###### tags: `archive` `thesis` `draft` `jptw`
# (Archive) Chapter 2 Related Work
:::info
Keywords | `sound event detection` `audio fingerprinting` `real-life recordings`
:::
Data annotation is a core ingredient to the success of every AI projects on account of the valuable information provided efficiently. Due to the high-cost of manually labeling, automated data labeling has been a highly-attracted task.

> Ref:
> [1] [Data Annotation & Its Role in Machine Learning](https://www.bmc.com/blogs/data-annotation/)
> ==[2]== [How to apply machine learning and deep learning methods to audio analysis](https://towardsdatascience.com/how-to-apply-machine-learning-and-deep-learning-methods-to-audio-analysis-615e286fcbbc)
> ==[3]== [Top 5 Challenges Making Data Labeling Ineffective](https://dataloop.ai/blog/data-labeling-challenges/)
> [4] [Data Labeling in 2021: How to Choose a Data Labeling Partner](https://research.aimultiple.com/data-labeling/)
> [5] [Toward a Web Search Information Behavior Model](https://link.springer.com/chapter/10.1007/978-3-540-75829-7_12)
> [6] [RCBA: An Efficient Annotation Tool for Community E-Learning](https://ieeexplore.ieee.org/document/6042799)

## 2.1 Sound event detection
Sound event detection is the key technology for the audio-related ML/DL tasks, in applications like retrieval in multimedia databases`[2]atrey2006audio` or unobtrustive monitoring in health care`[3]peng2009healthcare`, even for automatically annotating audio datasets. It has become a well-developed technique and there is a community ([DCASE](http://dcase.community)) dedicated to related workshop and challenge.

> Ref:
> [1] [Google Search | sound event detection "real life recordings"](https://scholar.google.com/scholar?as_ylo=2020&q=sound+event+detection+%22real+life+recordings%22&hl=zh-TW&as_sdt=0,5)
> [2] [Sound Event Localization and Detection | DCASE 2021](http://dcase.community/challenge2020/task-sound-event-localization-and-detection#results)
> [3] [Sound event detection using spatial features and convolutional recurrent neural network](https://ieeexplore.ieee.org/abstract/document/7952260)
> [4] [Sound event detection in real life recordings using coupled matrix factorization of spectral representations and class activity annotations](https://ieeexplore.ieee.org/abstract/document/7177950)
> [5] [Sound Event Detection by Multitask Learning of Sound Events and Scenes with Soft Scene Labels](https://ieeexplore.ieee.org/abstract/document/9053912)
> [6] [Overview and Evaluation of Sound Event Localization and Detection in DCASE 2019](https://ieeexplore.ieee.org/abstract/document/9306885?casa\_token=HlnOm9fRNq4AAAAA:\_0IYifwmRF9g4SGM-MnURdo4FLHtCAfKlPg8O5QTuPn1KkiiQIx4IWuJQK7nz2wJz4b241Y)
> ==[7]== [Sound Event Detection | Toni Heittola](https://homepages.tuni.fi/toni.heittola/research-sound-event-detection#acoustic-semantic-relationship)

## 2.2 Audio Fingerprinting

::: spoiler *rough draft (ch-tw)*
由於有效提供的寶貴信息，數據註釋是任何基於AI的模型訓練成功的核心要素。
聲音事件檢測是與音頻相關的ML任務的關鍵技術，在諸如多媒體數據庫中的檢索或衛生保健中的非干擾性監視之類的應用中。

:::

:::info
- Data annotation
- Sound event detection
-
:::