论文信息 - Medley2K: A Dataset of Medley Transitions

Medley2K: A Dataset of Medley Transitions

The automatic generation of medleys, i.e., musical pieces formed by different songs concatenated via smooth transitions, is not well studied in the current literature. To facilitate research on this topic, we make available a dataset called Medley2K that consists of 2,000 medleys and 7,712 labeled transitions. Our dataset features a rich variety of song transitions across different music genres. We provide a detailed description of this dataset and validate it by training a state-of-the-art generative model in the task of generating transitions between songs.

[1] Frank Nielsen,et al. DeepBach: a Steerable Model for Bach Chorales Generation , 2016, ICML.

[2] Juan Pablo Bello,et al. MedleyDB 2.0: New Data and a System for Sustainable Data Collection , 2016 .

[3] Ashis Pati,et al. Learning to Traverse Latent Spaces for Musical Score Inpainting , 2019, ISMIR.

[4] Heiga Zen,et al. WaveNet: A Generative Model for Raw Audio , 2016, SSW.

[5] Gaëtan Hadjeres,et al. Deep Learning Techniques for Music Generation , 2019 .

[6] Andrew M. Dai,et al. Music Transformer: Generating Music with Long-Term Structure , 2018, ICLR.

[7] Yi-Hsuan Yang,et al. MidiNet: A Convolutional Generative Adversarial Network for Symbolic-Domain Music Generation , 2017, ISMIR.

[8] Yi-Hsuan Yang,et al. Convolutional Generative Adversarial Networks with Binary Neurons for Polyphonic Music Generation , 2018, ISMIR.

[9] Olof Mogren,et al. C-RNN-GAN: Continuous recurrent neural networks with adversarial training , 2016, ArXiv.

[10] Roger Wattenhofer,et al. MIDI-VAE: Modeling Dynamics and Instrumentation of Music with Applications to Style Transfer , 2018, ISMIR.

[11] Matthias Mauch,et al. MedleyDB: A Multitrack Dataset for Annotation-Intensive MIR Research , 2014, ISMIR.

[12] Yoshua Bengio,et al. Modeling Temporal Dependencies in High-Dimensional Sequences: Application to Polyphonic Music Generation and Transcription , 2012, ICML.