.png){kind=icon}
返回
Pre-Training Audio Representations With Self-Supervision
.png){kind=icon}
OA
AI
DOI：10.1109/LSP.2020.2985586.png)
.png){kind=icon}
.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
We explore self-supervision as a way to learn general purpose audio representations. Specifically, we propose two self-supervised tasks: Audio2Vec, which aims at reconstructing a spectrogram slice from past and future slices and TemporalGap, which estimates the distance between two short audio segments extracted at random from the same audio clip. We evaluate how the representations learned via self-supervision transfer to different downstream tasks, either training a task-specific linear classifier on top of the pretrained embeddings, or fine-tuning a model end-to-end for each downstream task. Our results show that the representations learned with Audio2Vec transfer better than those learned by fully-supervised training on Audioset. In addition, by fine-tuning Audio2Vec representations it is possible to outperform fully-supervised models trained from scratch on each task, when limited data is available, thus improving label efficiency.
Keyword:
Task analysis
Decoding
Training
Computer architecture
Spectrogram
Predictive models
Time-frequency analysis
Self-supervised learning
audio processing
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
9.6
论文数:
1.1W
被引数:
1.7W
机构
引用论文
.png){kind=icon}
分享收藏分享收藏分享收藏
查看更多内容