相关论文: iKlax: a New Musical Audio Format for Active Liste…
Music has a unique and complex structure which is challenging for both expert humans and existing AI systems to understand, and presents unique challenges relative to other forms of audio. We present LLark, an instruction-tuned multimodal…
This paper introduces an extendable modular system that compiles a range of music feature extraction models to aid music information retrieval research. The features include musical elements like key, downbeats, and genre, as well as audio…
In this review, it is explained and compared different software and formalisms used in music interaction: sequencers, computer-assisted improvisation, meta- instruments, score-following, asynchronous dataflow languages, synchronous dataflow…
New machine learning algorithms are being developed to solve problems in different areas, including music. Intuitive, accessible, and understandable demonstrations of the newly built models could help attract the attention of people from…
This paper presents a device implementing a closed tactile loop for musical interaction, based on a small freely held magnet which serves as the medium for both input and output. The component parts as well as an example of its programmable…
The aim of this study is to introduce an application that enables information sharing and communication between visually-impaired individuals and able-bodied. For the purposes of the study, web-based audio library automation was designed…
We introduce Jukebox, a model that generates music with singing in the raw audio domain. We tackle the long context of raw audio using a multi-scale VQ-VAE to compress it to discrete codes, and modeling those using autoregressive…
Recent advancements in web-based audio systems have enabled sufficiently accurate timing control and real-time sound processing capabilities. Numerous specialized music tools, as well as digital audio workstations, are now accessible from…
Online streaming services have become the most popular way of listening to music. The majority of these services are endowed with recommendation mechanisms that help users to discover songs and artists that may interest them from the vast…
Multimodal models are critical for music understanding tasks, as they capture the complex interplay between audio and lyrics. However, as these models become more prevalent, the need for explainability grows-understanding how these systems…
We present TALKPLAY, a novel multimodal music recommendation system that reformulates recommendation as a token generation problem using large language models (LLMs). By leveraging the instruction-following and natural language generation…
Computing practice today depends on visual output to drive almost all user interaction. Other senses, such as audition, may be totally neglected, or used tangentially, or used in highly restricted specialized ways. We have excellent audio…
Using open-source and creative coding frameworks, a teamof artist-engineers from Portland Community College work-ing with artists who experience Intellectual/Developmentaldisabilities prototyped an ensemble of adapted instrumentsand…
In this paper, we propose a new compositional tool that will generate a musical outline of speech recorded/provided by the user for use as a musical building block in their compositions. The tool allows any user to use their own speech to…
This paper introduces a project of advanced system of music retrieval from the Internet. The system uses combination of text search (by author, title and other information about the music file included in id3 tag description or similar for…
Traditional recommendation systems represent user preferences in dense representations obtained through black-box encoder models. While these models often provide strong recommendation performance, they lack interpretability for users,…
One of the significant issues in the music supply chain today is the lack of consistent, complete and authoritative information or metadata regarding the creation of a given musical work. In many cases multiple entities in the music supply…
Recent music generation methods based on transformers have a context window of up to a minute. The music generated by these methods is largely unstructured beyond the context window. With a longer context window, learning long-scale…
This paper describes an object-oriented approach to music composition and sound design. The approach unifies the processes of music making and instrument building by using similar logic, objects, and procedures. The composition modules use…
Recent text-to-audio generation techniques have the potential to allow novice users to freely generate music audio. Even if they do not have musical knowledge, such as about chord progressions and instruments, users can try various text…