# ELEGANCE: Efficient LLM Guidance for Audio-Visual Target Speech Extraction

arXiv: https://arxiv.org/abs/2511.06288 · HTML: https://mlsanity.com/paper/2511.06288/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 52 references that are in the map.
- First posted on arXiv 9 Nov 2025.

## Builds on (most cited first, 30 of 42)

- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Representation Alignment for Generation: Training Diffusion Transformers Is Easier Than You Think](https://mlsanity.com/paper/2410.06940/) (2024)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [SDR - half-baked or well done?](https://mlsanity.com/paper/1811.02508/) (2018)
- [Deep Audio-Visual Speech Recognition](https://mlsanity.com/paper/1809.02108/) (2018)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Dual-path RNN: efficient long sequence modeling for time-domain single-channel speech separation](https://mlsanity.com/paper/1910.06379/) (2019)
- [LMFusion: Adapting Pretrained Language Models for Multimodal Generation](https://mlsanity.com/paper/2412.15188/) (2024)
- [An Investigation of Incorporating Mamba for Speech Enhancement](https://mlsanity.com/paper/2405.06573/) (2024)
- [Whispering LLaMA: A Cross-Modal Generative Error Correction Framework for Speech Recognition](https://mlsanity.com/paper/2310.06434/) (2023)
- [Watch or Listen: Robust Audio-Visual Speech Recognition with Visual Corruption Modeling and Reliability Scoring](https://mlsanity.com/paper/2303.08536/) (2023)
- [Large Language Models are Strong Audio-Visual Speech Recognition Learners](https://mlsanity.com/paper/2409.12319/) (2024)
- [SpeechBERTScore: Reference-Aware Automatic Evaluation of Speech Generation Leveraging NLP Evaluation Metrics](https://mlsanity.com/paper/2401.16812/) (2024)
- [Neural Target Speech Extraction: An Overview](https://mlsanity.com/paper/2301.13341/) (2023)
- [Speech Slytherin: Examining the Performance and Efficiency of Mamba for Speech Separation, Recognition, and Synthesis](https://mlsanity.com/paper/2407.09732/) (2024)
- [Improving Robustness of LLM-based Speech Synthesis by Learning Monotonic Alignment](https://mlsanity.com/paper/2406.17957/) (2024)
- [Muse: Multi-modal target speaker extraction with visual cues](https://mlsanity.com/paper/2010.07775/) (2020)
- [Look&Listen: Multi-Modal Correlation Learning for Active Speaker Detection and Speech Enhancement](https://mlsanity.com/paper/2203.02216/) (2022)
- [Large Language Model Can Transcribe Speech in Multi-Talker Scenarios with Versatile Instructions](https://mlsanity.com/paper/2409.08596/) (2024)
- [AKVSR: Audio Knowledge Empowered Visual Speech Recognition by Compressing Audio Knowledge of a Pretrained Model](https://mlsanity.com/paper/2308.07593/) (2023)
- [Selective Listening by Synchronizing Speech with Lips](https://mlsanity.com/paper/2106.07150/) (2021)
- [AV-SepFormer: Cross-Attention SepFormer for Audio-Visual Target Speaker Extraction](https://mlsanity.com/paper/2306.14170/) (2023)
- [USEV: Universal Speaker Extraction with Visual Cue](https://mlsanity.com/paper/2109.14831/) (2021)
- [Separate in the Speech Chain: Cross-Modal Conditional Audio-Visual Target Speech Extraction](https://mlsanity.com/paper/2404.12725/) (2024)
- [Listen, Chat, and Remix: Text-Guided Soundscape Remixing for Enhanced Auditory Experience](https://mlsanity.com/paper/2402.03710/) (2024)
- [ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding Inpainting](https://mlsanity.com/paper/2211.00109/) (2022)

## Abstract (arXiv)

Audio-visual target speaker extraction (AV-TSE) models primarily rely on visual cues from the target speaker. However, humans also leverage linguistic knowledge, such as syntactic constraints, next word prediction, and prior knowledge of conversation, to extract target speech. Inspired by this observation, we propose ELEGANCE, a novel framework that incorporates linguistic knowledge from large language models (LLMs) into AV-TSE models through three distinct guidance strategies: output linguistic constraints, intermediate linguistic prediction, and input linguistic prior. Comprehensive experiments with RoBERTa, Qwen3-0.6B, and Qwen3-4B on two AV-TSE backbones demonstrate the effectiveness of our approach. Significant improvements are observed in challenging scenarios, including visual cue impaired, unseen languages, target speaker switches, increased interfering speakers, and out-of-domain test set. Demo page: https://alexwxwu.github.io/ELEGANCE/.