LiveBand: Real-Time Music Accompaniment Generation System Achieves High-Fidelity Audio Synthesis
Researchers have introduced LiveBand, a system that generates high-fidelity music accompaniments to live audio in real time without accessing future audio frames. The model uses a causal transformer trained in the latent space of a pre-trained audio autoencoder, with adversarial supervision and causal masking to eliminate exposure bias. It outperforms prior work on audio quality, beat alignment, and mix adherence while running on consumer hardware.
LiveBand is a real-time music accompaniment generation system that operates under strict causal constraints, meaning it never looks ahead at future audio input when producing its output. The system trains a causal transformer generator within the continuous latent space of a pre-trained causal audio autoencoder, using adversarial sequence-level supervision from a discriminator. At each timestep, the generator receives only the causally available mix context and Gaussian noise, predicting accompaniment latents without access to future frames or ground-truth targets. A key design choice is that training and inference computations are matched — training uses a single parallel forward pass with causal masking, while inference proceeds autoregressively with a rolling attention state — eliminating teacher forcing and the associated exposure bias problem. On a multi-instrument music accompaniment benchmark, LiveBand surpasses prior approaches on objective measures of audio quality, beat alignment, and mix adherence. Notably, the system achieves real-time streaming generation on consumer-grade hardware, making it potentially practical for live musical performance applications.
What's missing
The paper does not appear to include subjective or perceptual listening evaluations (e.g., MOS scores or human preference studies), which are standard complements to objective metrics in audio generation research. It is also unclear whether the system has been tested in actual live performance settings with human musicians, or only on benchmark datasets. Generalization across diverse musical genres and instrumentations beyond the benchmark remains an open question.
What different sources said
- arXiv cs.AICenter
LiveBand: Live Accompaniment Generation in the Audio Domain
Related
Gut Bacteria Enzyme Found to Break Down Heat-Processed Food Compounds, Producing Novel Biogenic Amines
Researchers have discovered that an enzyme in common gut bacteria can degrade N-epsilon-carboxymethyllysine (CML), a compound formed during thermal food processing, producing previously unknown biogenic amines. The enzyme, ornithine decarboxylase SpeC from enterobacteria, acts on CML and related modified lysine derivatives through a low-level 'underground' catalytic activity. This finding suggests a previously unrecognized communication axis between thermally processed dietary compounds and gut microbial physiology, with potential implications for host health.
Full-Length Gene Sequencing Reveals Two Distinct Bacterial Communities in Black-Legged Ticks Expanding Into Canada
Researchers used Oxford Nanopore full-length 16S rRNA gene sequencing to characterize the microbiome of Ixodes scapularis black-legged ticks collected in Nova Scotia, Canada, distinguishing between tick-adapted bacteria and environmentally acquired bacteria. The study comes as I. scapularis — the primary vector of Lyme disease — is rapidly expanding northward into Canada due to climate change. The findings suggest that environmentally derived bacteria in tick microbiomes are not mere contamination, which has implications for how tick microbiome data is collected and interpreted across surveillance studies.
Study Identifies Metabolic Link Between Cell Envelope Stress and Biofilm Formation in Bacteria
Researchers have discovered that the metabolite acetyl-CoA directly inhibits enzymes that degrade the bacterial signaling molecule c-di-GMP, connecting cell envelope biosynthesis stress to biofilm formation in Pseudomonas aeruginosa. The study found that sub-inhibitory concentrations of antibiotics targeting early peptidoglycan biosynthesis — but not other antibiotic classes — elevate c-di-GMP levels by reducing phosphodiesterase activity, with acetyl-CoA competing for the enzyme active site. Because the relevant enzyme domain is broadly conserved across bacterial species, this checkpoint mechanism may be widespread and could have implications for understanding antibiotic-induced biofilm responses.