相关论文: Mesostructures: Beyond Spectrogram Loss in Differe…

Subwavelength resonance is a vital acoustic phenomenon in contrasting media. The narrow bandgap width of single-layer resonator has prompted the exploration of multi-layer metamaterials as an effective alternative, which consist of…

Long-context modeling is essential for symbolic music generation, since motif repetition and developmental variation can span thousands of musical events, yet practical workflows frequently rely on resource-limited hardware. We introduce…

This paper proposes a novel framework for unsupervised audio source separation using a deep autoencoder. The characteristics of unknown source signals mixed in the mixed input is automatically by properly configured autoencoders implemented…

Binaural audio remains underexplored within the music information retrieval community. Motivated by the rising popularity of virtual and augmented reality experiences as well as potential applications to accessibility, we investigate how…

With the proliferation of video platforms on the internet, recording musical performances by mobile devices has become commonplace. However, these recordings often suffer from degradation such as noise and reverberation, which negatively…

Music foundation models possess impressive music generation capabilities. When people compose music, they may infuse their understanding of music into their work, by using notes and intervals to craft melodies, chords to build progressions,…

Generalized impedance boundary conditions are effective, approximate boundary conditions that describe scattering of waves in situations where the wave interaction with the material involves multiple scales. In particular, this includes…

Extracting individual elements from music mixtures is a valuable tool for music production and practice. While neural networks optimized to mask or transform mixture spectrograms into the individual source(s) have been the leading approach,…

Learning how to localize and separate individual object sounds in the audio channel of the video is a difficult task. Current state-of-the-art methods predict audio masks from artificially mixed spectrograms, known as Mix-and-Separate…

Music source separation (MSS) is the task of separating a music piece into individual sources, such as vocals and accompaniment. Recently, neural network based methods have been applied to address the MSS problem, and can be categorized…

We study lightweight, elastic metamaterials consisting of tensegrity-inspired prisms, which present wide, low-frequency band gaps. For their realization, we alternate tensegrity elements with solid discs in periodic arrangements that we…

Recently, symbolic music generation has become a focus of numerous deep learning research. Structure as an important part of music, contributes to improving the quality of music, and an increasing number of works start to study the…

Audio-visual multi-modal modeling has been demonstrated to be effective in many speech related tasks, such as speech recognition and speech enhancement. This paper introduces a new time-domain audio-visual architecture for target speaker…

Discovering and exploring the underlying structure of multi-instrumental music using learning-based approaches remains an open problem. We extend the recent MusicVAE model to represent multitrack polyphonic measures as vectors in a latent…

At present, neural network-based models, including transformers, struggle to generate memorable and readily comprehensible music from unified and repetitive musical material due to a lack of understanding of musical structure. Consequently,…

In recent years, self-supervised learning has amassed significant interest for training deep neural representations without labeled data. One such self-supervised learning approach is masked spectrogram modeling, where the objective is to…

This work develops a dynamic homogenization approach for metamaterials. It finds an approximate macroscopic homogenized equation with constant coefficients posed in space and time; however, the resulting homogenized equation is higher order…

To achieve a flexible recommendation and retrieval system, it is desirable to calculate music similarity by focusing on multiple partial elements of musical pieces and allowing the users to select the element they want to focus on. A…

Temporal fluctuations in the phase of waves transmitted through a dynamic, strongly scattering, mesoscopic sample are investigated using ultrasonic waves, and compared with theoretical predictions based on circular Gaussian statistics. The…

Style transfer is a technique for combining two images based on the activations and feature statistics in a deep learning neural network architecture. This paper studies the analogous task in the audio domain and takes a critical look at…