FormalASR: New AI Models Convert Spoken Chinese Directly to Formal Written Text
Researchers have developed FormalASR, two compact AI models that convert spoken Chinese directly into formal written text without requiring post-processing. The models address a limitation of traditional speech recognition systems, which preserve informal speech patterns unsuitable for writing applications. This approach reduces computational overhead and enables on-device deployment for practical applications.
FormalASR presents an end-to-end solution to a common problem in automatic speech recognition: traditional ASR systems preserve disfluencies, filler words, and informal spoken structures that require additional processing to convert into formal written text. The researchers developed two model sizes (0.6B and 1.7B parameters) by fine-tuning Qwen3-ASR on newly constructed datasets—WenetSpeech-Formal and Speechio-Formal—which were created through LLM-based rewriting and quality filtering. Experiments demonstrate that FormalASR achieves up to 37.4% relative character error rate reduction compared to verbatim baselines while improving ROUGE-L and BERTScore metrics. The key advantage is eliminating the need for a separate large language model during deployment, making the solution lightweight and suitable for on-device use, thereby reducing latency and memory requirements.
What's missing
The study does not discuss potential limitations such as performance on accented speech, domain-specific vocabulary, or how the models handle code-switching between Chinese and other languages. Additionally, no information is provided about inference speed comparisons or actual on-device deployment results.
What different sources said
- arXiv cs.AICenter
FormalASR: End-to-End Spoken Chinese to Formal Text
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.