Automated audio captioning aims to describe audio data with captions using natural language. Existing methods often employ an encoder-decoder structure, where the attention-based decoder (e.g., Transformer decoder) is widely used and achieves state-of-the-art performance. Although this method effectively captures global information within audio data via the self-attention mechanism, it may ignore the event with short time duration, due to its limitation in capturing local information in an audio signal, leading to inaccurate prediction of captions. To address this issue, we propose a method using the pretrained audio neural networks (PANNs) as the encoder and local information assisted attention-free Transformer (LocalAFT) as the decoder. The novelty of our method is in the proposal of the LocalAFT decoder, which allows local information within an audio signal to be captured while retaining the global information. This enables the events of different duration, including short duration, to be captured for more precise caption generation. Experiments show that our method outperforms the state-of-the-art methods in Task 6 of the DCASE 2021 Challenge with the standard attention-based decoder for caption generation.
翻译:现有方法通常使用一种编码器解码器结构(例如,变换器解码器),在这种结构中,以关注为基础的解码器(例如,变换器解码器)被广泛使用,并达到最先进的性能。虽然这种方法通过自省机制有效地在音频数据中捕获全球信息,但由于在音频信号中获取当地信息受到限制,从而导致对字幕的预测不准确,因此可能会在短时间内忽略这一事件,从而导致在音频信号中获取当地信息受到限制,从而导致对字幕的预测不准确。为解决这一问题,我们建议采用一种方法,使用预先培训的音频神经网络(PANNs)作为编码器和地方信息协助的无注意力变码器(LoalAFT)作为解码器。我们方法的新颖之处在于“LocalAFT decoder”的建议中,它允许在保留全球信息的同时在音频信号中捕获当地信息。这使得不同时间(包括短期)的事件能够被记录,用于更精确的字幕生成。实验表明,我们的方法超出了以DC 2021号第6号任务生成中基于标准的注意状态的方法。