Table of Contents

• Interpreting Song Lyrics with an Audio-Informed Pre-trained Language ModelYixiao Zhang, Junyan Jiang, Gus Xia, Simon Dixon. 19-26 [doi]
• Toward postprocessing-free neural networks for joint beat and downbeat estimationTsung-Ping Chen, Li Su 0004. 27-35 [doi]
• Music Translation: Generating Piano Arrangements in Different Playing LevelsMatan Gover, Oded Zewi. 36-43 [doi]
• Scaling Polyphonic Transcription with Mixtures of Monophonic TranscriptionsIan Simon, Josh Gardner, Curtis Hawthorne, Ethan Manilow, Jesse H. Engel. 44-51 [doi]
• Attention-based audio embeddings for query-by-exampleAnup Singh, Kris Demuynck, Vipul Arora 0001. 52-58 [doi]
• SIATEC-C: Computationally efficient repeated pattern discovery in polyphonic musicOtso Björklund. 59-66 [doi]
• Tailed U-Net: Multi-Scale Music Representation LearningMarcel A. Vélez Vásquez, John Ashley Burgoyne. 67-75 [doi]
• DDSP-based Singing Vocoders: A New Subtractive-based Synthesizer and A Comprehensive EvaluationDa-Yi Wu, Wen-Yi Hsiao, Fu-Rong Yang, Oscar Friedman, Warren Jackson, Scott Bruzenak, Yi-Wen Liu, Yi-Hsuan Yang. 76-83 [doi]
• Equivariant self-supervision for musical tempo estimationElio Quinton. 84-92 [doi]
• How Music features and Musical Data Representations Affect Objective Evaluation of Music Composition: A Review of CSMT Data Challenge 2020Yuqiang Li, Shengchen Li, George Fazekas. 93-99 [doi]
• YM2413-MDB: A Multi-Instrumental FM Video Game Music Dataset with Emotion AnnotationsEunjin Choi, Yoonjin Chung, Seolhee Lee, JongIk Jeon, Taegyun Kwon, Juhan Nam. 100-108 [doi]
• Detecting Symmetries of All Cardinalities With Application to Musical 12-Tone RowsAnil Venkatesh, Viren Sachdev. 109-115 [doi]
• The power of deep without going deep? A study of HDPGMM music representation learningJaehun Kim, Cynthia C. S. Liem. 116-124 [doi]
• Pop Music Generation with Controllable Phrase LengthsDaiki Naruse, Tomoyuki Takahata, Yusuke Mukuta, Tatsuya Harada. 125-131 [doi]
• Exploiting Pre-trained Feature Networks for Generative Adversarial Networks in Audio-domain Loop GenerationYen-Tung Yeh, Yi-Hsuan Yang, Bo-Yu Chen. 132-140 [doi]
• Modeling the rhythm from lyrics for melody generation of pop songsDaiyu Zhang, Ju-Chiang Wang, Katerina Kosta, Jordan B. L. Smith, Shicen Zhou. 141-148 [doi]
• Visualization for AI-Assisted ComposingSimeon Rau, Frank Heyen, Stefan Wagner 0001, Michael Sedlmair. 151-159 [doi]
• Retrieving musical information from neural data: how cognitive features enrich acoustic onesEllie Abrams, Eva Muñoz Vidal, Claire Pelofi, Pablo Ripollés. 160-168 [doi]
• Beat Transformer: Demixed Beat and Downbeat Tracking with Dilated Self-AttentionJingwei Zhao, Gus Xia, Ye Wang. 169-177 [doi]
• Sketching the Expression: Flexible Rendering of Expressive Piano Performance with Self-Supervised LearningSeungyeon Rhyu, Sarah Kim, Kyogu Lee. 178-185 [doi]
• Exploiting Device and Audio Data to Tag Music with User-Aware Listening ContextsKarim M. Ibrahim, Elena V. Epure, Geoffroy Peeters, Gaël Richard. 186-192 [doi]
• Jukedrummer: Conditional Beat-aware Audio-domain Drum Accompaniment Generation via Transformer VQ-VAEYueh-Kao Wu, Ching-Yu Chiu, Yi-Hsuan Yang. 193-200 [doi]
• Learning Hierarchical Metrical Structure Beyond MeasuresJunyan Jiang, Daniel Chin, Yixiao Zhang, Gus Xia. 201-209 [doi]
• Mid-level Harmonic Audio Features for Musical Style ClassificationFrancisco C. F. Almeida, Gilberto Bernardes, Christof Weiss. 210-217 [doi]
• Distortion Audio Effects: Learning How to Recover the Clean SignalJohannes Imort, Giorgio Fabbro, Marco A. Martínez Ramírez, Stefan Uhlich, Yuichiro Koyama, Yuki Mitsufuji. 218-225 [doi]
• End-to-End Full-Page Optical Music Recognition for Mensural NotationAntonio Ríos-Vila, José M. Iñesta, Jorge Calvo-Zaragoza. 226-232 [doi]
• Mel Spectrogram Inversion with Stable PitchBruno Di Giorgi, Mark Levy, Richard Sharp. 233-239 [doi]
• Latent feature augmentation for chorus detectionXingjian Du, Huidong Liang, Yuan Wan, Yuheng Lin, Ke Chen 0021, Bilei Zhu, Zejun Ma. 240-247 [doi]
• AccoMontage2: A Complete Harmonization and Accompaniment Arrangement SystemLi Yi, Haochen Hu, Jingwei Zhao, Gus Xia. 248-255 [doi]
• Supervised and Unsupervised Learning of Audio Representations for Music UnderstandingMatthew C. McCallum, Filip Korzeniowski, Sergio Oramas, Fabien Gouyon, Andreas F. Ehmann. 256-263 [doi]
• Generating Coherent Drum Accompaniment with Fills and ImprovisationsRishabh Dahale, Vaibhav Talwadker, Preeti Rao, Prateek Verma. 264-271 [doi]
• Bottlenecks and solutions for audio to score alignment researchAlia Morsi, Xavier Serra. 272-279 [doi]
• Raga Classification From Vocal Performances Using Multimodal Analysis Martin Clayton, Preeti Rao, Nithya Nadig Shikarpur, Sujoy Roychowdhury, Jin Li. 283-290 [doi]
• Traces of Globalization in Online Music Consumption Patterns and Results of Recommendation AlgorithmsOleg Lesota, Emilia Parada-Cabaleiro, Stefan Brandl, Elisabeth Lex, Navid Rekabsaz, Markus Schedl. 291-297 [doi]
• Network Analyses for Cross-Cultural Music PopularityKongmeng Liew, Vipul Mishra, Yangyang Zhou, Elena V. Epure, Romain Hennequin, Shoko Wakamiya, Eiji Aramaki. 298-305 [doi]
• Three related corpora in Middle Byzantine music notation and a preliminary comparative analysisPolykarpos Polykarpidis, Dionysios Kalofonos, Dimitrios Balageorgos, Christina Anagnostopoulou. 306-313 [doi]
• Playing Technique Detection by Fusing Note Onset Information in Guzheng PerformanceDichucheng Li, Yulun Wu, Qinyu Li, Jiahao Zhao, Yi Yu 0001, Fan Xia, Wei Li 0012. 314-320 [doi]
• KDC: an open corpus for computational research of dastg?hi musicBabak Nikzat, Rafael Caro Repetto. 321-328 [doi]
• Inaccurate Prediction or Genre Evolution? Rethinking Genre ClassificationKe Nie. 329-336 [doi]
• In Search of Sañc?ras: Tradition-informed Repeated Melodic Pattern Recognition in Carnatic MusicThomas Nuttall, Genís Plaja-Roglans, Lara Pearson, Xavier Serra. 337-344 [doi]
• Automatic Chinese National Pentatonic Modes Recognition Using Convolutional Neural NetworkZhaowen Wang, Mingjin Che, Yue Yang, Wenwu Meng, Qinyu Li, Fan Xia, Wei Li 0012. 345-352 [doi]
• Teach Yourself Georgian Folk Songs Dataset: A Annotated Corpus Of Traditional Vocal PolyphonyDavid Gillman, Atalay Kutlay, Uday Goyat. 353-360 [doi]
• Adapting meter tracking models to Latin American musicLucas S. Maia, Martín Rocamora, Luiz W. P. Biscainho, Magdalena Fuentes. 361-368 [doi]
• Critiquing Task- versus Goal-oriented Approaches: A Case for Makam RecognitionKaustuv Kanti Ganguli, Sertan Sentürk, Carlos Guedes. 369-376 [doi]
• A Dataset for Greek Traditional and Folk Music: LyraCharilaos Papaioannou, Ioannis Valiantzas, Theodore Giannakopoulos, Maximos A. Kaliakatsos-Papakostas, Alexandros Potamianos. 377-383 [doi]
• Analysis and detection of singing techniques in repertoires of J-POP solo singersYuya Yamamoto, Juhan Nam, Hiroko Terasawa. 384-391 [doi]
• Performance MIDI-to-score conversion by neural beat trackingLele Liu, Qiuqiang Kong, Veronica Morfi, Emmanouil Benetos. 395-402 [doi]
• Symbolic Music Loop Generation with Neural Discrete RepresentationsSangjun Han, Hyeongrae Ihm, Moontae Lee, Woohyung Lim. 403-410 [doi]
• Automatic music mixing with deep learning and out-of-domain dataMarco A. Martínez Ramírez, Wei-Hsiang Liao, Chihiro Nagashima, Giorgio Fabbro, Stefan Uhlich, Yuki Mitsufuji. 411-418 [doi]
• Music-STAR: a Style Translation system for Audio-based Re-instrumentationMahshid Alinoori, Vassilios Tzerpos. 419-426 [doi]
• Learning Unsupervised Hierarchies of Audio ConceptsDarius Afchar, Romain Hennequin, Vincent Guigue. 427-436 [doi]
• Multi-objective Hyper-parameter Optimization of Behavioral Song EmbeddingsMassimo Quadrana, Antoine Larreche-Mouly, Matthias Mauch. 437-445 [doi]
• ATEPP: A Dataset of Automatically Transcribed Expressive Piano PerformanceHuan Zhang, Jingjing Tang, Syed Rm Rafee, Simon Dixon, George Fazekas, Geraint A. Wiggins. 446-453 [doi]
• PDAugment: Data Augmentation by Pitch and Duration Adjustments for Automatic Lyrics TranscriptionChen Zhang 0020, Jiaxing Yu, LuChin Chang, Xu Tan 0003, Jiawei Chen 0008, Tao Qin, Kejun Zhang. 454-461 [doi]
• Parameter Sensitivity of Deep-Feature based Evaluation Metrics for Audio TexturesChitralekha Gupta, Yize Wei, Zequn Gong, Purnima Kamath, Zhuoyao Li, Lonce Wyse. 462-468 [doi]
• Stability of Symbolic Feature Group Importance in the Context of Multi-Modal Music ClassificationIgor Vatolkin, Cory McKay. 469-476 [doi]
• Multi-pitch Estimation meets Microphone Mismatch: Applicability of Domain AdaptationFranca Bittner, Marcel Gonzalez, Maike L. Richter, Hanna M. Lukashevich, Jakob Abeßer. 477-484 [doi]
• Melody transcription via generative pre-trainingChris Donahue, John Thickstun, Percy Liang. 485-492 [doi]
• Source Separation of Piano Concertos with Test-Time AdaptationYigitcan Özer, Meinard Müller. 493-500 [doi]
• Counterpoint Error-Detection Tools for Optical Music Recognition of Renaissance Polyphonic MusicMartha E. Thomae, Julie Cumming, Ichiro Fujinaga. 501-508 [doi]
• A Dataset of Symbolic Texture Annotations in Mozart Piano SonatasLouis Couturier, Louis Bigo, Florence Levé. 509-516 [doi]
• Violin Etudes: A Comprehensive Dataset for f0 Estimation and Performance AnalysisNazif Can Tamer, Pedro Ramoneda, Xavier Serra. 517-524 [doi]
• Checklist Models for Improved Output Fluency in Piano Fingering PredictionNikita Srivatsan, Taylor Berg-Kirkpatrick. 525-531 [doi]
• Sonus Texere! Automated Dense Soundtrack Construction for Books using Movie AdaptationsJaidev Shriram, Makarand Tapaswi, Vinoo Alluri. 535-542 [doi]
• Musika! Fast Infinite Waveform Music GenerationMarco Pasini, Jan Schlüter. 543-550 [doi]
• Symphony Generation with Permutation Invariant Language ModelJiafeng Liu, Yuanliang Dong, Zehua Cheng, Xinran Zhang, Xiaobing Li, Feng Yu, Maosong Sun. 551-558 [doi]
• MuLan: A Joint Embedding of Music Audio and Natural LanguageQingqing Huang, Aren Jansen, Joonseok Lee, Ravi Ganti, Judith Yue Li, Daniel P. W. Ellis. 559-566 [doi]
• MeloForm: Generating Melody with Musical Form based on Expert Systems and Neural NetworksPeiling Lu, Xu Tan 0003, Botao Yu, Tao Qin, Sheng Zhao, Tie-Yan Liu. 567-574 [doi]
• Towards robust music source separation on loud commercial musicChang-Bin Jeon, Kyogu Lee. 575-582 [doi]
• Towards Quantifying the Strength of Music Scenes Using Live Event DataMichael Zhou, Andrew Mcgraw, Douglas R. Turnbull. 583-590 [doi]
• Learning Multi-Level Representations for Hierarchical Music Structure Analysis.Morgan Buisson, Brian McFee, Slim Essid, Hélène C. Crayencour. 591-597 [doi]
• Multi-instrument Music Synthesis with Spectrogram DiffusionCurtis Hawthorne, Ian Simon, Adam Roberts, Neil Zeghidour, Josh Gardner, Ethan Manilow, Jesse H. Engel. 598-607 [doi]
• DDX7: Differentiable FM Synthesis of Musical Instrument SoundsFranco Caspe, Andrew McPherson 0002, Mark Sandler 0001. 608-616 [doi]
• Singing beat tracking with Self-supervised front-end and linear transformersMojtaba Heydari, Zhiyao Duan. 617-624 [doi]
• EnsembleSet: a new high quality synthesised dataset for chamber ensemble separationSaurjya Sarkar, Emmanouil Benetos, Mark Sandler 0001. 625-632 [doi]
• End-to-End Lyrics Transcription Informed by Pitch and Onset EstimationTengyu Deng, Eita Nakamura, Kazuyoshi Yoshii. 633-639 [doi]
• Contrastive Audio-Language Learning for MusicIlaria Manco, Emmanouil Benetos, Elio Quinton, George Fazekas. 640-649 [doi]
• MusAV: A dataset of relative arousal-valence annotations for validation of audio modelsDmitry Bogdanov, Xavier Lizarraga-Seijas, Pablo Alonso-Jiménez, Xavier Serra. 650-658 [doi]
• What is missing in deep music generation? A study of repetition and structure in popular musicShuqi Dai, Huiran Yu, Roger B. Dannenberg. 659-666 [doi]
• Heterogeneous Graph Neural Network for Music Emotion RecognitionAngelo Cesar Mendes da Silva, Diego Furtado Silva, Ricardo Marcondes Marcacini. 667-674 [doi]
• And what if two musical versions don't share melody, harmony, rhythm, or lyrics ?Mathilde Abrassart, Guillaume Doras. 677-684 [doi]
• A diffusion-inspired training strategy for singing voice extraction in the waveform domainGenís Plaja-Roglans, Marius Miron, Xavier Serra. 685-693 [doi]
• A Model You Can Hear: Audio Identification with Playable PrototypesRomain Loiseau, Baptiste Bouvier, Yann Teytaut, Elliot Vincent, Mathieu Aubry, Loïc Landrieu. 694-700 [doi]
• An Exploration of Generating Sheet Music ImagesMarcos Acosta, Irmak Bukey, T. J. Tsai. 701-708 [doi]
• HPPNet: Modeling the Harmonic Structure and Pitch Invariance in Piano TranscriptionWeixing Wei, Peilin Li, Yi Yu 0001, Wei Li 0012. 709-716 [doi]
• Generating music with sentiment using Transformer-GANsPedro L. T. Neves, José Fornari, João Batista Florindo. 717-725 [doi]
• Improving Choral Music Separation through Expressive Synthesized Data from Sampled InstrumentsKe Chen 0021, Hao-Wen Dong, Yi Luo, Julian J. McAuley, Taylor Berg-Kirkpatrick, Miller S. Puckette, Shlomo Dubnov. 726-732 [doi]
• Ethics of Singing Voice Synthesis: Perceptions of Users and DevelopersKyungyun Lee, Gladys Hitt, Emily Terada, Jin Ha Lee. 733-740 [doi]
• Emotion-driven Harmonisation And Tempo Arrangement of Melodies Using Transfer LearningTakuya Takahashi, Mathieu Barthet. 741-748 [doi]
• Using Activation Functions for Improving Measure-Level Audio SynchronizationYigitcan Özer, Matej Istvanek, Vlora Arifi-Müller, Meinard Müller. 749-756 [doi]
• A deep learning method for melody extraction from a polyphonic symbolic music representationKaterina Kosta, Wei Tsung Lu, Gabriele Medeot, Pierre Chanquion. 757-763 [doi]
• A Reproducibility Study on User-centric MIR Research and Why it is ImportantPeter Knees, Bruce Ferwerda, Andreas Rauber, Sebastian Strumbelj, Annabel Resch, Laurenz Tomandl, Valentin Bauer, Fung Yee Tang, Josip Bobinac, Amila Ceranic, Riad Dizdar. 764-771 [doi]
• Music Separation Enhancement with Generative ModelingNoah Schaffer, Boaz Cogan, Ethan Manilow, Max Morrison, Prem Seetharaman, Bryan Pardo. 772-780 [doi]
• SampleMatch: Drum Sample Retrieval by Musical ContextStefan Lattner. 781-788 [doi]
• A Transformer-Based "Spellchecker" for Detecting Errors in OMR OutputTimothy de Reuse, Ichiro Fujinaga. 789-796 [doi]
• "More than words": Linking Music Preferences and Moral Values through LyricsVjosa Preniqi, Kyriaki Kalimeri, Charalampos Saitis. 797-805 [doi]
• A unified model for zero-shot singing voice conversion and synthesisJui-Te Wu, Jun-You Wang, Jyh-Shing Roger Jang, Li Su 0004. 809-816 [doi]
• Semantic Control of Generative Musical AttributesStewart Greenhill, Majid Abdolshah, Vuong Le, Sunil Gupta 0001, Svetha Venkatesh. 817-824 [doi]
• Music Representation Learning Based on Editorial Metadata from DiscogsPablo Alonso-Jiménez, Xavier Serra, Dmitry Bogdanov. 825-833 [doi]
• Melody Infilling with User-Provided Structural ContextChih-Pin Tan, Alvin W. Y. Su, Yi-Hsuan Yang. 834-841 [doi]
• Robust Melody Track Identification in Symbolic MusicXichu Ma, Xiao Liu, Bowen Zhang, Ye Wang. 842-849 [doi]
• Tracking the Evolution of a Band's Live Performances over DecadesFlorian Thalmann, Eita Nakamura, Kazuyoshi Yoshii. 850-857 [doi]
• Evaluating Generative Audio Systems and Their MetricsAshvala Vinay, Alexander Lerch 0001. 858-865 [doi]
• Representation Learning for the Automatic Indexing of Sound Effects LibrariesAlison B. Ma, Alexander Lerch 0001. 866-875 [doi]
• Concept-Based Techniques for "Musicologist-Friendly" Explanations in Deep Music ClassifiersFrancesco Foscarin, Katharina Hoedt, Verena Praher, Arthur Flexer, Gerhard Widmer. 876-883 [doi]
• Verse versus Chorus: Structure-aware Feature Extraction for Lyrics-based Genre RecognitionMaximilian Mayerl, Stefan Brandl, Günther Specht, Markus Schedl, Eva Zangerle. 884-890 [doi]
• Transfer Learning of wav2vec 2.0 for Automatic Lyric TranscriptionLongshen Ou, Xiangming Gu, Ye Wang. 891-899 [doi]
• A Novel Dataset and Deep Learning Benchmark for Classical Music Form Recognition and AnalysisDaniel Szelogowski, Lopamudra Mukherjee, Benjamin Whitcomb. 900-907 [doi]
• BAF: An audio fingerprinting dataset for broadcast monitoringGuillem Cortes, Alex Ciurana, Emilio Molina, Marius Miron, Owen Meyers, Joren Six, Xavier Serra. 908-916 [doi]
• Cadence Detection in Symbolic Classical Music using Graph Neural Networks.Emmanouil Karystinaios, Gerhard Widmer. 917-924 [doi]
• Domain Adversarial Training on Conditional Variational Auto-Encoder for Controllable Music GenerationJingwei Zhao, Gus Xia, Ye Wang. 925-932 [doi]
• Modeling perceptual loudness of piano tone: theory and applicationsYang Qu, Yutian Qin, Lecheng Chao, Hangkai Qian, Ziyu Wang 0008, Gus Xia. 933-940 [doi]
• On the Impact and Interplay of Input Representations and Network Architectures for Automatic Music TaggingMaximilian Damböck, Richard Vogl, Peter Knees. 941-948 [doi]