Up to 40 percent of road deaths around the world are thought to be caused by alcohol.

世界上40%以上的交通死亡事故都由醉駕造成。

But one day, cars could detect whether a driver’s voice sounds drunk, to stop them from driving and prevent accidents.

但也許有一天，車(chē)輛可以根據(jù)駕駛員的聲音自動(dòng)檢測(cè)他們飲酒與否，從而阻止其駕車(chē)、預(yù)防交通事故發(fā)生。

Researchers in Germany have created the first library of drunk speech patterns, which could be used to predict drunkenness by listening for vocal cues.

德國(guó)研究人員創(chuàng)立了世界上第一個(gè)“醉后語(yǔ)音模式”圖書(shū)館。這樣通過(guò)分析語(yǔ)音信息就能預(yù)測(cè)駕駛員是否處于醉酒狀態(tài)。

Called the Alcohol Language Corpus, the database was made between 2007 and 2009 by giving people too much alcohol to drink, before recording conversations conducted in a stopped car, where the drunk person was sitting in the passenger seat.

這個(gè)名為“酒后語(yǔ)言語(yǔ)料庫(kù)”的數(shù)據(jù)庫(kù)建于2007年到2009年間。實(shí)驗(yàn)場(chǎng)所是在一輛沒(méi)有開(kāi)動(dòng)的汽車(chē)上，大量飲酒后的受測(cè)者坐在乘客席上，他們說(shuō)的話都會(huì)被錄下來(lái)。

There are currently conversations from 162 German men and women in the publicly-available audio database.

該音頻數(shù)據(jù)庫(kù)對(duì)大眾開(kāi)放，目前的對(duì)話資料來(lái)自162名德國(guó)男性和女性。

Experts at Ludwig Maximilian University of Munich and the Institute of Legal Medicine in the city collected the data, FastCompany reported.

《快公司》（Fast Company）雜志報(bào)道，這些數(shù)據(jù)由慕尼黑大學(xué)（Ludwig Maximilian University）專(zhuān)家和慕尼黑市法醫(yī)學(xué)研究協(xié)會(huì)（the Institute of Legal Medicine）共同收集。

From this, an algorithm that is capable of detecting whether someone is drunk by listening in on slurring speech patterns, has been created by computer scientists at Queens College and Columbia University.

基于這些數(shù)據(jù)，來(lái)自皇后學(xué)院（Queens College）和哥倫比亞大學(xué)（Columbia University）的計(jì)算機(jī)科學(xué)家們開(kāi)發(fā)出一種測(cè)醉程序，這樣通過(guò)測(cè)聽(tīng)模糊語(yǔ)音模式就能判斷駕駛員是否醉酒。

They found that they could detect drunken speech patterns much like identifying an accent.

他們發(fā)現(xiàn)檢測(cè)醉后語(yǔ)音模式的過(guò)程與識(shí)別口音類(lèi)似。

Drunken speech hall marks include stammering and stuttering. Voices also tend to rise in pitch and words begin to slur, they said.

他們指出，醉酒的話語(yǔ)特征有說(shuō)話結(jié)結(jié)巴巴、音調(diào)升高、含糊不清等等。

It is hoped that the software could be used alongside devices such as locks and immobilizers to make it impossible for people to drive when drunk – perhaps by asking them a few questions while analyzing the driver’s voice.

人們希望這種軟件能和車(chē)鎖、防盜系統(tǒng)等設(shè)備一起使用以杜絕醉駕——或許可以通過(guò)向駕駛員提問(wèn)來(lái)分析其語(yǔ)音。

‘The cars themselves could listen to the driver, detect that the potential driver is intoxicated, and prevent the car from starting,’ the researchers explained.

研究人員說(shuō)：“車(chē)輛能自動(dòng)監(jiān)聽(tīng)駕駛員說(shuō)話，測(cè)出其醉酒狀態(tài)，并阻止車(chē)輛發(fā)動(dòng)。”

However, the safety system may be a few years away, because the algorithm to detect drunkenness is typically only right around three quarters of the time.

但是，此安全系統(tǒng)的應(yīng)用可能需要好幾年，因?yàn)槟壳斑@個(gè)程序測(cè)醉的準(zhǔn)確度只有75%左右。

‘That means, you want to go and drive your car, one in three times we're going to say you're drunk. That's bad for a product,’ Professor Andrew Rosenberg, of Queens College New York (CUNY) said.

“那就意味著你需要開(kāi)車(chē)時(shí)，三次中就有一次車(chē)輛誤判你醉酒。那可不是個(gè)好產(chǎn)品。”紐約皇后大學(xué)的安德魯·羅森博格（Andrew Rosenberg）教授說(shuō)道。

The next step is to add more languages to the library so that more experts can use the public library for their own research.

下一步要做的是添加更多語(yǔ)種到圖書(shū)館中，讓更多專(zhuān)家能使用這寫(xiě)公共資源進(jìn)行各自的研究。

（翻譯：xysweetxy 編輯：Julie）