HumanOmni-Speaker: Identifying Who said What and When

• URL: http://arxiv.org/abs/2603.21664v1
• Date: Mon, 23 Mar 2026 07:42:40 GMT
• Title: HumanOmni-Speaker: Identifying Who said What and When
• Abstract summary: Current models exploit visual biases in conventional benchmarks to bypass genuine cross-modal alignment.<n>We introduce Visual-Registered Speaker Diarization and Recognition (VR-SDR) and the HumanOmni-Speaker Benchmark.<n>Human Omni-Speaker demonstrates strong multimodal synergy, enabling end-to-end lip-reading and high-precision spatial localization without intrusive cropping.
• Score: 14.108013791864522
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• Beyond Monologue: Interactive Talking-Listening Avatar Generation with Conversational Audio Context-Aware Kernels [26.18760496276335]
  We develop an interactive virtual agent capable of simultaneously processing dual-stream audio inputs for both talking and listening.<n>Our approach successfully fuses strong temporal alignment with contextual semantics, setting a new state-of-the-art for generating highly natural and responsive interactive digital humans.
  arXiv  Detail & Related papers  (2026-04-11T22:34:21Z)
• A Novel Automatic Framework for Speaker Drift Detection in Synthesized Speech [34.33842514204989]
  Recent diffusion-based text-to-speech (TTS) models achieve high naturalness and expressiveness, yet often suffer from speaker drift.<n>We introduce the first automatic framework for detecting speaker drift by formulating it as a binary classification task over utterance-level speaker consistency.<n>Our method computes cosine similarity across overlapping segments of synthesized speech and prompts large language models with structured representations to assess drift.
  arXiv  Detail & Related papers  (2026-04-07T18:05:28Z)
• SNAP: Speaker Nulling for Artifact Projection in Speech Deepfake Detection [51.096014381455454]
  Self-supervised learning-based speech encoders struggle to generalize across unseen speakers.<n>Speaker entanglement causes detectors to exploit speaker-specific correlations rather than artifact-related cues.<n>We introduce SNAP, a speaker-nulling framework, to mitigate this reliance.
  arXiv  Detail & Related papers  (2026-03-21T07:05:30Z)
• Koopman Regularized Deep Speech Disentanglement for Speaker Verification [6.659299099827954]
  Deep Koopman Speech Disentanglement Autoencoder (DKSD-AE)<n>We propose a structured autoencoder that combines a novel multi-step Koopman operator learning module with instance normalization to disentangle speaker and content dynamics.<n>Our findings suggest that Koopman-based temporal modelling, when combined with instance normalization, provides an efficient and principled solution for speaker-focused representation learning.
  arXiv  Detail & Related papers  (2026-03-05T17:30:18Z)
• MIBURI: Towards Expressive Interactive Gesture Synthesis [62.45332399212876]
  Embodied Conversational Agents (ECAs) aim to emulate human face-to-face interaction through speech, gestures, and facial expressions.<n>Existing solutions for ECAs produce rigid, low-diversity motions that are unsuitable for human-like interaction.<n>We present MIBURI, the first online, causal framework for generating expressive full-body gestures and facial expressions synchronized with real-time spoken dialogue.
  arXiv  Detail & Related papers  (2026-03-03T18:59:51Z)
• A$^2$-LLM: An End-to-end Conversational Audio Avatar Large Language Model [39.89874984616492]
  A$2$-LLM is an end-to-end conversational audio avatar model that explains language, audio prosody, and 3D facial motion within a unified framework.<n>By deep semantic understanding, A$2$-LLM generates emotionally rich facial movements beyond simple lip-synchronization.
  arXiv  Detail & Related papers  (2026-02-04T02:19:46Z)
• Text2Lip: Progressive Lip-Synced Talking Face Generation from Text via Viseme-Guided Rendering [53.2204901422631]
  Text2Lip is a viseme-centric framework that constructs an interpretable phonetic-visual bridge.<n>We show that Text2Lip outperforms existing approaches in semantic fidelity, visual realism, and modality robustness.
  arXiv  Detail & Related papers  (2025-08-04T12:50:22Z)
• MultiVox: A Benchmark for Evaluating Voice Assistants for Multimodal Interactions [70.93364531054273]
  We introduce MultiVox, the first benchmark to evaluate the ability of voice assistants to integrate spoken and visual cues.<n>Specifically, MultiVox includes 1000 human-annotated and recorded speech dialogues that encompass diverse paralinguistic features.<n>Our evaluation on 10 state-of-the-art models reveals that, although humans excel at these tasks, current models consistently struggle to produce contextually grounded responses.
  arXiv  Detail & Related papers  (2025-07-14T23:20:42Z)
• Shushing! Let's Imagine an Authentic Speech from the Silent Video [15.426152742881365]
  Vision-guided speech generation aims to produce authentic speech from facial appearance or lip motions without relying on auditory signals.<n>Despite recent progress, existing methods struggle to achieve unified cross-modal alignment across semantics, timbre, and emotional prosody from visual cues.<n>We introduce ImaginTalk, a novel cross-modal diffusion framework that generates faithful speech using only visual input.
  arXiv  Detail & Related papers  (2025-03-19T06:28:17Z)
• OpenOmni: Advancing Open-Source Omnimodal Large Language Models with Progressive Multimodal Alignment and Real-Time Self-Aware Emotional Speech Synthesis [95.27191872116306]
  name is a two-stage training framework that integrates omnimodal alignment and speech generation.<n>It surpasses state-of-the-art models across omnimodal, vision-language, and speech-language benchmarks.<n>name achieves real-time speech generation with 1s latency at non-autoregressive mode.
  arXiv  Detail & Related papers  (2025-01-08T15:18:09Z)
• Generalizable Zero-Shot Speaker Adaptive Speech Synthesis with Disentangled Representations [12.388567657230116]
  We propose a generalizable zero-shot speaker adaptive text-to-speech and voice conversion model. GZS-TV introduces disentangled representation learning for speaker embedding extraction and timbre transformation. Our experiments demonstrate that GZS-TV reduces performance degradation on unseen speakers and outperforms all baseline models in multiple datasets.
  arXiv  Detail & Related papers  (2023-08-24T18:13:10Z)
• Learning to Listen: Modeling Non-Deterministic Dyadic Facial Motion [89.01668641930206]
  We present a framework for modeling interactional communication in dyadic conversations. We autoregressively output multiple possibilities of corresponding listener motion. Our method organically captures the multimodal and non-deterministic nature of nonverbal dyadic interactions.
  arXiv  Detail & Related papers  (2022-04-18T17:58:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.