@inproceedings{deshmukh2023pengi,
author = {Deshmukh, Soham and Elizalde, Benjamin and Singh, Rita and Wang, Huaming},
title = {Pengi: An Audio Language Model for Audio Tasks},
booktitle = {NeurIPS 2023},
year = {2023},
month = {May},
abstract = {In the domain of audio processing, Transfer Learning has facilitated the rise of Self-Supervised Learning and Zero-Shot Learning techniques. These approaches have led to the development of versatile models capable of tackling a wide array of tasks, while delivering state-of-the-art performance. However, current models inherently lack the capacity to produce the requisite language for open-ended tasks, such as Audio Captioning or Audio Question & Answering. We introduce Pengi, a novel Audio Language Model that leverages Transfer Learning by framing all audio tasks as text-generation tasks. It takes as input, an audio recording, and text, and generates free-form text as output. The input audio is represented as a sequence of continuous embeddings by an audio encoder. A text encoder does the same for the corresponding text input. Both sequences are combined as a prefix to prompt a pre-trained frozen language model. The unified architecture of Pengi enables open-ended tasks and close-ended tasks without any additional fine-tuning or task-specific extensions. When evaluated on 22 downstream tasks, our approach yields state-of-the-art performance in several of them. Our results show that connecting language models with audio models is a major step towards general-purpose audio understanding.},
url = {http://approjects.co.za/?big=en-us/research/publication/pengi-an-audio-language-model-for-audio-tasks/},
}