Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning

• URL: http://arxiv.org/abs/2410.16130v2
• Date: Tue, 31 Dec 2024 09:35:31 GMT
• Title: Can Large Audio-Language Models Truly Hear? Tackling Hallucinations with Multi-Task Assessment and Stepwise Audio Reasoning
• Authors: Chun-Yi Kuan, Hung-yi Lee,
• Abstract summary: Large audio-language models (LALMs) have shown impressive capabilities in understanding and reasoning about audio and speech information. These models still face challenges, including hallucinating non-existent sound events, misidentifying the order of sound events, and incorrectly attributing sound sources.
• Score: 55.2480439325792
• License:
• Abstract: Recent advancements in large audio-language models (LALMs) have shown impressive capabilities in understanding and reasoning about audio and speech information. However, these models still face challenges, including hallucinating non-existent sound events, misidentifying the order of sound events, and incorrectly attributing sound sources, which undermine their reliability and real-world application. To systematically evaluate these issues, we propose three distinct tasks: object existence, temporal order, and object attribute within audio. These tasks assess the models' comprehension of critical audio information aspects. Our experimental results reveal limitations in these fundamental tasks, underscoring the need for better models in recognizing specific sound events, determining event sequences, and identifying sound sources. To improve performance in these areas, we introduce a multi-turn chain-of-thought approach, which demonstrates significantly improved model performance across the proposed tasks.

Related papers

• Evaluation of Deep Audio Representations for Hearables [1.5646349560044959]
  This dataset includes 1,158 audio tracks, each 30 seconds long, created by spatially mixing proprietary monologues with high-quality recordings of everyday acoustic scenes. Our benchmark encompasses eight tasks that assess the general context, speech sources, and technical acoustic properties of the audio scenes. This superiority underscores the advantage of models trained on diverse audio collections, confirming their applicability to a wide array of auditory tasks, including encoding the environment properties necessary for hearable steering.
  arXiv  Detail & Related papers  (2025-02-10T16:51:11Z)
• ADIFF: Explaining audio difference using natural language [31.963783032080993]
  This paper comprehensively studies the task of explaining audio differences and then propose benchmark, baselines for the task. We present two new datasets for audio difference explanation derived from the AudioCaps and Clotho audio captioning datasets. We propose ADIFF, which introduces a cross-projection module, position captioning, and a three-step training process to enhance the model's ability to produce detailed explanations.
  arXiv  Detail & Related papers  (2025-02-06T20:00:43Z)
• AV-Odyssey Bench: Can Your Multimodal LLMs Really Understand Audio-Visual Information? [65.49972312524724]
  multimodal large language models (MLLMs) have expanded their capabilities to include vision and audio modalities. Our proposed DeafTest reveals that MLLMs often struggle with simple tasks humans find trivial. We introduce AV-Odyssey Bench, a comprehensive audio-visual benchmark designed to assess whether those MLLMs can truly understand the audio-visual information.
  arXiv  Detail & Related papers  (2024-12-03T17:41:23Z)
• Enhancing Audio-Language Models through Self-Supervised Post-Training with Text-Audio Pairs [3.8300818830608345]
  Multi-modal contrastive learning strategies for audio and text have rapidly gained interest. The ability of these models to understand natural language and temporal relations is still a largely unexplored and open field for research. We propose to equip the multi-modal ALMs with temporal understanding without loosing their inherent prior capabilities of audio-language tasks with a temporal instillation method TeminAL.
  arXiv  Detail & Related papers  (2024-08-17T18:53:17Z)
• Understanding Sounds, Missing the Questions: The Challenge of Object Hallucination in Large Audio-Language Models [49.87432626548563]
  We introduce methods to assess the extent of object hallucination of publicly available LALMs. Our findings reveal that LALMs are comparable to specialized audio captioning models in their understanding of audio content. We explore the potential of prompt engineering to enhance LALMs' performance on discriminative questions.
  arXiv  Detail & Related papers  (2024-06-12T16:51:54Z)
• Qwen-Audio: Advancing Universal Audio Understanding via Unified Large-Scale Audio-Language Models [98.34889301515412]
  We develop the Qwen-Audio model and address the limitation by scaling up audio-language pre-training to cover over 30 tasks and various audio types. Qwen-Audio achieves impressive performance across diverse benchmark tasks without requiring any task-specific fine-tuning. We further develop Qwen-Audio-Chat, which allows for input from various audios and text inputs, enabling multi-turn dialogues and supporting various audio-central scenarios.
  arXiv  Detail & Related papers  (2023-11-14T05:34:50Z)
• AV-SUPERB: A Multi-Task Evaluation Benchmark for Audio-Visual Representation Models [92.92233932921741]
  We propose the AV-SUPERB benchmark that enables general-purpose evaluation of unimodal audio/visual and bimodal fusion representations. We evaluate 5 recent self-supervised models and show that none of these models generalize to all tasks. We show that representations may be improved with intermediate-task fine-tuning and audio event classification with AudioSet serves as a strong intermediate task.
  arXiv  Detail & Related papers  (2023-09-19T17:35:16Z)
• Audiovisual Highlight Detection in Videos [78.26206014711552]
  We present results from two experiments: efficacy study of single features on the task, and an ablation study where we leave one feature out at a time. For the video summarization task, our results indicate that the visual features carry most information, and including audiovisual features improves over visual-only information. Results indicate that we can transfer knowledge from the video summarization task to a model trained specifically for the task of highlight detection.
  arXiv  Detail & Related papers  (2021-02-11T02:24:00Z)
• COALA: Co-Aligned Autoencoders for Learning Semantically Enriched Audio Representations [32.456824945999465]
  We propose a method for learning audio representations, aligning the learned latent representations of audio and associated tags. We evaluate the quality of our embedding model, measuring its performance as a feature extractor on three different tasks.
  arXiv  Detail & Related papers  (2020-06-15T13:17:18Z)

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.