arXiv:2505. 21954v2 Announce Type: replace-cross Abstract: We present UniTalk, a novel dataset emphasizing challenging scenarios to enhance model generalization for the task of active speaker detection (ASD).
arXiv:2609.26648v1 Announce Type: cross Abstract: Active speaker detection (ASD) requires reliable association between visible faces and acoustic speech, yet existing systems often degrade under chal...
arXiv:2609.10366v1 Announce Type: cross Abstract: While AVSR has achieved sub-1% word error rates on the standard LRS3 benchmark, its reliance on broadcast speech obscures whether this reflects true...
arXiv:2606. 02724v1 Announce Type: cross Abstract: Audio-visual speaker tracking aims to localize and track active speakers by leveraging auditory and visual cues, enabling fine-grained, human-centric scene understanding.
arXiv:2607. 08111v1 Announce Type: cross Abstract: Training target speaker extraction (TSE) models for real conversational mixtures remains challenging because large-scale training corpora and clean target speech for supervision are unavailable.
arXiv:2609.10394v1 Announce Type: cross Abstract: Current audio-visual speech recognition (AVSR) benchmarks, like LRS3, rely heavily on clean, scripted and rehearsed speech. They fail to reflect the...
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...
The paper introduces Cue2Narrate, a two‑stage pipeline that jointly predicts what visual events to narrate and when to insert the narration in long, untrimmed movie clips. It uses a dual‑head audio‑visual localizer to identify visual cue and narration windows, followed by a LoRA‑adapted vision‑language model that generates concise audio descriptions, trained with a Description Ranking Loss. The authors also present the LongLSMDC benchmark, comprising up to 8‑minute clips, and show that Cue2Narrate outperforms video‑only and audio‑only baselines by 5–12 points in average mAP and improves AD generation over fine‑tuned base VLMs.
SONIC‑O1 is a new benchmark designed to evaluate multimodal large language models on audio‑video understanding. It contains 60 hours of 231 clips across 13 real‑world conversational domains, with 4,958 human‑verified annotations and demographic metadata. The benchmark tests open‑ended summarization, multiple‑choice question answering, and temporally grounded reasoning, revealing performance gaps between model families and across demographic groups.
arXiv:2607. 02504v1 Announce Type: cross Abstract: Long-form TV dramas present a formidable challenge for comprehensive video understanding, where deciphering complex storyline often relies on \textbf{speaker recognition}, the task of accurately attributing each spoken utterance to its respective character.
The paper introduces SNAP, a speaker‑nulling framework designed to improve deepfake speech detection. By estimating a speaker subspace and orthogonally projecting out speaker‑dependent components, SNAP isolates synthesis artifacts in the residual features. This reduction of speaker entanglement enables detectors to focus on artifact‑related cues, achieving state‑of‑the‑art performance.
arXiv:2606. 19325v1 Announce Type: cross Abstract: Existing multi-speaker dialogue systems bind speakers to utterances through structured supervision: per-turn tags, multi-stream transcriptions, or learnable speaker embeddings.
arXiv:2609.14118v1 Announce Type: cross Abstract: Online understanding of who is talking to the camera wearer is a key capability for egocentric social interaction. However, existing talk-to-me (TTM)...