相关论文: Exploring Transformer-Based Music Overpainting for…

Transformer architectures have achieved remarkable success across language, vision, and multimodal tasks, and there is growing demand for them to address in-context compositional learning tasks. In these tasks, models solve the target…

This paper investigates foundation models tailored for music informatics, a domain currently challenged by the scarcity of labeled data and generalization issues. To this end, we conduct an in-depth comparative study among various…

Audio inpainting aims to reconstruct missing segments in corrupted recordings. Most of existing methods produce plausible reconstructions when the gap lengths are short, but struggle to reconstruct gaps larger than about 100 ms. This paper…

The performance of approaches to Music Instrument Classification, a popular task in Music Information Retrieval, is often impacted and limited by the lack of availability of annotated data for training. We propose to address this issue with…

We present a supervised neural network model for polyphonic piano music transcription. The architecture of the proposed model is analogous to speech recognition systems and comprises an acoustic model and a music language model. The…

Automatic Music Transcription (AMT) has advanced significantly for the piano, but transcription for the guitar remains limited due to several key challenges. Existing systems fail to detect and annotate expressive techniques (e.g., slides,…

This study focuses on the perception of music performances when contextual factors, such as room acoustics and instrument, change. We propose to distinguish the concept of "performance" from the one of "interpretation", which expresses the…

Musical rhythms performed by humans typically show temporal fluctuations. While they have been characterized in simple rhythmic tasks, it is an open question what is the nature of temporal fluctuations, when several musicians perform music…

Competitive music transcription models require large amounts of paired audio-score data, which is scarce due to collection costs, alignment difficulty, and copyright restrictions. Meanwhile, vast quantities of unpaired audio recordings and…

Learning music representations that are general-purpose offers the flexibility to finetune several downstream tasks using smaller datasets. The wav2vec 2.0 speech representation model showed promising results in many downstream speech…

Music Performers have their own idiosyncratic way of interpreting a musical piece. A group of skilled performers playing the same piece of music would likely to inject their unique artistic styles in their performances. The variations of…

We introduce the Latent Fourier Transform (LatentFT), a framework that provides novel frequency-domain controls for generative music models. LatentFT combines a diffusion autoencoder with a latent-space Fourier transform to separate musical…

Recent advances in generative AI music have resulted in new technologies that are being framed as co-creative tools for musicians with early work demonstrating their potential to add to music practice. While the field has seen many valuable…

Due to advances in deep learning, the performance of automatic beat and downbeat tracking in musical audio signals has seen great improvement in recent years. In training such deep learning based models, data augmentation has been found an…

Attention-based Transformer models have been increasingly employed for automatic music generation. To condition the generation process of such a model with a user-specified sequence, a popular approach is to take that conditioning sequence…

Self-supervised representation learning has shown remarkable success in a number of domains. A common practice is to perform data augmentation via hand-crafted transformations intended to leave the semantics of the data invariant. We seek…

Fine-tuning large-scale music generation models, such as MusicGen and Mustango, is a computationally expensive process, often requiring updates to billions of parameters and, therefore, significant hardware resources. Parameter-Efficient…

Current state-of-the-art AI based classical music creation algorithms such as Music Transformer are trained by employing single sequence of notes with time-shifts. The major drawback of absolute time interval expression is the difficulty of…

With the rapid advancement of generative audio models, distinguishing between human-composed and generated music is becoming increasingly challenging. As a response, models for detecting fake music have been proposed. In this work, we…

Automated piano performance evaluation traditionally relies on symbolic (MIDI) representations, which capture note-level information but miss the acoustic nuances that characterize expressive playing. I propose using pre-trained audio…