英文新聞
Researchers are working on machine learning systems to identify1 COVID-19 cases by the sounds of a person’s cough.
One system has demonstrated a high success rate in detecting COVID-19 in people with no physical signs2 of the disease. Such a tool could be important in the fight against3 COVID-19, which can be spread by people who do not even know they are infected.
Researchers at the Massachusetts Institute of Technology, MIT, recently published a paper reporting results of the system.
The team created an artificial intelligence (AI) model to examine the sounds of people who produced a forced cough4. The sounds were collected from people who recorded them on computers or mobile devices. The individuals were also asked to provide information about any symptoms they were experiencing, as well as whether they had been officially tested for COVID-19.
People then sent the recordings and data to researchers through the internet or their devices. Researchers reported they had received more than 70,000 recordings, amounting to5 about 200,000 individual cough examples. The team then trained the model on the cough sounds, as well as spoken words.
When the new cough recordings were fed into6 the system, it correctly identified 98.5 percent of coughs from people confirmed to have COVID-19, the researchers reported. The model also detected 100 percent of coughs in people who reported they had tested positive7 for the virus, but had no signs of the disease.
The team says it is working to develop “a user-friendly8 app” that could be used on a wide basis to detect COVID-19 cases. This would make it possible for users to cough into their phone and receive immediate information on whether they might be infected and should seek an official test.
中文翻譯
研究人員正致力於藉由一個人的咳嗽聲來辨識新冠病毒病例的機器學習系統。
有個系統已經展現了高成功率，它可以偵測出無身體徵兆的人體內的病毒。這樣的工具對於對抗新冠病毒很重要，這病毒會藉著甚至不知道自己已經感染的人散佈。
麻省理工學院(MIT)的研究人員近期發表了一篇論文，報告了此系統的相關結果‧
此團隊製造了一個人工智慧(AI)模型來檢查人們故意咳嗽的的聲音。這些咳嗽聲藉著人們從電腦或行動裝置錄製來收集。每個人也須提供他們正經歷的任何症狀資訊，以及他們是否已被正式檢測過新冠病毒。
人們接著將錄音和數據透過網路或他們的裝置寄給研究人員。研究人員報告他們收到了超過70,000則錄音，總計達200,000段個別咳嗽實例。接著團隊訓練咳嗽聲以及口語的模型。
研究人員指出，當新的咳嗽錄音輸入系統中的時候，系統能正確辨識98.5%確診新冠病毒病患的咳嗽聲。模型也能 100% 偵測出確診卻沒有疾病症狀的病患咳嗽聲。
團隊表示他們正在開發使用者友善的應用程式，可利用於更廣泛的基礎上。這可能使得使用者對著他們的手機咳嗽，然後就能收到是否他們可能感染或應該尋求正式檢測的立即資訊。
單字學習
| 英文單字 | 詞性 | 中文 |
|---|---|---|
| identify | (v.) | 辨識；辨認 |
| cough | (v./n.) | 咳嗽 |
| demonstrate | (v.) | 展現；展示 |
| detect | (v.) | 偵測 |
| artificial intelligence (AI) | (n.) | 人工智慧 |
| symptom | (n.) | 症狀 |
| device | (n.) | 裝置；器具 |
| confirm | (v.) | 確認 |
| positive | (adj.) | 陽性的 |
| virus | (n.) | 病毒 |
| sign | (n.) | 徵兆；跡象 |
| immediate | (adj.) | 立即的 |
片語與其他用語
| 英文 | 中文 |
|---|---|
| n.-friendly | …友善的 |
| amount to | 總計到達…… |
| the fight against | 與……的對抗 |
重點解析
重點解析
- identify這個動詞指的是辨識或辨認的意思，跟recognize意思相近，facial recognition technology 「人臉辨識技術」與fingerprint recognition system 「指紋辨識系統」都是biometric identification「生物特徵辨識」的一種。
- sign當名詞有很多意思：招牌、標誌和手勢等，在這篇文章中則是疾病的「徵兆」，這裡意思跟symptom差不多。
- fight against 是「與……對抗/抗爭」的意思，可以把fight當動詞用，例如：People assembled to fight against the gender inequalities. 「群眾聚集起來一起對抗性別不平等」。也可以把fight當名詞使用：The fight against cancer is still ongoing, to which people strive to find the solution. 人類與癌症的對抗持續進行中，他們致力於找出癌症的解方。
- force是逼迫、強迫的意思，所以forced cough是非自然的咳嗽，被刻意製造出的咳嗽反應。
- amount to是一個動詞片語，有「總計，總數達到……」的意思。例如：The confirmed cases of COVID-19 have amounted to 55,600,000 globally. 「新冠病毒確診人數全球總計已達5560萬人」。
- feed是餵養的意思，但feed into在這邊是數據或資料放入電腦、資料庫的意思。另外它也可指「流入、注入」：This small stream feeds into the river near here. 「這條小溪注入這附近的河」。
- positive 「有正面的」、「正向的」、「積極的」和「肯定的」等意思，但在醫事檢驗中positive是「陽性的」，negative則是「陰性的」。
- user-friendly 指的是對使用者友善的，也就是使用者使用上方便容易的意思。像這樣一個名詞+friendly的用法還有很多，例如：environment-friendly環境友善的、eco-friendly 生態友善的、gender-friendly 性別友善的等等。
本文摘自：https://learningenglish.voanews.com/a/ai-aims-to-identify-covid-19-by-sounds-of-a-cough/5648054.html
菁英線上課程：
► https://www.language-center.com.tw/english-online/index.html
菁英國際，讓人生開始不一樣
website：https://www.language-center.com.tw/
facebook：https://www.facebook.com/language.center.tw
contact us：0800-090-800