4 articles tagged with #speech-separation. AI-curated summaries with sentiment analysis and key takeaways from 50+ sources.
Researchers propose MeCo, a MeanFlow-based generative corrector that improves multi-channel speech separation by refining discriminative model outputs in a single step. The method combines Data-Space Optimization with specialized loss functions to achieve state-of-the-art performance in both signal fidelity and human listening quality with minimal computational cost.
GenTSE introduces a two-stage generative language model for target speaker extraction that separates semantic and acoustic token generation, demonstrating improved speech quality and speaker consistency over previous LM-based approaches. The system employs novel training strategies including Frozen-LM Conditioning and Direct Preference Optimization to reduce exposure bias and align outputs with human perceptual preferences.
This research examines how the Scale-Invariant Signal-to-Distortion Ratio (SI-SDR) metric used to train and evaluate speech separation models performs poorly when training data contains noise, revealing fundamental limitations in the current benchmark approach. The authors propose reference enhancement techniques to mitigate this issue, though results indicate that processing introduces artifacts that limit overall quality improvements.
Researchers have developed TIGER, a new speech separation model that reduces parameters by 94.3% and computational costs by 95.3% while outperforming current state-of-the-art models. The team also introduced EchoSet, a new dataset with realistic acoustic environments that shows better generalization for speech separation models.
