MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation

• URL: http://arxiv.org/abs/2605.28035v1
• Date: Wed, 27 May 2026 06:38:54 GMT
• Title: MTAVG-Bench 2.0: Diagnosing Failure Modes of Cinematic Expressiveness in Multi-Talker Audio-Video Generation
• Abstract summary: We introduce MTAVG-Bench 2.0, a benchmark for diagnosing failure modes of cinematic expressiveness in multi-talker audio-video generation.<n>MTAVG-Bench 2.0 targets short-drama and scene-level generation, and establishes a high-level failure taxonomy spanning acting, narrative, atmosphere, and audio-visual language.<n> Experimental results show that commercial omni models such as Gemini substantially outperform other evaluators.
• Score: 56.428467142804756
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In recent years, Multi-Talker Audio-Video Generation (MTAVG) models have shown promising performance on fundamental metrics such as lip-sync and audio-visual alignment. However, these metrics remain insufficient for assessing cinematic expressiveness in scene-level generation. In multi-character scenes, generation models must go beyond audio-visual realism to convey coherent character performance and other higher-level cinematic qualities. To fill this gap, we introduce MTAVG-Bench 2.0, a benchmark for diagnosing failure modes of cinematic expressiveness in multi-talker audio-video generation. Unlike prior settings that mainly focus on the quality of basic multi-turn dialogue, MTAVG-Bench 2.0 targets short-drama and scene-level generation, and establishes a high-level failure taxonomy spanning acting, narrative, atmosphere, and audio-visual language. Based on this taxonomy, we construct more than 10,000 question-answering evaluation instances, together with subsets for short-drama-level assessment and temporal localization of failure modes, to systematically evaluate the ability of omni large language models to diagnose high-level audio-visual failures. Experimental results show that commercial omni models such as Gemini substantially outperform other evaluators, yet even the strongest models continue to struggle with complex failures in our benchmark. These results demonstrate that MTAVG-Bench 2.0 provides a systematic benchmark for failure diagnosis in cinematic multi-talker audio-video generation.

Related papers

• MRMAD: A Multi-Round Multi-Audio Benchmark for Evaluating Acoustic Degradation Perception in Large Audio-Language Models [11.14810883033264]
  We introduce MRMAD, a benchmark for evaluating audio degradation perception and understanding in large audio-language models (LALMs)<n> MRMAD spans speech, music, and sound, and frames evaluation as multi-turn dialogues across multiple audio inputs.<n>We find that current models often recognize coarse content while failing to diagnose, compare, or reason about degradations reliably.
  arXiv  Detail & Related papers  (2026-08-23T06:23:31Z)
• MSAVBench: Towards Comprehensive and Reliable Evaluation of Multi-Shot Audio-Video Generation [88.7702943548674]
  We introduce MSAVBench, the first comprehensive benchmark and adaptive hybrid evaluation framework for multi-shot audio-video generation.<n>Our benchmark spans four key dimensions, video, audio, shot, and reference, covering diverse task settings, varying shot counts of up to 15, and challenging non-realistic scenarios.<n> MSAVBench achieves high alignment with human judgments, reaching a Spearman rank correlation of 91.5%.
  arXiv  Detail & Related papers  (2026-05-19T17:59:33Z)
• Talker-T2AV: Joint Talking Audio-Video Generation with Autoregressive Diffusion Modeling [59.97930201616015]
  We propose Talker-T2AV, an autoregressive diffusion framework where high-level cross-modal modeling occurs in a shared backbone.<n>A shared autoregressive language model jointly reasons over audio and video in a unified patch-level token space.<n> Experiments on talking portrait benchmarks show Talker-T2AV outperforms dual-branch baselines in lip-sync accuracy, video quality, and audio quality.
  arXiv  Detail & Related papers  (2026-04-26T07:48:47Z)
• AVGen-Bench: A Task-Driven Benchmark for Multi-Granular Evaluation of Text-to-Audio-Video Generation [42.157453071865056]
  AVGen-Bench is a task-driven benchmark for T2AV generation featuring high-quality prompts across 11 real-world categories.<n>We propose a multi-granular evaluation framework that combines lightweight specialist models with Multimodal Large Language Models (MLLMs)<n>Our evaluation reveals a pronounced gap between strong audio-visual aesthetics and weak semantic reliability, including persistent failures in text rendering, speech coherence, physical reasoning, and a universal breakdown in musical pitch control.
  arXiv  Detail & Related papers  (2026-04-09T17:59:39Z)
• MSVBench: Towards Human-Level Evaluation of Multi-Shot Video Generation [48.84450712826316]
  MSVBench is the first comprehensive benchmark featuring hierarchical scripts and reference images tailored for Multi-Shot Video generation.<n>We propose a hybrid evaluation framework that synergizes the high-level semantic reasoning of Large Multimodal Models with the fine-grained perceptual rigor of domain-specific expert models.
  arXiv  Detail & Related papers  (2026-02-27T12:26:34Z)
• PhyAVBench: A Challenging Audio Physics-Sensitivity Benchmark for Physically Grounded Text-to-Audio-Video Generation [63.3417467957431]
  Text-to-audio-video (T2AV) generation underpins a wide range of applications demanding realistic audio-visual content.<n>We present PhyAVBench, a challenging audio physics-sensitivity benchmark designed to evaluate the audio physics grounding capabilities of existing T2AV models.<n>Unlike prior benchmarks that primarily focus on audio-video synchronization, PhyAVBench explicitly evaluates models' understanding of the physical mechanisms underlying sound generation.
  arXiv  Detail & Related papers  (2025-12-30T05:22:31Z)
• T2AV-Compass: Towards Unified Evaluation for Text-to-Audio-Video Generation [41.03487954415606]
  Text-to-Audio-Video (T2AV) generation aims to synthesize temporally coherent video and semantically synchronized audio from natural language.<n>We present T2AV-, a unified benchmark for comprehensive evaluation of T2AV systems.<n>Even the strongest models fall substantially short of human-level realism and cross-modal consistency.
  arXiv  Detail & Related papers  (2025-12-24T10:30:35Z)
• See, Hear, and Understand: Benchmarking Audiovisual Human Speech Understanding in Multimodal Large Language Models [24.851643680674474]
  AV-SpeakerBench is a curated benchmark of 3,212 multiple-choice questions focused on speaker-centric audiovisual reasoning in real-world videos.<n>It features: (1) a speaker-centered formulation that treats speakers-not scenes-as the core reasoning unit; (2) fusion-grounded question design embedding audiovisual dependencies into question semantics; and (3) expert-curated annotations ensuring temporal precision and cross-modal validity.
  arXiv  Detail & Related papers  (2025-12-01T21:57:26Z)
• AHELM: A Holistic Evaluation of Audio-Language Models [78.20477815156484]
  multimodal audio-language models (ALMs) take interleaved audio and text as input and output text.<n>AHELM is a benchmark that aggregates various datasets -- including 2 new synthetic audio-text datasets called PARADE and CoRe-Bench.<n>We also standardize the prompts, inference parameters, and evaluation metrics to ensure equitable comparisons across models.
  arXiv  Detail & Related papers  (2025-08-29T07:40:39Z)

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.