AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs

• URL: http://arxiv.org/abs/2510.07293v1
• Date: Wed, 08 Oct 2025 17:50:16 GMT
• Title: AudioMarathon: A Comprehensive Benchmark for Long-Context Audio Understanding and Efficiency in Audio LLMs
• Authors: Peize He, Zichen Wen, Yubo Wang, Yuxuan Wang, Xiaoqian Liu, Jiajie Huang, Zehui Lei, Zhuangcheng Gu, Xiangqi Jin, Jiabing Yang, Kai Li, Zhifei Liu, Weijia Li, Cunxiang Wang, Conghui He, Linfeng Zhang,
• Abstract summary: AudioMarathon is a benchmark designed to evaluate both understanding and inference efficiency on long-form audio.<n>We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows.<n>The results show large gaps across current LALMs and highlight the need for better temporal reasoning.
• Score: 53.248502396225724
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Processing long-form audio is a major challenge for Large Audio Language models (LALMs). These models struggle with the quadratic cost of attention ($O(N^2)$) and with modeling long-range temporal dependencies. Existing audio benchmarks are built mostly from short clips and do not evaluate models in realistic long context settings. To address this gap, we introduce AudioMarathon, a benchmark designed to evaluate both understanding and inference efficiency on long-form audio. AudioMarathon provides a diverse set of tasks built upon three pillars: long-context audio inputs with durations ranging from 90.0 to 300.0 seconds, which correspond to encoded sequences of 2,250 to 7,500 audio tokens, respectively, full domain coverage across speech, sound, and music, and complex reasoning that requires multi-hop inference. We evaluate state-of-the-art LALMs and observe clear performance drops as audio length grows. We also study acceleration techniques and analyze the trade-offs of token pruning and KV cache eviction. The results show large gaps across current LALMs and highlight the need for better temporal reasoning and memory-efficient architectures. We believe AudioMarathon will drive the audio and multimodal research community to develop more advanced audio understanding models capable of solving complex audio tasks.

Related papers

• Echoes Over Time: Unlocking Length Generalization in Video-to-Audio Generation Models [42.75068463173552]
  We tackle the scaling challenge in multimodal-to-audio generation, examining whether models trained on short instances can generalize to longer ones during testing.<n>Our approach integrates a hierarchical method and non-causal Mamba to support long-form audio generation.<n>We show in our experiments that our proposed method could achieve remarkable results on long-video to audio benchmarks, beating prior works in video-to-audio tasks.
  arXiv  Detail & Related papers  (2026-02-24T15:01:39Z)
• Towards Audio Token Compression in Large Audio Language Models [26.379508239446935]
  Large Audio Language Models (LALMs) demonstrate impressive performance across diverse tasks.<n>However, their scalability is limited by the quadratic complexity of attention and the high token rates of audio signals.<n>This paper explores techniques to reduce the number of audio tokens generated by the LALM's audio encoder but before they are consumed by the LLM decoder.
  arXiv  Detail & Related papers  (2025-11-26T02:00:38Z)
• BLAB: Brutally Long Audio Bench [90.20616799311578]
  Brutally Long Audio Bench (BLAB) is a long-form audio benchmark that evaluates audio LMs on localization, duration estimation, emotion, and counting tasks.<n>BLAB consists of 833+ hours of diverse, full-length audio clips, each paired with human-annotated, text-based natural language questions and answers.<n>We evaluate six open-source and proprietary audio LMs on BLAB and find that all of them, including advanced models such as Gemini 2.0 Pro and GPT-4o, struggle with the tasks.
  arXiv  Detail & Related papers  (2025-05-05T22:28:53Z)
• Audio Flamingo 2: An Audio-Language Model with Long-Audio Understanding and Expert Reasoning Abilities [72.91296768332163]
  We introduce Audio Flamingo 2 (AF2), an Audio-Language Model, and LongAudio, a dataset for training ALMs on long audio captioning and question-answering tasks.<n>AF2 achieves state-of-the-art performance with only a 3B parameter small language model, surpassing large open-source and proprietary models across over 20 benchmarks.<n>For the first time, we extend audio understanding to long audio segments (30 secs to 5 mins) and propose LongAudio, a large and novel dataset for training ALMs on long audio captioning and question-answering tasks.
  arXiv  Detail & Related papers  (2025-03-06T00:10:26Z)
• Beyond Single-Audio: Advancing Multi-Audio Processing in Audio Large Language Models [56.776580717999806]
  Real-world applications often involve processing multiple audio streams simultaneously. We propose the first multi-audio evaluation benchmark that consists of 20 datasets from 11 multi-audio tasks. We propose a novel multi-audio-LLM (MALLM) to capture audio context among multiple similar audios.
  arXiv  Detail & Related papers  (2024-09-27T12:06:53Z)
• Enhancing Temporal Understanding in Audio Question Answering for Large Audio Language Models [0.9285295512807729]
  The Audio Question Answering (AQA) task includes audio event classification, audio captioning, and open-ended reasoning.<n>LALMs excel in general audio understanding, but are limited in temporal reasoning.<n>This paper addresses these challenges and limitations in audio temporal reasoning.
  arXiv  Detail & Related papers  (2024-09-10T05:26:53Z)
• Mirasol3B: A Multimodal Autoregressive model for time-aligned and contextual modalities [67.89368528234394]
  One of the main challenges of multimodal learning is the need to combine heterogeneous modalities. Video and audio are obtained at much higher rates than text and are roughly aligned in time. Our approach achieves the state-of-the-art on well established multimodal benchmarks, outperforming much larger models.
  arXiv  Detail & Related papers  (2023-11-09T19:15:12Z)
• Make-An-Audio: Text-To-Audio Generation with Prompt-Enhanced Diffusion Models [65.18102159618631]
  multimodal generative modeling has created milestones in text-to-image and text-to-video generation. Its application to audio still lags behind for two main reasons: the lack of large-scale datasets with high-quality text-audio pairs, and the complexity of modeling long continuous audio data. We propose Make-An-Audio with a prompt-enhanced diffusion model that addresses these gaps.
  arXiv  Detail & Related papers  (2023-01-30T04:44:34Z)

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.