OpenBibleTTS: New Benchmark and Models for Text-to-Speech in 37 Low-Resource Languages
Researchers introduced OpenBibleTTS, a large-scale benchmark dataset and collection of text-to-speech models covering 37 underrepresented languages, addressing a significant gap in speech synthesis technology. The study compared multiple TTS architectures and found that no single system performs best across all languages, with different models excelling in different contexts. The work is significant because it provides open-source resources to advance speech synthesis for linguistic communities that have historically been underserved by AI technology.
OpenBibleTTS is a new benchmark for low-resource speech synthesis that spans 37 underrepresented languages, created to address the uneven distribution of text-to-speech advances across the world's languages. The researchers conducted a systematic comparison of various TTS architectures, including Gemini-TTS and monolingual EveryVoice models, evaluating them on both in-domain Biblical text and out-of-domain material. Results revealed that Gemini-TTS achieved the highest listener ratings on most evaluated languages, while monolingual EveryVoice models trained on OpenBibleTTS performed strongest for intelligibility and were preferred in several African languages. The study found that open from-scratch systems degrade significantly on out-of-domain text, highlighting a persistent gap between broad multilingual coverage and reliable synthesis quality in underserved communities. All processed datasets, alignments, and trained models have been open-sourced to support future research in low-resource TTS.
What's missing
The study does not specify which 37 languages are included in the benchmark, nor does it detail the size of the dataset or the specific phonetic challenges addressed. Additionally, the paper does not discuss potential limitations in using Biblical text as the primary domain for training, which may not reflect the linguistic patterns of everyday speech in these communities.
What different sources said
- arXiv cs.AICenter
GlobeAudio: A Multilingual Multicultural Benchmark for Naturalistic Evaluation of Large Audio-Language Models
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.