AudioGPT: Understanding and Generating Speech, Music, Sound, and Talking Head
Authors:
Top Cited Papers
Open Access
- 24 March 2024
- journal article
- research article
- Published by Association for the Advancement of Artificial Intelligence (AAAI) in Proceedings of the AAAI Conference on Artificial Intelligence
- Vol. 38 (21) , 23802-23804
Abstract
Large language models (LLMs) have exhibited remarkable capabilities across a variety of domains and tasks, challenging our understanding of learning and cognition. Despite the recent success, current LLMs are not capable of processing complex audio information or conducting spoken conversations (like Siri or Alexa). In this work, we propose a multi-modal AI system named AudioGPT, which complements LLMs (i.e., ChatGPT) with 1) foundation models to process complex audio information and solve numerous understanding and generation tasks; and 2) the input/output interface (ASR, TTS) to support spoken dialogue. With an increasing demand to evaluate multi-modal LLMs of human intention understanding and cooperation with foundation models, we outline the principles and processes and test AudioGPT in terms of consistency, capability, and robustness. Experimental results demonstrate the capabilities of AudioGPT in solving 16 AI tasks with speech, music, sound, and talking head understanding and generation in multi-round dialogues, which empower humans to create rich and diverse audio content with unprecedented ease. Code can be found in https://github.com/AIGC-Audio/AudioGPTKeywords
All Related Versions
This publication has 6 references indexed in Scilit:
- Separate What You Describe: Language-Queried Audio Source Separation2022
- Audio Pyramid Transformer with Domain Adaption for Weakly Supervised Sound Event Detection and Audio Classification2022
- FastDiff: A Fast Conditional Diffusion Model for High-Quality Speech Synthesis2022
- HuBERT: Self-Supervised Speech Representation Learning by Masked Prediction of Hidden UnitsIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2021
- Conv-TasNet: Surpassing Ideal Time–Frequency Magnitude Masking for Speech SeparationIEEE/ACM Transactions on Audio, Speech, and Language Processing, 2019
- BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding2019