arXiv:2609.22913v1 Announce Type: cross Abstract: Talking-head and dyadic models now achieve real-time inference, yet fast motion generation alone does not produce an interactive conversation. A live...
The paper introduces ReACT‑TTS, a two‑stage framework that uses a one‑second sequence of listener facial reactions to plan the emotion and prosody of a conversational utterance before speech synthesis. Experiments on the MELD dataset show that temporally conditioned models outperform text‑only baselines in macro‑F1 and VAD concordance, while accuracy remains unchanged. A contextual‑appropriateness study with speech researchers indicates a strong preference for temporally conditioned responses, and the approach is integrated with a Grad‑TTS backbone for end‑to‑end speech generation.
arXiv:2606. 01031v1 Announce Type: cross Abstract: Audio-driven talking-head generation has advanced rapidly, yet existing evaluation protocols mainly rely on frame-wise metrics that assume strict temporal correspondence between generated and reference videos.
PRISM‑Bench is an audio‑centric diagnostic benchmark for text‑to‑audio‑video generation, built from 900 human‑verified samples. It evaluates audio along two axes—audio type (speech, music, sound) and sound‑source visibility (on‑screen vs. off‑screen)—across four perceptual dimensions (audio‑visual coherence, audio quality, audio expressiveness, and prompt following) using 35 fine‑grained criteria. The benchmark employs an enhanced MLLM‑as‑a‑Judge protocol that aligns strongly with human raters, revealing a performance gap between frontier and open‑source T2AV models and highlighting overfitting to perceptual fidelity while struggling with complex grounding and control tasks, especially for music and synchronized on‑screen audio.
arXiv:2605. 07061v2 Announce Type: replace-cross Abstract: Joint audio-video generation models are rapidly approaching professional production quality, raising a central question: do they understand audio-visual physics, or merely generate plausible sounds and frames that violate real-world consistency?
The paper introduces an automated pipeline that extracts conversational turns and backchannels from separate-channel recordings of spontaneous dyadic dialogue, combining voice activity detection, channel-energy filtering, temporal merging, automatic speech recognition, and context-based post‑processing. Evaluated on 99 ten‑minute Danish conversations, the system achieved F1 scores around 0.62 for both turns and backchannels, with median onset/offset errors of roughly 0.15–0.18 s. Performance was consistent across normal and asymmetric listening conditions, and a case study showed the pipeline’s outputs were less variable than human annotations, supporting its use as a reliable first‑pass annotation tool in semi‑automated workflows.
arXiv:2603. 16859v2 Announce Type: replace Abstract: Omni-modal large language models (OLMs) redefine human-machine interaction by natively integrating audio, vision, and text.
arXiv:2610.10208v1 Announce Type: cross Abstract: Automatic audio scene description turns a recording into a text account of a situation. One difficulty is deciding which elements of the audio should...
arXiv:2609.14666v1 Announce Type: cross Abstract: Turn-taking is a fundamental component of spoken interaction, and while humans naturally rely on both verbal and non-verbal signals, dialogue systems...
Motion-Omni is an end‑to‑end framework that jointly generates spoken dialogue and full‑body motion, producing speech, facial expressions, and hand, upper‑body, and lower‑body movements directly from the hidden states of a language model. The system requires joint training of the language model, speech generator, and motion generator to maintain audio‑motion alignment, and it is supervised using a scalable, model‑agnostic pipeline that pseudo‑labels 422,856 speech‑motion pairs. With a Qwen2.5‑7B‑Instruct backbone, Motion‑Omni‑Q7 achieves near‑cascade performance on motion metrics while being 5.4× faster, and it outperforms other non‑teacher cascades on beat correlation, diversity, and word error rate.
HUG‑VIS is a unified multimodal benchmark for human‑centered visual intelligence, comprising 8,400 half‑body videos of 30 professional actors performing 280 emotion‑action prompts in Mandarin. The dataset provides synchronized video, audio, text, and alpha mattes for four tasks—human emotion recognition, video generation, voice cloning, and video matting—allowing evaluation of both open‑ and closed‑source models under a zero‑shot protocol. Results reveal that linguistic cues dominate emotion recognition, visual affect is weakest, and that automatic metrics and human judgments diverge in generation and cloning tasks, while motion‑related boundary fidelity remains a key challenge for matting.
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...