BASENet: New Speech Enhancement Network Optimized for Human Hearing Achieves High Quality with Minimal Parameters
Researchers have proposed BASENet, a speech enhancement neural network that partitions audio frequencies according to the human auditory Bark scale, achieving strong performance metrics with only 0.83 million parameters. Unlike conventional models that apply uniform processing across all frequencies, BASENet allocates more computational capacity to perceptually important low frequencies and less to high frequencies. The architecture's efficiency and a real-time causal variant make it potentially suitable for deployment on resource-constrained devices such as hearing aids or mobile phones.
BASENet (Band-Adapted Speech Enhancement Network) is a new deep learning architecture for speech enhancement that mirrors the non-uniform spectral resolution of human hearing by dividing the audio spectrum into Bark-scale critical bands. Each band receives a scaled-capacity encoder proportional to its perceptual density, automatically dedicating more processing depth to low frequencies and less to high frequencies. A cross-band attention module captures harmonic relationships across bands using frequency-pooled representations at linear computational complexity. On the standard VoiceBank+DEMAND benchmark, BASENet achieves a PESQ score of 3.55 and approximately 96% STOI, representing the fewest parameters (0.83M) and lowest compute (7.3 GMACs) among all reported methods exceeding a PESQ of 3.50. A causal variant of the model reaches 3.44 PESQ, outperforming several non-causal baselines and suggesting viability for real-time streaming applications. The work was submitted to arXiv in June 2026 and has not yet undergone formal peer review.
What's missing
As a preprint, BASENet has not yet been peer-reviewed. The study evaluates performance solely on the VoiceBank+DEMAND benchmark; generalization to other noisy speech datasets, languages, or real-world acoustic conditions is not demonstrated. Latency and memory footprint on actual embedded hardware are not reported, leaving practical deployment claims partially unverified.
What different sources said
- arXiv cs.AICenter
BASENet: Band-Adapted Speech Enhancement Network with Cross-Band Attention
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.