Related papers: A Transformer Based Pitch Sequence Autoencoder wit…

Amid the rising intersection of generative AI and human artistic processes, this study probes the critical yet less-explored terrain of alignment in human-centric automatic song composition. We propose a novel task of Colloquial…

We argue that training autoencoders to reconstruct inputs from noised versions of their encodings, when combined with perceptual losses, yields encodings that are structured according to a perceptual hierarchy. We demonstrate the emergence…

Human preference alignment can greatly enhance Multimodal Large Language Models (MLLMs), but collecting high-quality preference data is costly. A promising solution is the self-evolution strategy, where models are iteratively trained on…

Music mixing involves combining individual tracks into a cohesive mixture, a task characterized by subjectivity where multiple valid solutions exist for the same input. Existing automatic mixing systems treat this task as a deterministic…

Automatic music transcription (AMT) aims to infer a latent symbolic representation of a piece of music (piano-roll), given a corresponding observed audio recording. Transcribing polyphonic music (when multiple notes are played…

Text-to-music generation has advanced rapidly, with modern autoregressive and diffusion-based models producing convincing music from natural-language prompts. However, much of this progress relies on large-scale training data and external…

Automatic Music Transcription (AMT) -- the task of converting music audio into note representations -- has seen rapid progress, driven largely by deep learning systems. Due to the limited availability of richly annotated music datasets,…

The advent of generative AI models has revolutionized digital content creation, yet it introduces challenges in maintaining copyright integrity due to generative parroting, where models mimic their training data too closely. Our research…

In this work we describe and evaluate methods to learn musical embeddings. Each embedding is a vector that represents four contiguous beats of music and is derived from a symbolic representation. We consider autoencoding-based methods…

Building upon Diff-A-Riff, a latent diffusion model for musical instrument accompaniment generation, we present a series of improvements targeting quality, diversity, inference speed, and text-driven control. First, we upgrade the…

Music performance synthesis aims to synthesize a musical score into a natural performance. In this paper, we borrow recent advances in text-to-speech synthesis and present the Deep Performer -- a novel system for score-to-audio music…

We present a framework for real-time human-AI musical co-performance, in which a latent diffusion model generates instrumental accompaniment in response to a live stream of context audio. The system combines a MAX/MSP front-end-handling…

Deep learning models define the state-of-the-art in Automatic Drum Transcription (ADT), yet their performance is contingent upon large-scale, paired audio-MIDI datasets, which are scarce. Existing workarounds that use synthetic data often…

State of the art music recommender systems mainly rely on either matrix factorization-based collaborative filtering approaches or deep learning architectures. Deep learning models usually use metadata for content-based filtering or predict…

It is increasingly considered that human speech perception and production both rely on articulatory representations. In this paper, we investigate whether this type of representation could improve the performances of a deep generative model…

Modelling musical structure is vital yet challenging for artificial intelligence systems that generate symbolic music compositions. This literature review dissects the evolution of techniques for incorporating coherent structure, from…

We propose a deep attention-based alignment network, which aims to automatically predict lyrics and melody with given incomplete lyrics as input in a way similar to the music creation of humans. Most importantly, a deep neural…

Research on automatic music generation has seen great progress due to the development of deep neural networks. However, the generation of multi-instrument music of arbitrary genres still remains a challenge. Existing research either works…

With the goal of building a system capable of controllable symbolic music loop generation and editing, this paper explores a generalisation of Masked Language Modelling we call Superposed Language Modelling. Rather than input tokens being…

Making a slight mistake during live music performance can easily be spotted by an astute listener, even if the performance is an improvisation or an unfamiliar piece. An example might be a highly dissonant chord played by mistake in a…