Audio Flamingo: A Novel Audio Language Model with Few-Shot Learning and Dialogue Abilities
This addresses the need for LLMs to handle real-world audio applications, representing a domain-specific advancement.
The paper tackles the problem of enabling large language models to understand diverse audio inputs, including non-speech sounds and non-verbal speech, by proposing Audio Flamingo, a novel audio language model that achieves new state-of-the-art benchmarks across various audio understanding tasks.
Augmenting large language models (LLMs) to understand audio -- including non-speech sounds and non-verbal speech -- is critically important for diverse real-world applications of LLMs. In this paper, we propose Audio Flamingo, a novel audio language model with 1) strong audio understanding abilities, 2) the ability to quickly adapt to unseen tasks via in-context learning and retrieval, and 3) strong multi-turn dialogue abilities. We introduce a series of training techniques, architecture design, and data strategies to enhance our model with these abilities. Extensive evaluations across various audio understanding tasks confirm the efficacy of our method, setting new state-of-the-art benchmarks. Our demo website is https://audioflamingo.github.io/ and the code is open-sourced at https://github.com/NVIDIA/audio-flamingo.