshausen \\& Neumann},
      address = {Saarbr{\"u}cken, Germany}
  }
  

• Michael Krause, Frank Zalkow, Julia Zalkow, Christof Weiß, and Meinard Müller. Classifying leitmotifs in recordings of operas by Richard Wagner. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 473–480. Montréal, Canada, 2020.
  PDF Details BibTeX▼

  @inproceedings{KrauseZZWM20_LeitmotifClassification_ISMIR,
      author = {Krause, Michael and Zalkow, Frank and Zalkow, Julia and Wei{\ss}, Christof and M{\"u}ller, Meinard},
      title = "Classifying Leitmotifs in Recordings of Operas by {R}ichard {W}agner",
      booktitle = "Proceedings of the International Society for Music Information Retrieval Conference ({ISMIR})",
      address = "Montr{\'{e}}al, Canada",
      pages = "473--480",
      year = "2020",
      customlinkPDF = "https://archives.ismir.net/ismir2020/paper/000019.pdf",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2020-ISMIR-LeitmotifClassification"
  }
  

• Hendrik Schreiber, Frank Zalkow, and Meinard Müller. Modeling and estimating local tempo: A case study on Chopin's mazurkas. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 773–779. Montréal, Canada, 2020.
  PDF BibTeX▼

  @inproceedings{SchreiberZM20_LocalTempoChopin_ISMIR,
      author = {Schreiber, Hendrik and Zalkow, Frank and M{\"u}ller, Meinard},
      title = "Modeling and Estimating Local Tempo: {A} Case Study on {C}hopin's Mazurkas",
      booktitle = "Proceedings of the International Society for Music Information Retrieval Conference ({ISMIR})",
      address = "Montr{\'{e}}al, Canada",
      pages = "773--779",
      year = "2020",
      customlinkPDF = "https://archives.ismir.net/ismir2020/paper/000014.pdf"
  }
  

• Frank Zalkow and Meinard Müller. Using weakly aligned score–audio pairs to train deep chroma models for cross-modal music retrieval. In Proceedings of the International Society for Music Information Retrieval Conference (ISMIR), 184–191. Montréal, Canada, 2020.
  PDF Details BibTeX▼

  @inproceedings{ZalkowMueller20_WeaklyAlignedCTC_ISMIR,
      author = {Zalkow, Frank and M{\"u}ller, Meinard},
      title = "Using Weakly Aligned Score--Audio Pairs to Train Deep Chroma Models for Cross-Modal Music Retrieval",
      booktitle = "Proceedings of the International Society for Music Information Retrieval Conference ({ISMIR})",
      address = "Montr{\'{e}}al, Canada",
      pages = "184--191",
      year = "2020",
      customlinkPDF = "https://archives.ismir.net/ismir2020/paper/000023.pdf",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2020-ISMIR-ctc-chroma"
  }
  

• Frank Zalkow and Meinard Müller. Learning low-dimensional embeddings of audio shingles for cross-version retrieval of classical music. Applied Sciences, 2020. doi:10.3390/app10010019.
  PDF BibTeX▼

  @article{ZalkowMueller20_Shingles_AppliedSciences,
      author = {Zalkow, Frank and M{\"u}ller, Meinard},
      title = "Learning Low-Dimensional Embeddings of Audio Shingles for Cross-Version Retrieval of Classical Music",
      journal = "Applied Sciences",
      volume = "10",
      number = "1",
      year = "2020",
      doi = "10.3390/app10010019",
      customlinkPDF = "https://www.mdpi.com/2076-3417/10/1/19"
  }
  

2019

• Frank Zalkow, Angel Villar Corrales, TJ Tsai, Vlora Arifi-Müller, and Meinard Müller. Tools for semi-automatic bounding box annotation of musical measures in sheet music. In Demos and Late Breaking News of the International Society for Music Information Retrieval Conference (ISMIR). Delft, The Netherlands, 2019.
  PDF Details BibTeX▼

  @inproceedings{2019_ZalkowVTAM_MeasureAnnotation_ISMIR-LBD,
      author = {Zalkow, Frank and Corrales, Angel Villar and Tsai, TJ and Arifi-M{\"u}ller, Vlora and M{\"u}ller, Meinard},
      title = "Tools for Semi-Automatic Bounding Box Annotation of Musical Measures in Sheet Music",
      booktitle = "Demos and Late Breaking News of the International Society for Music Information Retrieval Conference ({ISMIR})",
      address = "Delft, The Netherlands",
      year = "2019",
      customlinkPDF = "https://www.audiolabs-erlangen.de/content/resources/MIR/00\_2019-ISMIR-LBD-Measures/2019\_ZalkowVTAM\_BoundingBox\_ISMIR-LBD.pdf",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2019-ISMIR-LBD-Measures"
  }
  

• Prachi Govalkar, Johannes Fischer, Frank Zalkow, and Christian Dittmar. A comparison of recent neural vocoders for speech signal reconstruction. In Proceedings of the ISCA Speech Synthesis Workshop (SSW), 7–12. Vienna, Austria, September 2019. doi:10.21437/SSW.2019-2.
  PDF BibTeX▼

  @inproceedings{GovalkarFZD19_ComparisionVocoders_SSW,
      author = "Govalkar, Prachi and Fischer, Johannes and Zalkow, Frank and Dittmar, Christian",
      title = "A Comparison of Recent Neural Vocoders for Speech Signal Reconstruction",
      booktitle = "Proceedings of the ISCA Speech Synthesis Workshop ({SSW})",
      address = "Vienna, Austria",
      month = "September",
      year = "2019",
      doi = "10.21437/SSW.2019-2",
      pages = "7--12",
      customlinkPDF = "https://www.audiolabs-erlangen.de/resources/NLUI/2019-SSW-NeuralVocoders/"
  }
  

• Meinard Müller and Frank Zalkow. FMP notebooks: educational material for teaching and learning fundamentals of music processing. In Proceedings of the International Conference on Music Information Retrieval (ISMIR), 573–580. Delft, The Netherlands, November 2019.
  PDF Details BibTeX▼

  @inproceedings{MuellerZ19_FMP_ISMIR,
      author = {M{\"u}ller, Meinard and Zalkow, Frank},
      title = "{FMP} Notebooks: Educational Material for Teaching and Learning Fundamentals of Music Processing",
      booktitle = "Proceedings of the International Conference on Music Information Retrieval ({ISMIR})",
      address = "Delft, The Netherlands",
      month = "November",
      year = "2019",
      pages = "573--580",
      customlinkPDF = "https://archives.ismir.net/ismir2019/paper/000069.pdf",
      customlinkDetails = "https://www.audiolabs-erlangen.de/FMP"
  }
  

• Frank Zalkow, Stefan Balke, and Meinard Müller. Evaluating salience representations for cross-modal retrieval of western classical music recordings. In Proceedings of the IEEE International Conference on Acoustics, Speech, and Signal Processing (ICASSP), 331–335. Brighton, United Kingdom, 2019. doi:10.1109/ICASSP.2019.8683609.
  PDF Details BibTeX▼

  @inproceedings{ZalkowBM19_SalienceRetrieval_ICASSP,
      author = {Zalkow, Frank and Balke, Stefan and M{\"u}ller, Meinard},
      title = "Evaluating Salience Representations for Cross-Modal Retrieval of Western Classical Music Recordings",
      booktitle = "Proceedings of the {IEEE} International Conference on Acoustics, Speech, and Signal Processing ({ICASSP})",
      address = "Brighton, United Kingdom",
      year = "2019",
      pages = "331--335",
      doi = "10.1109/ICASSP.2019.8683609",
      customlinkPDF = "https://ieeexplore.ieee.org/document/8683609",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2019-ICASSP-BarlowMorgenstern/"
  }
  

2018

• Frank Zalkow, Sebastian Rosenzweig, Johannes Graulich, Lukas Dietz, El Mehdi Lemnaouar, and Meinard Müller. A web-based interface for score following and track switching in choral music. In Demos and Late Breaking News of the International Society for Music Information Retrieval Conference (ISMIR). Paris, Fance, 2018.
  PDF Details BibTeX▼

  @inproceedings{ZalkowRGDMM18_Carus_ISMIR-LBD,
      author = {Zalkow, Frank and Rosenzweig, Sebastian and Graulich, Johannes and Dietz, Lukas and Lemnaouar, El Mehdi and M{\"u}ller, Meinard},
      title = "A Web-Based Interface for Score Following and Track Switching in Choral Music",
      booktitle = "Demos and Late Breaking News of the International Society for Music Information Retrieval Conference ({ISMIR})",
      address = "Paris, Fance",
      year = "2018",
      customlinkPDF = "https://www.audiolabs-erlangen.de/content/resources/MIR/00\_2018-ISMIR-LBD-Carus/2018\_ZalkowRGDMM\_Carus\_ISMIR-LBD.pdf",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2018-ISMIR-LBD-Carus"
  }
  

• Frank Zalkow and Meinard Müller. Vergleich von PCA- und Autoencoder-basierter Dimensionsreduktion von Merkmalssequenzen für die effiziente Musiksuche. In Proceedings of the Deutsche Jahrestagung für Akustik (DAGA), 1526–1529. München, Germany, 2018.
  PDF BibTeX▼

  @inproceedings{ZalkowM18_VergleichAutoencoderPCA_DAGA,
      author = {Zalkow, Frank and M{\"u}ller, Meinard},
      title = {Vergleich von {PCA}- und {A}utoencoder-basierter {D}imensionsreduktion von {M}erkmalssequenzen f{\"u}r die effiziente {M}usiksuche},
      booktitle = {Proceedings of the {D}eutsche {J}ahrestagung f{\"u}r {A}kustik ({DAGA})},
      address = {M{\"u}nchen, Germany},
      year = "2018",
      pages = "1526--1529",
      customlinkPDF = "https://pub.dega-akustik.de/DAGA\_2018/data/articles/000079.pdf"
  }
  

• Meinard Müller, Helmut Hedwig, Frank Zalkow, and Stefan Popescu. Constraint-based time-scale modification of music recordings for noise beautification. Applied Sciences, March 2018. doi:10.3390/app8030436.
  PDF Details BibTeX▼

  @article{MuellerHZP18_NoiseBeauty_AppliedSciences,
      author = {M{\"u}ller, Meinard and Hedwig, Helmut and Zalkow, Frank and Popescu, Stefan},
      journal = "Applied Sciences",
      title = "Constraint-Based Time-Scale Modification of Music Recordings for Noise Beautification",
      year = "2018",
      month = "March",
      volume = "8",
      number = "3",
      articlenumber = "436",
      doi = "10.3390/app8030436",
      customlinkPDF = "http://www.mdpi.com/2076-3417/8/3/436",
      customlinkDetails = "https://www.audiolabs-erlangen.de/resources/MIR/2018-MRI-NoiseBeauty"
  }
  

2017

• Frank Zalkow, Christof Weiß, and Meinard Müller. Exploring tonal-dramatic relationships in richard Wagner’s ring cycle. In Proceedings of the International Conference on Music Information Retrieval (ISMIR), 642–648. Suzhou, China, 2017.
  PDF BibTeX▼

  @inproceedings{ZalkowWM17_WagnerHarmony_ISMIR,
      author = {Zalkow, Frank and Wei{\ss}, Christof and M{\"u}ller, Meinard},
      title = "Exploring Tonal-Dramatic Relationships in Richard {W}agne{r’s} Ring Cycle",
      booktitle = "Proceedings of the International Conference on Music Information Retrieval ({ISMIR})",
      address = "Suzhou, China",
      year = "2017",
      pages = "642--648",
      articlenumber = "436",
      customlinkPDF = "https://archives.ismir.net/ismir2017/paper/000132.pdf"
  }
  

• Christof Weiß, Frank Zalkow, Meinard Müller, Stephanie Klauk, and Rainer Kleinertz. Versionsübergreifende Visualisierung harmonischer Verläufe: Eine Fallstudie zu Wagners Ring-Zyklus. In Proceedings of the Jahrestagung der Gesellschaft für Informatik (GI), 205–217. Chemnitz, Germany, 2017. doi:10.18420/in2017_14.
  PDF BibTeX▼

  @inproceedings{WeissZMKK17_WagnerRing_GI,
      author = {Wei{\ss}, Christof and Zalkow, Frank and M{\"u}ller, Meinard and Klauk, Stephanie and Kleinertz, Rainer},
      title = {{V}ersions{\"u}bergreifende {V}isualisierung harmonischer {V}erl{\"a}ufe: {E}ine {F}allstudie zu {W}agners {R}ing-{Z}yklus},
      booktitle = {Proceedings of the Jahrestagung der Gesellschaft f{\"u}r Informatik ({GI})},
      address = "Chemnitz, Germany",
      year = "2017",
      pages = "205--217",
      customlinkPDF = "https://dl.gi.de/handle/20.500.12116/3903",
      doi = "10.18420/in2017\_14"
  }
  

• Frank Zalkow, Christof Weiß, Thomas Prätzlich, Vlora Arifi-Müller, and Meinard Müller. A multi-version approach for transferring measure annotations between music recordings. In Proceedings of the AES International Conference on Semantic Audio, 148–155. Erlangen, Germany, 2017. doi:10.17743/aesconf.2017.978-1-942220-15-2.
  PDF BibTeX▼

  @inproceedings{ZalkowWPAM17_MeasureTransfer_AES,
      author = {Zalkow, Frank and Wei{\ss}, Christof and Pr{\"a}tzlich, Thomas and Arifi-M{\"u}ller, Vlora and M{\"u}ller, Meinard},
      title = "A Multi-Version Approach for Transferring Measure Annotations Between Music Recordings",
      booktitle = "Proceedings of the {AES} International Conference on Semantic Audio",
      pages = "148--155",
      address = "Erlangen, Germany",
      year = "2017",
      doi = "10.17743/aesconf.2017.978-1-942220-15-2",
      customlinkPDF = "http://www.aes.org/e-lib/browse.cfm?elib=18772"
  }
  

2016

• Stephanie Klauk and Frank Zalkow. Das italienische Streichquartett im 18. Jahrhundert. Möglichkeiten der semiautomatisierten Stilanalyse. In Wolfgang Auhagen and Wolfgang Hirschmann, editors, Bericht zur Jahrestagung der Gesellschaft für Musikforschung (GfM) 2015 in Halle/Saale. Mainz, Germany, 2016. Schott Campus.
  PDF BibTeX▼

  @inproceedings{KlaukZalkow16_Streichq_GfM,
      author = "Klauk, Stephanie and Zalkow, Frank",
      editor = "Auhagen, Wolfgang and Hirschmann, Wolfgang",
      title = "{D}as italienische {S}treichquartett im 18. {J}ahrhundert. {M}öglichkeiten der semiautomatisierten {S}tilanalyse",
      booktitle = {{B}ericht zur {J}ahrestagung der {G}esellschaft f{\"u}r {M}usikforschung ({GfM}) 2015 in Halle/Saale},
      publisher = "{S}chott {C}ampus",
      address = "Mainz, Germany",
      year = "2016",
      customlinkPDF = "http://schott-campus.com/wp-content/uploads/2016/09/klauk\_zalkow\_italienisches-streichquartett.pdf"
  }
  

• Frank Zalkow, Stephan Brand, and Bejamin Graf. Musical Style Modification as an Optimization Problem. In Hans Timmermans, editor, Proceedings of the International Computer Music Conference Utrecht 2016, 206–211. Utrecht, Netherlands, 2016. HKU University of the Arts Utrecht, HKU Music and Technology.
  PDF BibTeX▼

  @inproceedings{ZalkowBrandGraf16_StyleOpt_ICMC,
      author = "Zalkow, Frank and Brand, Stephan and Graf, Bejamin",
      editor = "Timmermans, Hans",
      title = "{M}usical {S}tyle {M}odification as an {O}ptimization {P}roblem",
      booktitle = "{P}roceedings of the {I}nternational {C}omputer {M}usic {C}onference {U}trecht 2016",
      publisher = "{HKU} {U}niversity of the {A}rts {U}trecht, {HKU} {M}usic and {T}echnology",
      address = "Utrecht, Netherlands",
      year = "2016",
      pages = "206--211",
      customlinkPDF = "http://hdl.handle.net/2027/spo.bbp2372.2016.041"
  }