arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2104.01778cs.SDcs.AI
收藏

AST:音频频谱图Transformer

AST: Audio Spectrogram Transformer

MIT Computer Science and Artificial Intelligence Laboratory(麻省理工学院计算机科学与人工智能实验室)

Yuan Gong, Yu-An Chung, James Glass

摘要:

在过去的十年中,卷积神经网络(CNN)已被广泛采用作为端到端音频分类模型的主要构建块,其目的是学习从音频频谱图到相应标签的直接映射。为了更好地捕捉长期全球背景,最近的趋势是在CNN之上添加自注意力机制,形成CNN-注意力混合模型。然而,目前还不清楚依赖CNN是否是必要的,以及纯粹基于注意力的神经网络是否足以在音频分类中获得良好的性能。在本文中,我们回答了这个问题,通过介绍音频频谱图Transformer(AST),第一个卷积自由,纯粹基于注意力的音频分类模型。我们在各种音频分类基准上评估了AST,其中它在AudioSet上实现了0.485 mAP的最新结果,在ESC-50上实现了95.6%的准确率,在Speech Commands V2上实现了98.1%的准确率。

英文摘要:

In the past decade, convolutional neural networks (CNNs) have been widely adopted as the main building block for end-to-end audio classification models, which aim to learn a direct mapping from audio spectrograms to corresponding labels. To better capture long-range global context, a recent trend is to add a self-attention mechanism on top of the CNN, forming a CNN-attention hybrid model. However, it is unclear whether the reliance on a CNN is necessary, and if neural networks purely based on attention are sufficient to obtain good performance in audio classification. In this paper, we answer the question by introducing the Audio Spectrogram Transformer (AST), the first convolution-free, purely attention-based model for audio classification. We evaluate AST on various audio classification benchmarks, where it achieves new state-of-the-art results of 0.485 mAP on AudioSet, 95.6% accuracy on ESC-50, and 98.1% accuracy on Speech Commands V2.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑