GenTSE: New Generative Language Model Approach Improves Target Speaker Extraction
Researchers have developed GenTSE, a two-stage generative language model that separates semantic and acoustic processing to improve target speaker extraction from mixed audio. The method uses continuous embeddings and training strategies designed to reduce the gap between training and inference. The approach demonstrates improvements in speech quality, intelligibility, and speaker consistency on standard benchmarks.
GenTSE is a decoder-only generative language model designed for target speaker extraction (TSE), the task of isolating one speaker's voice from mixed audio. The system operates in two stages: the first predicts coarse semantic tokens representing the speaker's content, while the second generates fine acoustic tokens for high-fidelity speech reconstruction. Rather than using discretized prompts, both stages leverage continuous SSL or codec embeddings to provide richer contextual information. To address exposure bias—the mismatch between training with ground-truth inputs and inference with predicted inputs—the researchers employ a Frozen-LM Conditioning strategy that trains on predicted tokens from earlier model checkpoints. They additionally apply Direct Preference Optimization (DPO) to align outputs with human perceptual preferences. Experiments on the Libri2Mix dataset show GenTSE outperforms previous language model-based systems across multiple metrics.
What's missing
The paper does not discuss computational requirements, inference latency, or scalability to real-world applications with longer audio sequences or larger speaker pools. Generalization beyond Libri2Mix to other datasets or languages is not addressed. The specific architecture details of the SSL/codec embeddings and their dimensionality are not provided in the abstract.
What different sources said
- arXiv cs.AICenter
GenTSE: Enhancing Target Speaker Extraction via a Coarse-to-Fine Generative Language Model
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.