Hasil untuk "Music"

G. V. Békésy, E. Wever, W. T. Peake

C. Krumhansl, E. J. Kessler

R. Peterson

P. Stoica, K. Sharman

A. Bennett

J. Haitsma, T. Kalker

C. Krumhansl

W. Thompson, E. G. Schellenberg, Gabriela Husain

Laura K. Cirelli, K. M. Einarson, L. Trainor

Teppo Särkämö, M. Tervaniemi, Sari Laitinen et al.

Tao Sun, Seounmi Youn, Guohua Wu et al.

S. Malloch, C. Trevarthen

Janne Spijkervet, J. Burgoyne

While deep learning has enabled great advances in many areas of music, labeled music datasets remain especially hard, expensive, and time-consuming to create. In this work, we introduce SimCLR to the music domain and contribute a large chain of audio data augmentations to form a simple framework for self-supervised, contrastive learning of musical representations: CLMR. This approach works on raw time-domain music data and requires no labels to learn useful representations. We evaluate CLMR in the downstream task of music classification on the MagnaTagATune and Million Song datasets and present an ablation study to test which of our music-related innovations over SimCLR are most effective. A linear classifier trained on the proposed representations achieves a higher average precision than supervised models on the MagnaTagATune dataset, and performs comparably on the Million Song dataset. Moreover, we show that CLMR's representations are transferable using out-of-domain datasets, indicating that our method has strong generalisability in music classification. Lastly, we show that the proposed method allows data-efficient learning on smaller labeled datasets: we achieve an average precision of 33.1% despite using only 259 labeled songs in the MagnaTagATune dataset (1% of the full dataset) during linear evaluation. To foster reproducibility and future research on self-supervised learning in music, we publicly release the pre-trained models and the source code of all experiments of this paper.

Chongbin Zhang, Jiaxiang Zheng, Moxi Cao

Abstract Music source separation, as a fundamental task in intelligent audio processing, plays a critical role in enhancing the performance of music generation, editing, and understanding systems. However, existing separation models often suffer from structural limitations such as reliance on a single modeling path, entangled time-frequency representations, and difficulty in adapting to heterogeneous sound sources. Furthermore, they struggle to maintain an effective balance between long-range dependency modeling and inference efficiency. To address these challenges, this paper proposes a novel dual-path state space modeling architecture, MSNet. By introducing decoupled modeling mechanisms for temporal and frequency pathways, and incorporating Mamba-based state space units for multidimensional structural parsing of audio signals, MSNet enhances selective control and structural representation in time-frequency modeling. Experimental results demonstrate that MSNet achieves state-of-the-art performance on the MUSDB18 dataset across multiple evaluation metrics. In particular, it shows superior robustness and stability when dealing with dynamically complex sources such as vocals and drums. Additionally, the model achieves a real-time factor (RTF) below 0.1 while maintaining superior separation quality, making it suitable for deployment in practical applications. This study not only demonstrates the feasibility of state space models for complex audio modeling but also introduces a new architectural paradigm for music source separation that balances accuracy and efficiency. The implementation is publicly available at: https://github.com/NMLAB8/Mamba-S-Net.

Raluca RAD

Olivier Messiaen wanted his music to express of his profound Catholic faith, and many of his instrumental works written for the concert hall have an overt religious message. The Star of Bethlehem and the Cross of Golgotha, the most powerful symbols of Christianity, stand at the beginning and the end of Christ’s earthly life. The connection between the birth of Jesus and His death on the cross in theological texts and pictorial representations in Christian art is briefly surveyed. The study focuses on the way Messiaen gave a musical expression to this connection by using similar motifs and themes in movements depicting the joy of the Nativity and movements expressing the sorrow of the Passion. Relevant movements in which the composer uses the so-called Boris motif are presented, followed by an in-depth analysis of the “Theme of the star and the cross” in the piano cycle Vingt Regards sur l’Enfant-Jésus.

Shuhei Tsuchida, Satoru Fukayama, Masahiro Hamasaki et al.

Eduardo Fonseca, Jordi Pons, Xavier Favory et al.

E. Clarke

Sima H Anvari, L. Trainor, Jennifer Woodside et al.

V. Salimpoor, D. Zald, R. Zatorre et al.