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.

翻译：增强大型语言模型对音频的理解能力——包括非语音声音和非语言性语音——对于大型语言模型在多样化实际应用场景中至关重要。本文提出音频火烈鸟（Audio Flamingo），一种新型音频语言模型，具备：1）强大的音频理解能力；2）通过上下文学习和检索快速适应未见任务的能力；3）强大的多轮对话能力。我们引入一系列训练技术、架构设计和数据策略来增强模型这些能力。跨多种音频理解任务的广泛评估验证了本方法的有效性，并创下新的最先进基准。