# VorTEX: Various overlap ratio for Target speech EXtraction

arXiv: https://arxiv.org/abs/2603.14803 · HTML: https://mlsanity.com/paper/2603.14803/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 28 references that are in the map.
- First posted on arXiv 16 Mar 2026.

## Builds on (most cited first, 23 of 23)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [RoFormer: Enhanced Transformer with Rotary Position Embedding](https://mlsanity.com/paper/2104.09864/) (2021)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Scaling Instruction-Finetuned Language Models](https://mlsanity.com/paper/2210.11416/) (2022)
- [LibriTTS: A Corpus Derived from LibriSpeech for Text-to-Speech](https://mlsanity.com/paper/1904.02882/) (2019)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Conv-TasNet: Surpassing Ideal Time-Frequency Magnitude Masking for Speech Separation](https://mlsanity.com/paper/1809.07454/) (2018)
- [Deep clustering: Discriminative embeddings for segmentation and separation](https://mlsanity.com/paper/1508.04306/) (2015)
- [LibriMix: An Open-Source Dataset for Generalizable Speech Separation](https://mlsanity.com/paper/2005.11262/) (2020)
- [Continuous speech separation: dataset and analysis](https://mlsanity.com/paper/2001.11482/) (2020)
- [Restructuring Vector Quantization with the Rotation Trick](https://mlsanity.com/paper/2410.06424/) (2024)
- [TextrolSpeech: A Text Style Control Speech Corpus With Codec Language Text-to-Speech Models](https://mlsanity.com/paper/2308.14430/) (2023)
- [Separate Anything You Describe](https://mlsanity.com/paper/2308.05037/) (2023)
- [Typing to Listen at the Cocktail Party: Text-Guided Target Speaker Extraction](https://mlsanity.com/paper/2310.07284/) (2023)
- [SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling](https://mlsanity.com/paper/2407.01857/) (2024)
- [SDR -- Medium Rare with Fast Computations](https://mlsanity.com/paper/2110.06440/) (2021)
- [USED: Universal Speaker Extraction and Diarization](https://mlsanity.com/paper/2309.10674/) (2023)
- [A Study of the Scale Invariant Signal to Distortion Ratio in Speech Separation with Noisy References](https://mlsanity.com/paper/2508.14623/) (2025)
- [Beyond Speaker Identity: Text Guided Target Speech Extraction](https://mlsanity.com/paper/2501.09169/) (2025)
- [Continuous Target Speech Extraction: Enhancing Personalized Diarization and Extraction on Complex Recordings](https://mlsanity.com/paper/2401.15993/) (2024)
- [Universal Speaker Embedding Free Target Speaker Extraction and Personal Voice Activity Detection](https://mlsanity.com/paper/2501.03612/) (2025)
- [DGMO: Training-Free Audio Source Separation through Diffusion-Guided Mask Optimization](https://mlsanity.com/paper/2506.02858/) (2025)
- [Inter-Speaker Relative Cues for Text-Guided Target Speech Extraction](https://mlsanity.com/paper/2506.01483/) (2025)

## Abstract (arXiv)

Target speech extraction (TSE) aims to recover a target speaker's voice from a mixture. While recent text-prompted approaches have shown promise, most approaches assume fully overlapped mixtures, limiting insight into behavior across realistic overlap ratios. We introduce VorTEX (Various overlap ratio for Target speech EXtraction), a text-prompted TSE architecture with a Decoupled Adaptive Multi-branch (DAM) Fusion block that separates primary extraction from auxiliary regularization pathways. To enable controlled analysis, we construct PORTE, a two-speaker dataset spanning overlap ratios from 0% to 100%. We further propose Suppression Ratio on Energy (SuRE), a diagnostic metric that detects suppression behavior not captured by conventional measures. Experiments show that existing models exhibit suppression or residual interference under overlap, whereas VorTEX achieves the highest separation fidelity across 20-100% overlap (e.g., 5.50 dB at 20% and 2.04 dB at 100%) while maintaining zero SuRE, indicating robust extraction without suppression-driven artifacts.