AnimeScore: New Framework for Evaluating Anime-Like Speech Characteristics
Researchers have proposed AnimeScore, a preference-based framework for automatically evaluating how 'anime-like' a synthesized voice sounds, accepted to INTERSPEECH 2026. The system collects pairwise human judgments rather than traditional Mean Opinion Scores, addressing the lack of a shared absolute scale for anime-likeness. The work provides a practical automated metric that could also serve as a reward signal for training generative speech models.
AnimeScore is a new dataset and evaluation framework designed to fill a gap in speech synthesis research: the absence of a standardized, objective metric for anime-style voice quality. The researchers collected 15,000 pairwise preference judgments from 187 evaluators, who also provided free-form descriptions of what made a voice sound anime-like. Acoustic analysis from the study found that perceived anime-likeness is driven by controlled resonance shaping, prosodic continuity, and deliberate articulation — not simply high pitch as might be assumed. The team benchmarked two approaches: handcrafted acoustic features reached a 69.3% AUC ceiling, while self-supervised learning (SSL)-based ranking models achieved up to 90.8% AUC, demonstrating substantially better automated alignment with human preferences. Beyond evaluation, the authors suggest the metric can function as a reward signal for preference-based optimization of generative speech models, with potential applications in anime dubbing, voice synthesis, and related creative industries. The paper has been accepted to INTERSPEECH 2026.
What's missing
The paper does not appear to address cross-cultural or cross-linguistic generalizability of the anime-likeness concept, nor whether the 187 evaluators were screened for familiarity with anime, which could affect the reliability and scope of the preference judgments. It is also unclear how the framework would handle regional or genre-specific variation within anime speech styles.
What different sources said
- arXiv cs.CLCenter
AnimeScore: A Preference-Based Dataset and Framework for Evaluating Anime-Like Speech Style
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.