# HumanOmni-Speaker: Identifying Who said What and When

arXiv: https://arxiv.org/abs/2603.21664 · HTML: https://mlsanity.com/paper/2603.21664/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Builds on 31 of its 36 references that are in the map.
- First posted on arXiv 23 Mar 2026.

## Builds on (most cited first, 30 of 31)

- [Robust Speech Recognition via Large-Scale Weak Supervision](https://mlsanity.com/paper/2212.04356/) (2022)
- [Show and Tell: A Neural Image Caption Generator](https://mlsanity.com/paper/1411.4555/) (2014)
- [VoxCeleb2: Deep Speaker Recognition](https://mlsanity.com/paper/1806.05622/) (2018)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models](https://mlsanity.com/paper/2311.07919/) (2023)
- [LRS3-TED: a large-scale dataset for visual speech recognition](https://mlsanity.com/paper/1809.00496/) (2018)
- [Learning Audio-Visual Speech Representation by Masked Multimodal Cluster Prediction](https://mlsanity.com/paper/2201.02184/) (2022)
- [Lip Reading Sentences in the Wild](https://mlsanity.com/paper/1611.05358/) (2016)
- [VITA-1.5: Towards GPT-4o Level Real-Time Vision and Speech Interaction](https://mlsanity.com/paper/2501.01957/) (2025)
- [LLaMA-Omni: Seamless Speech Interaction with Large Language Models](https://mlsanity.com/paper/2409.06666/) (2024)
- [Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation](https://mlsanity.com/paper/1804.03619/) (2018)
- [StreamingBench: Assessing the Gap for MLLMs to Achieve Streaming Video Understanding](https://mlsanity.com/paper/2411.03628/) (2024)
- [A Review of Speaker Diarization: Recent Advances with Deep Learning](https://mlsanity.com/paper/2101.09624/) (2021)
- [FunAudioLLM: Voice Understanding and Generation Foundation Models for Natural Interaction Between Humans and LLMs](https://mlsanity.com/paper/2407.04051/) (2024)
- [Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels](https://mlsanity.com/paper/2303.14307/) (2023)
- [Mini-Omni2: Towards Open-source GPT-4o with Vision, Speech and Duplex Capabilities](https://mlsanity.com/paper/2410.11190/) (2024)
- [OmniBench: Towards The Future of Universal Omni-Language Models](https://mlsanity.com/paper/2409.15272/) (2024)
- [AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection](https://mlsanity.com/paper/1901.01342/) (2019)
- [V-STaR: Benchmarking Video-LLMs on Video Spatio-Temporal Reasoning](https://mlsanity.com/paper/2503.11495/) (2025)
- [Audio-Visual Speech Recognition With A Hybrid CTC/Attention Architecture](https://mlsanity.com/paper/1810.00108/) (2018)
- [Embodied AI Agents: Modeling the World](https://mlsanity.com/paper/2506.22355/) (2025)
- [HumanOmni: A Large Vision-Speech Language Model for Human-Centric Video Understanding](https://mlsanity.com/paper/2501.15111/) (2025)
- [OmniMMI: A Comprehensive Multi-modal Interaction Benchmark in Streaming Video Contexts](https://mlsanity.com/paper/2503.22952/) (2025)
- [VATLM: Visual-Audio-Text Pre-Training with Unified Masked Prediction for Speech Representation Learning](https://mlsanity.com/paper/2211.11275/) (2022)
- [Whisper-Flamingo: Integrating Visual Features into Whisper for Audio-Visual Speech Recognition and Translation](https://mlsanity.com/paper/2406.10082/) (2024)
- [Improving LLM Video Understanding with 16 Frames Per Second](https://mlsanity.com/paper/2503.13956/) (2025)
- [Cross-modal Supervision for Learning Active Speaker Detection in Video](https://mlsanity.com/paper/1603.08907/) (2016)
- [SpeakerLM: End-to-End Versatile Speaker Diarization and Recognition with Multimodal Large Language Models](https://mlsanity.com/paper/2508.06372/) (2025)
- [Scaling and Enhancing LLM-based AVSR: A Sparse Mixture of Projectors Approach](https://mlsanity.com/paper/2505.14336/) (2025)
- [Unveiling Visual Biases in Audio-Visual Localization Benchmarks](https://mlsanity.com/paper/2409.06709/) (2024)

## Built on by (most cited first, 3 of 3)

- [Human-Centric Intelligence in the Era of Foundation Models: A Survey](https://mlsanity.com/paper/2608.18184/) (2026)
- [OmniSmartHome: A Multimodal Reasoning Benchmark for Smart-Home Agents](https://mlsanity.com/paper/2609.32569/) (2026)
- [Omni-Modal LLMs Know More Than They Say](https://mlsanity.com/paper/2610.16135/) (2026)

## Abstract (arXiv)

While Omni-modal Large Language Models have made strides in joint sensory processing, they fundamentally struggle with a cornerstone of human interaction: deciphering complex, multi-person conversational dynamics to accurately answer ``Who said what and when.'' Current models suffer from an ``illusion of competence'' -- they exploit visual biases in conventional benchmarks to bypass genuine cross-modal alignment, while relying on sparse, low-frame-rate visual sampling that destroys crucial high-frequency dynamics like lip movements. To shatter this illusion, we introduce Visual-Registered Speaker Diarization and Recognition (VR-SDR) and the HumanOmni-Speaker Benchmark. By strictly eliminating visual shortcuts, this rigorous paradigm demands true end-to-end spatio-temporal identity binding using only natural language queries. To overcome the underlying architectural perception gap, we propose HumanOmni-Speaker, powered by a Visual Delta Encoder. By sampling raw video at 25 fps and explicitly compressing inter-frame motion residuals into just 6 tokens per frame, it captures fine-grained visemes and speaker trajectories without triggering a catastrophic token explosion. Ultimately, HumanOmni-Speaker demonstrates strong multimodal synergy, natively enabling end-to-end lip-reading and high-precision spatial localization without intrusive cropping, and achieving superior performance across a wide spectrum of speaker-centric tasks.