@inproceedings{BauerEtAl2024_ProsodyNormalization_ESSV, address = {Regensburg, Germany}, author = {Judith Bauer and Frank Zalkow and Meinard M\"{u}ller and Christian Dittmar}, 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}, url-pdf = {https://nbn-resolving.org/urn:nbn:de:bvb:898-opus4-70976} } @article{GoshEtAl24_AudioVisualTTS_AppliedIntelligence, author = {Subhayu Ghosh and Snehashis Sarkar and Sovan Ghosh and Frank Zalkow and Nanda Dulal Jana}, title = {Audio-visual speech synthesis using vision transformer--enhanced autoencoders with ensemble of loss functions}, journal = {Applied Intelligence}, volume = {}, number = {}, year = {2024}, pages = {}, doi = {10.1007/s10489-024-05380-7}, url-demo = {https://github.com/Subhayu-ghosh/ViTAE-AVSS}, url-pdf = {https://link.springer.com/article/10.1007/s10489-024-05380-7} } @inproceedings{ZalkowGMHD23_EvalAlignmentTTS_ICASSP, author = {Frank Zalkow and Prachi Govalkar and Meinard M{\"u}ller and Emanu{\"e}l A.\ P.\ Habets and Christian Dittmar}, 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}, url-pdf = {https://ieeexplore.ieee.org/document/10097248}, url-details = {https://www.audiolabs-erlangen.de/resources/NLUI/2023-ICASSP-eval-alignment-tts}, } @incollection{MuellerZalkow_FMP_BOOKCHAP, title = {FMP Notebooks}, author = {Meinard M{\"u}ller and Frank Zalkow}, booktitle = {Musik und Internet: Aktuelle Phänomene popul{\"a}rer Kulturen}, editor = {Peter Moormann and Nicolas Ruth}, publisher = {Springer VS}, address = {Wiesbaden, Germany}, pages = {237--247}, year = {2023}, series = {Musik und Medien}, doi = {10.1007/978-3-658-39145-4} } @inproceedings{SaniBZHD23_Postprocessing_ITG, author = {Paolo Sani and Judith Bauer and Frank Zalkow and Emanu{\"e}l A.\ P.\ Habets and Christian Dittmar}, 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}, url-pdf = {https://ieeexplore.ieee.org/document/10363041}, url-details = {https://www.audiolabs-erlangen.de/resources/NLUI/2023-ITG-postprocessing}, } @inproceedings{ZalkowEtAl23_AudioLabsBlizzard_Blizzard, author = {Frank Zalkow and Paolo Sani and Michael Fast and Judith Bauer and Mohammad Joshaghani and Kishor Kayyar Lakshminarayana and Emanu{\"e}l A.\ P.\ Habets and Christian Dittmar}, 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}, url-pdf = {https://www.isca-speech.org/archive/blizzard_2023/zalkow23_blizzard.html}, } @article{WeissEtAl23_WagnerRingDataset_TISMIR, author = {Christof Weiß and Vlora Arifi-M{\"u}ller and Michael Krause and Frank Zalkow and Stephanie Klauk and Rainer Kleinertz and Meinard M{\"u}ller}, 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}, url-demo = {https://zenodo.org/records/7672157}, url-pdf = {https://transactions.ismir.net/articles/10.5334/tismir.161} } @article{ShihWZMY22_ThemeTransformer_TMM, author = {Yi{-}Jen Shih and Shih{-}Lun Wu and Frank Zalkow and Meinard M{\"u}ller and Yi{-}Hsuan Yang}, 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}, url-details = {https://atosystem.github.io/ThemeTransformer}, url-pdf = {https://ieeexplore.ieee.org/document/9740506}, } @article{WeissZAMMKVG21_SWD_JOCCH, author = {Christof Wei{\ss} and Frank Zalkow and Vlora Arifi-M{\"u}ller and Meinard M{\"u}ller and Hendrik Vincent Koops and Anja Volk and Harald G. Grohganz}, 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}, url-pdf = {https://dl.acm.org/doi/10.1145/3429743}, url-details = {https://doi.org/10.5281/zenodo.4431535} } @article{ZalkowBM21_Indexing_Signals, author = {Frank Zalkow and Julian Brandner and Meinard M{\"u}ller}, title = {Efficient Retrieval of Music Recordings Using Graph-Based Index Structures}, journal = {Signals}, volume = {2}, number = {2}, year = {2021}, doi = {10.3390/signals2020021}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2020_signals-indexing}, url-pdf = {https://www.mdpi.com/2624-6120/2/2/21}, pages = {336--352} } @phdthesis{Zalkow21_Thesis_PhD, author = {Frank Zalkow}, title = {Learning Audio Representations for Cross-Version Retrieval of Western Classical Music}, type = {doctoralthesis}, pages = {172}, school = {Friedrich-Alexander-Universit{\"a}t Erlangen-N{\"u}rnberg (FAU)}, address = {Erlangen, Germany}, year = {2021}, url-details = {https://nbn-resolving.org/urn:nbn:de:bvb:29-opus4-167774}, } @article{MuellerZalkow21_libfmp_JOSS, author = {Meinard M{\"u}ller and Frank Zalkow}, 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}, url-details = {https://github.com/meinardmueller/libfmp}, } @article{ZalkowMueller21_ChromaCTC_TASLP, author = {Frank Zalkow and Meinard M{\"u}ller}, 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}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2021_TASLP-ctc-chroma}, url-pdf = {https://ieeexplore.ieee.org/document/9531521}, } @article{ZalkowMueller20_Shingles_AppliedSciences, author = {Frank Zalkow and Meinard M{\"u}ller}, 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}, url-details = {https://www.mdpi.com/2076-3417/10/1/19}, url-pdf = {2020_ZalkowMueller_Shingles_AppliedSciences.pdf} } @inproceedings{ZalkowMueller20_WeaklyAlignedCTC_ISMIR, author = {Frank Zalkow and Meinard M{\"u}ller}, 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}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2020-ISMIR-ctc-chroma}, url-pdf = {2020_ZalkowM_CTC_ISMIR.pdf} } @inproceedings{SchreiberZM20_LocalTempoChopin_ISMIR, author = {Hendrik Schreiber and Frank Zalkow and Meinard M{\"u}ller}, 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}, } @inproceedings{KrauseZZWM20_LeitmotifClassification_ISMIR, author = {Michael Krause and Frank Zalkow and Julia Zalkow and Christof Wei{\ss} and Meinard M{\"u}ller}, 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}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2020-ISMIR-LeitmotifClassification}, } @incollection{KlaukZalkow20_MelodischeAnalyseStreichquartette_SSM, author = {Stephanie Klauk and Frank Zalkow}, 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}, editor = {Stephanie Klauk}, publisher = {Saarbr{\"u}cker Studien zur Musikwissenschaft 20, K{\"o}nigshausen \& Neumann}, address = {Saarbr{\"u}cken, Germany} } @article{ZalkowBAM20_MTD_TISMIR, title = {{MTD}: A Multimodal Dataset of Musical Themes for {MIR} Research}, author = {Frank Zalkow and Stefan Balke and Vlora Arifi-M{\"{u}}ller and Meinard M{\"{u}}ller}, 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}, url-demo = {https://www.audiolabs-erlangen.de/resources/MIR/MTD}, url-details = {https://transactions.ismir.net/articles/10.5334/tismir.68/}, url-pdf = {2020_ZalkowBAM20_MTD_TISMIR.pdf} } @inproceedings{ZalkowBM19_SalienceRetrieval_ICASSP, author = {Frank Zalkow and Stefan Balke and Meinard M{\"u}ller}, 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}, url = {https://ieeexplore.ieee.org/document/8683609}, url-pdf = {https://ieeexplore.ieee.org/document/8683609}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2019-ICASSP-BarlowMorgenstern/}, url-presentation = {2019_poster_ZalkowBM_SalienceThemeRetrieval_ICASSP.pdf} } @inproceedings{MuellerZ19_FMP_ISMIR, author = {Meinard M{\"u}ller and Frank Zalkow}, 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}, url-pdf = {2019_MuellerZalkow_FMP_ISMIR.pdf}, url-details = {https://www.audiolabs-erlangen.de/FMP}, url-presentation = {2019_poster_MuellerZalkow_FMP_ISMIR.pdf} } @inproceedings{GovalkarFZD19_ComparisionVocoders_SSW, author = {Prachi Govalkar and Johannes Fischer and Frank Zalkow and Christian Dittmar}, 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}, url = {http://dx.doi.org/10.21437/SSW.2019-2}, pages = {7--12}, url-pdf = {GovalkarFZD19_ComparisionVocoders_SSW.pdf}, url-details = {https://www.audiolabs-erlangen.de/resources/NLUI/2019-SSW-NeuralVocoders/} } @inproceedings{2019_ZalkowVTAM_MeasureAnnotation_ISMIR-LBD, author = {Frank Zalkow and Angel Villar Corrales and TJ Tsai and Vlora Arifi-M{\"u}ller and Meinard M{\"u}ller}, 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}, url-pdf = {2019_ZalkowVTAM_BoundingBox_ISMIR-LBD.pdf}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2019-ISMIR-LBD-Measures}, url-presentation = {2019_poster_ZalkowVTAM_BoundingBox_ISMIR-LBD.pdf} } @article{MuellerHZP18_NoiseBeauty_AppliedSciences, author = {Meinard M{\"u}ller and Helmut Hedwig and Frank Zalkow and Stefan Popescu}, 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}, url-pdf = {2018_MuellerHZP_NoiseBeauty_AppliedSciences_PrintedVersion.pdf}, url = {http://www.mdpi.com/2076-3417/8/3/436}, url-demo = {https://www.audiolabs-erlangen.de/resources/MIR/2018-MRI-NoiseBeauty}, doi = {10.3390/app8030436}, ISSN = {2076-3417} } @inproceedings{ZalkowM18_VergleichAutoencoderPCA_DAGA, author = {Frank Zalkow and Meinard M{\"u}ller}, 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}, url-pdf = {ZalkowM18_VergleichAutoencoderPCA_DAGA.pdf}, url-presentation = {2018_presentation_ZalkowM_VergleichAutoencoderPCA_Daga.pdf} } @inproceedings{ZalkowRGDMM18_Carus_ISMIR-LBD, author = {Frank Zalkow and Sebastian Rosenzweig and Johannes Graulich and Lukas Dietz and El Mehdi Lemnaouar and Meinard M{\"u}ller}, 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}, url-pdf = {2018_ZalkowRGDMM_Carus_ISMIR-LBD.pdf}, url-details = {https://www.audiolabs-erlangen.de/resources/MIR/2018-ISMIR-LBD-Carus}, url-presentation = {2018_poster_ZalkowRGDMM_Carus_ISMIR-LBD.pdf} } @inproceedings{ZalkowWPAM17_MeasureTransfer_AES, author = {Frank Zalkow and Christof Wei{\ss} and Thomas Pr{\"a}tzlich and Vlora Arifi-M{\"u}ller and Meinard M{\"u}ller}, 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}, url = {http://www.aes.org/e-lib/browse.cfm?elib=18772}, url-pdf = {ZalkowWPAM17_MeasureTransfer_AES.pdf}, url-presentation = {2017_poster_ZalkowWPAM_Triple_AES.pdf} } @inproceedings{WeissZMKK17_WagnerRing_GI, author = {Christof Wei{\ss} and Frank Zalkow and Meinard M{\"u}ller and Stephanie Klauk and Rainer Kleinertz}, 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}, url = {https://dl.gi.de/handle/20.500.12116/3903}, doi = {10.18420/in2017_14} } @inproceedings{ZalkowWM17_WagnerHarmony_ISMIR, author = {Frank Zalkow and Christof Wei{\ss} and Meinard M{\"u}ller}, 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}, url = {https://ismir2017.smcnus.org/wp-content/uploads/2017/10/132_Paper.pdf}, url-pdf = {ZalkowWM17_WagnerHarmony_ISMIR.pdf}, url-presentation = {2017_poster_ZalkowWM_Wagner_ISMIR.pdf} } @inproceedings{ZalkowBrandGraf16_StyleOpt_ICMC, author = {Frank Zalkow and Stephan Brand and Bejamin Graf}, 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}, editor = {Hans Timmermans}, publisher = {{HKU} {U}niversity of the {A}rts {U}trecht, {HKU} {M}usic and {T}echnology}, address = {Utrecht, Netherlands}, year = {2016}, pages = {206--211}, url = {http://hdl.handle.net/2027/spo.bbp2372.2016.041}, url-pdf = {ZalkowBrandGraf16_StyleOpt_ICMC.pdf}, url-presentation = {2016_poster_ZalkowBrandGraf_StyleOpt_ICMC.pdf} } @inproceedings{KlaukZalkow16_Streichq_GfM, author = {Stephanie Klauk and Frank Zalkow}, 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}, editor = {Wolfgang Auhagen and Wolfgang Hirschmann}, publisher = {{S}chott {C}ampus}, address = {Mainz, Germany}, year = {2016}, url = {http://schott-campus.com/das-italienische-streichquartett-im-18-jahrhundert}, url-pdf = {http://schott-campus.com/wp-content/uploads/2016/09/klauk_zalkow_italienisches-streichquartett.pdf}, url-presentation = {2015_poster_KlaukZalkow_Streichq_GfM.pdf} }