arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2201.12352cs.SDcs.LGeess.AS
收藏

基于注意加权事件嵌入的自动音频字幕

Automatic Audio Captioning using Attention weighted Event based Embeddings

TCS Research, Tata Consultancy Services Limited(塔塔咨询服务有限公司TCS研究院)

Swapnil Bhosale, Rupayan Chakraborty, Sunil Kumar Kopparapu

摘要:

自动音频字幕(AAC)是指将音频翻译成描述音频事件、事件来源及其关系的自然语言的任务。目前AAC数据集的样本有限,已经形成了将迁移学习与音频事件检测(AED)结合作为父任务的趋势。朝着这个方向,在本文中,我们提出了一种编码器-解码器架构,具有用于AAC的轻量级(即具有较少的可学习参数)Bi-LSTM递归层,并比较了两种最先进的预训练AED模型作为嵌入提取器的性能。我们的研究结果表明,一个有效的AED为基础的嵌入提取器结合时间的注意力和增强技术是能够超越现有的文献与计算密集型架构。此外,我们还提供了证据,证明作为我们模型的一部分生成的非均匀注意力加权编码的能力,以便于解码器在生成每个令牌时浏览音频的特定部分。

英文摘要:

Automatic Audio Captioning (AAC) refers to the task of translating audio into a natural language that describes the audio events, source of the events and their relationships. The limited samples in AAC datasets at present, has set up a trend to incorporate transfer learning with Audio Event Detection (AED) as a parent task. Towards this direction, in this paper, we propose an encoder-decoder architecture with light-weight (i.e. with lesser learnable parameters) Bi-LSTM recurrent layers for AAC and compare the performance of two state-of-the-art pre-trained AED models as embedding extractors. Our results show that an efficient AED based embedding extractor combined with temporal attention and augmentation techniques is able to surpass existing literature with computationally intensive architectures. Further, we provide evidence of the ability of the non-uniform attention weighted encoding generated as a part of our model to facilitate the decoder glance over specific sections of the audio while generating each token.

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。

↑