# Cocktail-Party Audio-Visual Speech Recognition

arXiv: https://arxiv.org/abs/2506.02178 · HTML: https://mlsanity.com/paper/2506.02178/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 17 of its 35 references that are in the map.
- First posted on arXiv 2 Jun 2025.

## Builds on (most cited first, 17 of 17)

- [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)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [End-to-end Audio-visual Speech Recognition with Conformers](https://mlsanity.com/paper/2102.06657/) (2021)
- [VisualVoice: Audio-Visual Speech Separation with Cross-Modal Consistency](https://mlsanity.com/paper/2101.03149/) (2021)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [Robust Self-Supervised Audio-Visual Speech Recognition](https://mlsanity.com/paper/2201.01763/) (2022)
- [A Light Weight Model for Active Speaker Detection](https://mlsanity.com/paper/2303.04439/) (2023)
- [MuAViC: A Multilingual Audio-Visual Corpus for Robust Speech Recognition and Robust Speech-to-Text Translation](https://mlsanity.com/paper/2303.00628/) (2023)
- [Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation](https://mlsanity.com/paper/2406.10082/) (2024)
- [Super-Human Performance in Online Low-latency Recognition of Conversational Speech](https://mlsanity.com/paper/2010.03449/) (2020)
- [From Text Segmentation to Smart Chaptering: A Novel Benchmark for Structuring Video Transcriptions](https://mlsanity.com/paper/2402.17633/) (2024)
- [Seeing Through the Conversation: Audio-Visual Speech Separation based on Diffusion Model](https://mlsanity.com/paper/2310.19581/) (2023)
- [Speaker-Targeted Audio-Visual Models for Speech Recognition in Cocktail-Party Environments](https://mlsanity.com/paper/1906.05962/) (2019)
- [MSA-ASR: Efficient Multilingual Speaker Attribution with frozen ASR Models](https://mlsanity.com/paper/2411.18152/) (2024)

## Built on by (most cited first, 7 of 7)

- [A Cocktail-Party Benchmark: Multi-Modal dataset and Comparative Evaluation Results](https://mlsanity.com/paper/2510.23276/) (2025)
- [The Lipreading Gap: Do VSR Models Perceive Visual Speech Like Human Lipreaders?](https://mlsanity.com/paper/2606.07435/) (2026)
- [AVSRBench: A Multi-Condition AVSR Benchmark](https://mlsanity.com/paper/2609.10366/) (2026)
- [Candor-LR: A Dyadic Conversational Dataset for Audio-Visual Speech Recognition](https://mlsanity.com/paper/2609.10394/) (2026)
- [Audio-Visual Turn-taking Prediction in Cocktail Party Scenarios](https://mlsanity.com/paper/2609.17056/) (2026)
- [Adapting Personalized Speech Enhancement for Low-Latency Audio-Visual Target-Speaker Extraction](https://mlsanity.com/paper/2609.30631/) (2026)
- [Learning Visual Speech Representations via Cross-Modal Distillation and Joint Face-Lip Modeling](https://mlsanity.com/paper/2610.19559/) (2026)

## Abstract (arXiv)

Audio-Visual Speech Recognition (AVSR) offers a robust solution for speech recognition in challenging environments, such as cocktail-party scenarios, where relying solely on audio proves insufficient. However, current AVSR models are often optimized for idealized scenarios with consistently active speakers, overlooking the complexities of real-world settings that include both speaking and silent facial segments. This study addresses this gap by introducing a novel audio-visual cocktail-party dataset designed to benchmark current AVSR systems and highlight the limitations of prior approaches in realistic noisy conditions. Additionally, we contribute a 1526-hour AVSR dataset comprising both talking-face and silent-face segments, enabling significant performance gains in cocktail-party environments. Our approach reduces WER by 67% relative to the state-of-the-art, reducing WER from 119% to 39.2% in extreme noise, without relying on explicit segmentation cues.