SDAICLASJun 17, 2024

GAMA: A Large Audio-Language Model with Advanced Audio Understanding and Complex Reasoning Abilities

arXiv:2406.11768v1185 citations
Originality Highly original
AI Analysis

This work addresses the challenge of enabling AI systems to understand non-speech sounds and perform complex reasoning, which is incremental as it builds on existing audio-language models with novel training methods.

The paper tackles the problem of audio understanding and complex reasoning by proposing GAMA, a large audio-language model that integrates multiple audio representations and is fine-tuned on a synthetic instruction dataset. The result shows that GAMA outperforms other models on diverse audio tasks by margins of 1%-84% and demonstrates superior complex reasoning capabilities.

Perceiving and understanding non-speech sounds and non-verbal speech is essential to making decisions that help us interact with our surroundings. In this paper, we propose GAMA, a novel General-purpose Large Audio-Language Model (LALM) with Advanced Audio Understanding and Complex Reasoning Abilities. We build GAMA by integrating an LLM with multiple types of audio representations, including features from a custom Audio Q-Former, a multi-layer aggregator that aggregates features from multiple layers of an audio encoder. We fine-tune GAMA on a large-scale audio-language dataset, which augments it with audio understanding capabilities. Next, we propose CompA-R (Instruction-Tuning for Complex Audio Reasoning), a synthetically generated instruction-tuning (IT) dataset with instructions that require the model to perform complex reasoning on the input audio. We instruction-tune GAMA with CompA-R to endow it with complex reasoning abilities, where we further add a soft prompt as input with high-level semantic evidence by leveraging event tags of the input audio. Finally, we also propose CompA-R-test, a human-labeled evaluation dataset for evaluating the capabilities of LALMs on open-ended audio question-answering that requires complex reasoning. Through automated and expert human evaluations, we show that GAMA outperforms all other LALMs in literature on diverse audio understanding tasks by margins of 1%-84%. Further, GAMA IT-ed on CompA-R proves to be superior in its complex reasoning and instruction following capabilities.

Code Implementations2 repos
Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes