MMAU: A Massive Multi-Task Audio Understanding and Reasoning Benchmark

By S. Sakshi, Utkarsh Tyagi, Sonal Kumar, Ashish Seth, S Ramaneswaran, Oriol Nieto, Ramani Duraiswami, Sreyan Ghosh, Dinesh Manocha. International Conference on Learning Representations, 2024

308 citations recorded by the source corpus.

The ability to comprehend audio--which includes speech, non-speech sounds, and music--is crucial for AI agents to interact effectively with the world. We present MMAU, a novel benchmark designed to evaluate multimodal audio understanding models on tasks requiring expert-level knowledge and complex reasoning. MMAU comprises 10k carefully curated audio clips paired with human-annotated natural language questions and answers spanning speech, environmental sounds, and music. It includes information extraction and reasoning questions, requiring models to demonstrate 27 distinct skills across unique and challenging tasks. Unlike existing benchmarks, MMAU emphasizes advanced perception and reasoning with domain-specific knowledge, challenging models to tackle tasks akin to those faced by experts. We assess 18 open-source and proprietary (Large) Audio-Language Models, demonstrating the significant challenges posed by MMAU. Notably, even the most advanced Gemini Pro v1.5 achieves only 52.97% accuracy, and the state-of-the-art open-source Qwen2-Audio achieves only 52.50%, highlighting considerable room for improvement. We believe MMAU will drive the audio and multimodal research community to develop more advanced audio understanding models capable of solving complex audio tasks.

Subfields: Artificial Intelligence, Signal Processing

View Paper: https://www.semanticscholar.org/paper/c0605c96870e59b4caf2247a98c6bd3aad25882f

Citations in the corpus