From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data

• URL: http://arxiv.org/abs/2505.20166v1
• Date: Mon, 26 May 2025 16:08:41 GMT
• Title: From Alignment to Advancement: Bootstrapping Audio-Language Alignment with Synthetic Data
• Authors: Chun-Yi Kuan, Hung-yi Lee,
• Abstract summary: We introduce LISTEN, a contrastive-like training method designed to improve ALLMs' ability to distinguish between present and absent sounds.<n>We also extend BALSa to multi-audio scenarios, where the model either explains the differences between audio inputs or produces a unified caption.<n> Experimental results indicate that our method effectively mitigates audio hallucinations while reliably maintaining strong performance in audio understanding, reasoning, and instruction-following skills.
• Score: 55.2480439325792
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Audio-aware large language models (ALLMs) have recently made great strides in understanding and processing audio inputs. These models are typically adapted from text-based large language models (LLMs) through additional training on audio-related tasks. However, this adaptation process presents two major limitations. First, ALLMs often suffer from catastrophic forgetting, where important textual capabilities such as instruction-following are lost after training on audio data. In some cases, models may even hallucinate sounds that are not present in the input audio, raising concerns about their reliability. Second, achieving cross-modal alignment between audio and language typically relies on large collections of task-specific question-answer pairs for instruction tuning, making the process resource-intensive. To address these issues, we leverage the backbone LLMs from ALLMs to synthesize general-purpose caption-style alignment data. We refer to this process as bootstrapping audio-language alignment via synthetic data generation from backbone LLMs (BALSa). Building on BALSa, we introduce LISTEN (Learning to Identify Sounds Through Extended Negative Samples), a contrastive-like training method designed to improve ALLMs' ability to distinguish between present and absent sounds. We further extend BALSa to multi-audio scenarios, where the model either explains the differences between audio inputs or produces a unified caption that describes them all, thereby enhancing audio-language alignment. Experimental results indicate that our method effectively mitigates audio hallucinations while reliably maintaining strong performance in audio understanding, reasoning, and instruction-following skills. Moreover, incorporating multi-audio training further enhances the model's comprehension and reasoning capabilities. Overall, BALSa offers an efficient and scalable approach to the development of ALLMs.

Related papers

• Step-Audio-AQAA: a Fully End-to-End Expressive Large Audio Language Model [85.72664004969182]
  We introduce Step-Audio-AQAA, a fully end-to-end LALM designed for Audio Query-Audio Answer (AQAA) tasks.<n>The model integrates a dual-codebook audio tokenizer for linguistic and semantic feature extraction.<n>Our post-training approach employs interleaved token-output of text and audio to enhance semantic coherence.
  arXiv  Detail & Related papers  (2025-06-10T16:37:39Z)
• IFEval-Audio: Benchmarking Instruction-Following Capability in Audio-based Large Language Models [18.11667976818302]
  IFEval-Audio contains 280 audio-instruction-answer triples across six diverse dimensions.<n>Each example pairs an audio input with a text instruction, requiring the model to generate an output that follows a specified structure.<n>We benchmark state-of-the-art audio LLMs on their ability to follow audio-involved instructions.
  arXiv  Detail & Related papers  (2025-05-22T15:15:29Z)
• Teaching Audio-Aware Large Language Models What Does Not Hear: Mitigating Hallucinations through Synthesized Negative Samples [55.2480439325792]
  Recent advancements in audio-aware large language models (ALLMs) enable them to process and understand audio inputs.<n>These models often hallucinate non-existent sound events, reducing their reliability in real-world applications.<n>We propose LISTEN, a contrastive-like training method that enhances ALLMs' ability to distinguish between present and absent sounds.
  arXiv  Detail & Related papers  (2025-05-20T15:44:01Z)
• Baichuan-Audio: A Unified Framework for End-to-End Speech Interaction [9.101978573666546]
  Baichuan-Audio is an end-to-end audio large language model that seamlessly integrates audio understanding and generation.<n>It features a text-guided aligned speech generation mechanism, enabling real-time speech interaction with both comprehension and generation capabilities.
  arXiv  Detail & Related papers  (2025-02-24T15:16:34Z)
• 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)
• C3LLM: Conditional Multimodal Content Generation Using Large Language Models [66.11184017840688]
  We introduce C3LLM, a novel framework combining three tasks of video-to-audio, audio-to-text, and text-to-audio together. C3LLM adapts the Large Language Model (LLM) structure as a bridge for aligning different modalities. Our method combines the previous tasks of audio understanding, video-to-audio generation, and text-to-audio generation together into one unified model.
  arXiv  Detail & Related papers  (2024-05-25T09:10:12Z)
• AudioSetMix: Enhancing Audio-Language Datasets with LLM-Assisted Augmentations [1.2101820447447276]
  Multi-modal learning in the audio-language domain has seen significant advancements in recent years. However, audio-language learning faces challenges due to limited and lower-quality data compared to image-language tasks. Our method systematically generates audio-caption pairs by augmenting audio clips with natural language labels and corresponding audio signal processing operations. This scalable method produces AudioSetMix, a high-quality training dataset for text-and-audio related models.
  arXiv  Detail & Related papers  (2024-05-17T21:08:58Z)
• LauraGPT: Listen, Attend, Understand, and Regenerate Audio with GPT [65.69648099999439]
  Generative Pre-trained Transformer (GPT) models have achieved remarkable performance on various natural language processing tasks. We propose LauraGPT, a novel unified audio-and-text GPT-based LLM for audio recognition, understanding, and generation.
  arXiv  Detail & Related papers  (2023-10-07T03:17:59Z)
• Exploring the Role of Audio in Video Captioning [59.679122191706426]
  We present an audio-visual framework, which aims to fully exploit the potential of the audio modality for captioning. We propose new local-global fusion mechanisms to improve information exchange across audio and video.
  arXiv  Detail & Related papers  (2023-06-21T20:54:52Z)
• Make-An-Audio 2: Temporal-Enhanced Text-to-Audio Generation [72.7915031238824]
  Large diffusion models have been successful in text-to-audio (T2A) synthesis tasks. They often suffer from common issues such as semantic misalignment and poor temporal consistency. We propose Make-an-Audio 2, a latent diffusion-based T2A method that builds on the success of Make-an-Audio.
  arXiv  Detail & Related papers  (2023-05-29T10:41:28Z)

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.