BCI Device Spells Your Brain’s Thoughts Out脑机接口设备读心有术

戴维·阿克斯　俞月圆/译

One of the great tragedies of anarthria， the loss of speech， is that many people who suffer the condition can still think clearly. They just cant express themselves the way most of us do， with words. Especially if theyre also paralyzed and cant type out their thoughts on a tablet.

言语讷吃，即丧失言语能力的疾病。患上此病的一大悲剧在于，许多患者仍然能够清晰地思考，只是不能像我们大多数人一样用语言表达自我。如果他们同时还瘫痪了，不能在平板电脑上打出他们的想法，情况就愈加凄惨。

For years， scientists have been trying to help anarthric people—in particular paralyzed ones—speak through technology. The latest approach is to implant devices， in or near the brains of anarthric people， that can literally read the electrical impulses that comprise their thoughts—and beam text to a device that either displays it or sounds it out.

多年来，科学家们一直试图通过技术帮助言语讷吃患者，特别是其中瘫痪的患者，帮他们开口说话。最新的方法是在言语讷吃患者的大脑中或大脑附近植入设备，直接读取构成他们思想的电脉冲，并将文本传送到一个可以显示或者念出该文本的设备上。

These brain-computer interfaces， or BCIs， have been getting more and more sophisticated. But they still have a big accuracy problem. In a major experiment four years ago， one leading BCI prototype mistranslated the thoughts of around a quarter of the trials participants.

这些脑机接口（或称BCI）变得越来越精密，但准确度仍然是一个很大的问题。在4年前的一项重要试验中，一个顶级BCI原型误译了大约1/4试验参与者的想法。

In other words， every fourth phrase the users were thinking… ended up wrong on the screen. Thats almost as if every fourth line of text you wrote in an email conversation just ended up being automatically rewritten as gibberish1.

换句话说，用户想到的短语里，每隔3组就会在屏幕上显示出1组错误短语。这几乎就像你写来往电子邮件时，每写完3行，第4行就会被自动改写为胡言乱语。

The same team that oversaw that 2019 trial， the Chang Lab at University of California， San Francisco， is now trying a different approach. The lab， led by top neuroscientist Edward Chang， has developed a new BCI that translates individual letters instead of whole words or phrases. Users spell out their thoughts， one letter at a time.

主持2019年那项试验的团队，即加州大学旧金山分校的张氏实验室，现在正在尝试一种不同的方法。该实验室由顶尖神经科学家张复伦领导。他们已经开发出一种新的BCI，可以翻译单个字母，而不是整个单词或短语。用户一个字母一个字母地拼写出自己的想法。

The initial results are encouraging. The BCI was able to correctly translate and present about 94 percent of the letters being thought out by participants. The Chang Labs new spelling-BCI could help advance brain implant technology， bringing it closer to everyday use by large numbers of people， and giving a voice to the voiceless.

試验的初步结果令人鼓舞。该BCI能够正确翻译并呈现参与者想出的约94%的字母。张氏实验室的这个新型拼写BCI有助于推动大脑植入技术的发展，使其向大规模日常应用迈进一步，让无声者得以发声。

The Chang Lab made headlines four years ago when it demoed its BrainNet BCI. In the experiment， two volunteers wore electroencephalogram electrodes on their heads—the kind neurologists use to detect epilepsy. Unlike older， cruder BCIs， BrainNet did not require invasive surgery to implant sensors dir-ectly into the brain.

4年前，张氏实验室因演示其基于“大脑网络”技术的BCI而登上头条。在当时的试验中，两名志愿者头戴脑电图电极，就是神经学家用来检查癫痫的那种电极。与较粗糙的老式BCI不同，“大脑网络”技术不需要通过侵入性外科手术将传感器直接植入大脑。

The volunteers silently concentrated on certain simple thoughts. The EE headsets detected their brain waves through their skulls， and an algorithm matched these waves to a “dictionary” of phrases the lab had written by asking volunteers to utter phrases， then recording the resulting neurological activity.

志愿者们默默地专注于某些简单的想法。脑电耳机透过他们的头骨探测脑电波，再由一种算法将这些脑电波与一本“词典”中的短语进行比对。这本“词典”是实验室提前编写好的，编写方法是让志愿者说出短语，然后记下由此产生的神经活动。

That BrainNet worked at all was impressive. But its 76-percent peak accuracy left a lot of room for improvement. “A major challenge for these approaches is achieving high single-trial accuracy rates，” Chang and his team conceded.

“大脑网络”技术能起到作用已经令人印象深刻，但其76%的峰值准确率仍有很大的进步空间。张复伦及其团队承认：“这些方法面临的一个主要挑战就是在单次试验中达到较高的准确率。”

Spelling out thoughts one letter at a time would certainly be slower than feeding whole thoughts into a BCI， but could it be more accurate？ To find out， the Chang Lab recruited a volunteer who， back in 2019， had an electrocor-ticography array—a postcard-size patch of 16 electrodes—implanted under his skull. The volunteer suffers from “severe limb and vocal-tract paralysis，” according to the lab.

一個字母一个字母地拼写出想法肯定比把整个想法输入BCI要慢，但前者会更准确吗？为了得到答案，张氏实验室招募了一名志愿者——早在2019年，这名志愿者颅内就植入了一个明信片大小、包含16个电极的脑皮层电极阵列芯片。张氏实验室称，这名志愿者患有“严重的肢体和声道麻痹”。

Chang and his teammates， including UCSF neuroscientists Sean Metzger and David Moses， taught the subject the NATO phonetic alphabet. They instructed the volunteer to spell out thoughts by thinking of each letters NATO code word.

张复伦和他的团队成员，包括加州大学旧金山分校的神经科学家肖恩·梅茨格和戴维·摩西，一起教受试志愿者北约音标字母。他们让受试志愿者在脑子里想出每个字母对应的北约音标代码，以此拼出想法。

The BCI read the brain waves. An algorithm did its best to match the waves to a 1，152-word dictionary. Thoughts—at least， the algorithms best translation of ones thoughts—scrolled across a computer screen at a rate of 29 letters per minute.

BCI读取受试志愿者的脑电波，再由一种算法尽力将其脑电波与一本“词典”中的1152个单词进行比对。想法，或者说至少是算法对想法的最佳翻译，以每分钟29个字母的速度在电脑屏幕上滚动出现。

The system was pretty accurate. During both instances when the subject thought， “Thank you，” the translated text came out onscreen as， well， “thank you.”

该系统的正确率比较高。受试志愿者有两次想的是thank you（谢谢你），翻译后的文本在屏幕上显示出来的就是thank you（谢谢你）。

But it wasnt perfect. “Good morning” came out as “good morning” on the first try and “good for legs” on the second try. And “you are not going to believe this” totally befuddled2 the BCI and its algorithm， getting a garbled translation as “you plan to go in on a bit love this” on the first attempt， and as “ypuaranpdggingloavlinesoeb” on the second attempt.

但该系统并不完美。第一次试验中，good morning（早上好）显示为good morning（早上好），但第二次就显示成good for legs（对腿好）。此外，you are not going to believe this（你不会相信的）这句话完全迷惑了BCI 及其算法，第一次翻译出来的文本是一句含糊不清的you plan to go in on a bit love this（你打算参与其中有一点爱这个），第二次则显示出ypuaranpdggingloavlinesoeb。

Overall， the system demonstrated a “median character error rate” of six percent. Scaling up the data for a hypothetical 9，000-word vocabulary， Changs team concluded that the error rate would be only slightly greater： just 8 percent or so.

总的来说，该系统的“字符错误率中位值”为6%。张复伦的团队将数据规模扩大到9000个单词的假设词汇量，得出的结论是错误率只会略高一点，仅为8%左右。

“These results illustrate the clinical viability of a silently controlled speech neuroprosthesis3 to generate sentences from a large vocabulary through a spelling-based approach，” Chang， Metzger， Moses and their co-authors wrote in a peer-reviewed study that was published in Nature Communications.

张复伦、梅茨格、摩西，以及他们的合著者在研究论文中写道：“这些结果说明，无声控制的言语神经假体通过一种基于拼写的方法从大量词汇中生成句子，这在临床上是可行的。”该论文经过同行评审，发表于《自然·通讯》杂志。

Samuel Andrew Hires， a University of Southern California neurobiologist who was not involved with the study， said he was impressed. “A typical human is around 30 to 35 words per minute with modern text prediction， perhaps faster if you are a teenager，” he said. “Here， the subjects were only about six times slower， which is quite impressive considering they couldnt move or speak. Im not sure what my word error rate is on my phone， but it feels like about one in every 10 words， on par with the performance from brain decoding.”

南加州大學的神经生物学家塞缪尔·安德鲁·海尔斯未参与这项研究，但研究成果令他印象深刻。他说：“普通人针对现代文本进行预测的速度大约是每分钟30到35个字，青少年也许会更快。在张氏实验室的试验中，受试志愿者的速度只减慢了大约6倍。考虑到他们既不能移动也不能说话，试验结果令人赞叹。我不确定我使用手机时的单词错误率是多少，但感觉大约每10个单词中就有1个是错的，这与解码大脑的错误率相当。”

But dont expect the spelling approach to change the world overnight. Were still a long way from a tough， fast， accurate and affordable version of a thought-to-text system that a wide var-iety of speech-impaired people can use in public.

但是，不要指望这种拼写方法能在一夜之间改变世界。我们离实现一个耐用、快捷、准确、价格低廉、可供各类言语障碍者在公共场合使用的思想转文字系统，还有很长的路要走。

Durability is an issue. Implanting a device under the skull is traumatic and risky. Ideally， a device will work for many， many years before needing to be repaired or replaced. To that end， its good news that the volunteers electrocorticography array still worked pretty well after 2.5 years， Moses said.

耐用性是一个问题。颅内植入一个设备可引起损伤，而且存在风险。理想情况下，一个设备在需要修理或更换之前可以工作很多很多年。摩西说，在这方面，受试志愿者的脑皮层电极阵列芯片在两年半以后仍然工作得很好，这是一个好消息。

But a lot more experimentation is necessary in order to prove the system is widely effective. “We think that the main thing to confirm is that our BCI can work with a variety of users with a variety of disabilities，” Moses said.

但为了证明该系统的广泛有效性，还需要进行更多的试验。摩西说：“我们认为最需要确认的是我们的BCI可以帮助身患不同残疾的各类用户。”

Only after a lot more testing can any lab—Changs or another—think about licensing the technology for use by the general public. At that point， the challenge will be to shrink it down， toughen it and make it portable—and affordable. Moses said he envisions “a fully implantable neural interface” that can “wirelessly communicate with a phone， tablet or laptop computer to allow port-able use.”

不管是张氏实验室还是其他实验室，只有进行更多的测试后，才能考虑将该技术授权给公众使用。到了那时，研究人员面对的挑战将是如何使BCI變得小巧耐用、便携廉价。摩西说他设想的是“一个完全可植入的神经接口”，可以“与手机、平板电脑或笔记本电脑进行无线通信，以实现便携式使用”。

Offices. Classrooms. Even bars and restaurants. “Brain-computer interfaces have the potential to restore communication，” the Chang team wrote. All those pent-up4 thoughts， rattling around in the brains of anarthric people who can think clearly but say nothing， could come tumbling out. One letter at a time.

设想的BCI应用场景包括办公室、教室，甚至酒吧和餐馆。张复伦的团队写道：“脑机接口能让用户重新与人交流。”对于能清晰思考却什么都说不出来的言语讷吃患者，盘旋在他们大脑中的所有被压抑的想法都可以倾吐出来了，一个字母一个字母地说出来。

（译者为“《英语世界》杯”翻译大赛获奖者）