外刊社banner.gif

经济学人双语精读TE-2023-05-08期|人工智能：装病打电话请假（PDF版+Word版+音频）

5.8英语外刊社人工智能装病.png

5.8每日一篇 | 英语外刊社

Artificial intelligence：Sickies called
An algorithm can diagnose a cold from changes in someone’s voice

【1】Faking sickness is about to get harder. Sneaking a day off work by nervously coughing down the phone to your boss might no longer cut the mustard—very soon your company might be able to tell whether or not your symptoms are real, just from the sound of your voice.

【2】As anyone who has woken up with a runny nose and a voice like Darth Vader can attest, infection with the common cold virus alters how a person’s voice sounds. That is because the vocal cords often become inflamed, which changes their acoustic properties. The tissue temporarily swells and, therefore, vibrates at a lower pitch, which tends to make people with a cold develop a deeper voice.

【3】A research team at the Sardar Vallabhbhai National Institute of Technology in Surat, India, tried to decode exactly how a “cold voice” differs from a healthy voice. Their research makes use of the fact that human speech, like any musical instrument, does not produce single frequencies of sounds. Even the best trained singers cannot hit pure notes like those that come from tuning forks. The dominant notes in the human voice are instead accompanied by a series of higher-pitched overtones.

【4】Together these sets of notes fit into mathematical patterns called harmonics, with overtones having frequencies that are multiples of the original note. For example, the pitch of the second harmonic note is twice the frequency of the main note and so on. The amplitude (loudness) of these harmonics in speech tends to diminish as they proceed up the frequency scale. The team of researchers, led by Pankaj Warule, an electronic engineer, reasoned that infection with a cold might alter how this attenuation happened.

【5】To find out, the scientists made use of an unusual resource: recordings of the voices of 630 people in Germany, 111 of whom were suffering from a cold. Each was asked to count from one to 40 and describe what they did at the weekend. They also read aloud Aesop’s fable “The North Wind and the Sun”, which has been a popular text for phonetics research since 1949.

【6】By breaking down each person’s speech into its spectrum of component wavelengths, the researchers could identify the dominant frequencyand the harmonics in each case. They then used machine-learning algorithms to analyse the relationships between the amplitudes of these harmonicsand found patterns that could distinguish the cold voices from the healthy voices. They reported their work in Biomedical Signal Processing and Control.

【7】It is not just the common cold that can be diagnosed from speech in this way. Other scientists are looking at how conditions from Parkinson’s disease and depression to head and neck cancers can also affect the patterns of frequencies in a person’s voice. It is part of a wider effort by medics, psychiatrists and computer scientists to remotely detect biomarkers for diseases in data collected on how people talk, write and even walk.

【8】The Indian team’s diagnosis of cold voice is not yet foolproof. The results show it can correctly diagnose a cold up to around 70% of the time. Faced with another dreary Monday at the office, would you take the risk?

①短语：1.原文：Sneaking a day off work by nervously coughing down the phone to your boss might no longer cut the mustard.

词典: cut the mustard 如所期待的那么好；符合要求

例句：Other magazines have tried to copy the formula but have never quite cut the mustard.

其他杂志都想套用这一方法，但都做得不好。

2.原文：The tissue temporarily swells and, therefore, vibrates at a lower pitch, which tends to make people with a cold develop a deeper voice.

词典: tend to do sth 往往会做某事；倾向于做某事

例句：A problem for manufacturers is that lighter cars tend to be noisy.

制造商们遇到的一个问题是，重量较轻的汽车往往噪音大。

3.原文：Together these sets of notes fit into mathematical patterns called harmonics, with overtones having frequencies that are multiples of the original note.

词典: fit into 融入；归属，适于（种情形或体系）

例句：Most film locations broadly fit into two categories; those on private property and those in a public place.

多数电影的拍摄场地大致归为两类：私人宅院与公共场地。

4.原文：They then used machine-learning algorithms to analyse the relationships between the amplitudes of these harmonics and found patterns that could distinguish the cold voices from the healthy voices.

词典: distinguish A from B 区分A和B；A有别于B

例句：There is something about music that distinguishes it from all other art forms.

音乐的某种特质使其有别于所有其他艺术形式。

②长难句

1. 原文：Their research makes use of the fact that human speech, like any musical instrument, does not produce single frequencies of sounds.

分析：本句包含一个同位语从句。主句为“Their research makes use of the fact”；“that human speech... sounds”为同位语从句，对the fact进行解释说明。

译文：他们的研究基于这一事实：就像任何乐器一样，人类语言不会产生单一频率的声音。

2. 原文：They then used machine-learning algorithms to analyse the relationships between the amplitudes of these harmonics and found patterns that could distinguish the cold voices from the healthy voices.

分析：本句包含一个限制性定语从句。主句为“They used machine-learning algorithms and found patterns”；“to analyse... these harmonics ”为目的状语；“that could ... healthy voices”为限制性定语从句，修饰patterns。

译文：然后，他们使用机器学习算法来分析这些谐波振幅之间的关系，找到能够区分感冒嗓和健康嗓的模式。

③写作技巧：

The amplitude (loudness) of these harmonics in speech tends to diminish as they proceed up the frequency scale.

这些谐波在语音中的振幅（响度）随着频率增加而减小。

The team of researchers, led by Pankaj Warule, an electronic engineer, reasoned that infection with a cold might alter how this attenuation happened.

电子工程师潘卡杰·瓦鲁尔（Pankaj Warule）领导的研究团队推断，感冒可能会改变振幅衰减的发生方式。

生词: diminish v.减少，减弱

proceed v.继续做

attenuation n.衰减；减弱动词形式为attenuate“使减弱；使减少”

本文可积累两个表示“减少”的词：diminish和attenuate。

proceed up表示“继续向上”，可引申为“增加；上升”。

proceed to do sth表示“继续做某事”

proceed against 表示“提起诉讼；起诉”

例句：The government strives to promote renewable energies and energy efficiency in all sectors in order to attenuate the negative effects of climate change

政府努力在所有部门推广可再生能源和节能，以期减轻气候变化带来的不利影响。

④背景知识：

Harmonics（谐波）：基波（Fundamental）频率是信号的主要频率（基频），在音频中，它是一个声音中最低的频率，基波决定了声音的音调。谐波频率比信号的主要频率高，是频率中为基波频率整数倍的频率成分。假设现在音频频率的基波是100Hz，那么谐波就是200Hz、300Hz、400Hz……谐波的作用就是美化声音赋予色彩。一般对于大多数人声或乐器，适当提升基波低端频率处的均衡量，可以获得温暖感与丰满度，同理，如果声音太沉闷，也可以衰减基波频率的均衡量；而提升谐波频率处的均衡量，能够增强声音的现场感与清晰度，同理，如果太刺耳，也可以衰减谐波频率处的均衡量。

段落大意：

【1】算法能通过人声诊断感冒，装病越来越难了。

【2】感冒患者的声音会发生变化。

【3】研究团队正在破解健康嗓和感冒嗓的区别。

【4】感冒会改变人声中振幅衰减的方式。

【5】研究团队对630位德国人的人声录音进行分析。

【6】研究团队找到了能区分感冒嗓和健康嗓的方式。

【7】这项技术还能检测其他疾病对人声频率模式的影响。

【8】这项技术诊断感冒的正确率高达70%左右。