戴維·阿克斯　俞月圓/譯

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.

言語訥吃，即喪失言語能力的疾病?；忌洗瞬〉囊淮蟊瘎≡谟?，許多患者仍然能夠清晰地思考，只是不能像我們大多數(shù)人一樣用語言表達自我。如果他們同時還癱瘓了，不能在平板電腦上打出他們的想法，情況就愈加凄慘。

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.

多年來，科學(xué)家們一直試圖通過技術(shù)幫助言語訥吃患者，特別是其中癱瘓的患者，幫他們開口說話。最新的方法是在言語訥吃患者的大腦中或大腦附近植入設(shè)備，直接讀取構(gòu)成他們思想的電脈沖，并將文本傳送到一個可以顯示或者念出該文本的設(shè)備上。

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.

這些腦機接口（或稱BCI）變得越來越精密，但準確度仍然是一個很大的問題。在4年前的一項重要試驗中，一個頂級BCI原型誤譯了大約1/4試驗參與者的想法。

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.

換句話說，用戶想到的短語里，每隔3組就會在屏幕上顯示出1組錯誤短語。這幾乎就像你寫來往電子郵件時，每寫完3行，第4行就會被自動改寫為胡言亂語。

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年那項試驗的團隊，即加州大學(xué)舊金山分校的張氏實驗室，現(xiàn)在正在嘗試一種不同的方法。該實驗室由頂尖神經(jīng)科學(xué)家張復(fù)倫領(lǐng)導(dǎo)。他們已經(jīng)開發(fā)出一種新的BCI，可以翻譯單個字母，而不是整個單詞或短語。用戶一個字母一個字母地拼寫出自己的想法。

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.

試驗的初步結(jié)果令人鼓舞。該BCI能夠正確翻譯并呈現(xiàn)參與者想出的約94%的字母。張氏實驗室的這個新型拼寫B(tài)CI有助于推動大腦植入技術(shù)的發(fā)展，使其向大規(guī)模日常應(yīng)用邁進一步，讓無聲者得以發(fā)聲。

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，張氏實驗室因演示其基于“大腦網(wǎng)絡(luò)”技術(shù)的BCI而登上頭條。在當(dāng)時的試驗中，兩名志愿者頭戴腦電圖電極，就是神經(jīng)學(xué)家用來檢查癲癇的那種電極。與較粗糙的老式BCI不同，“大腦網(wǎng)絡(luò)”技術(shù)不需要通過侵入性外科手術(shù)將傳感器直接植入大腦。

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.

志愿者們默默地專注于某些簡單的想法。腦電耳機透過他們的頭骨探測腦電波，再由一種算法將這些腦電波與一本“詞典”中的短語進行比對。這本“詞典”是實驗室提前編寫好的，編寫方法是讓志愿者說出短語，然后記下由此產(chǎn)生的神經(jīng)活動。

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.

“大腦網(wǎng)絡(luò)”技術(shù)能起到作用已經(jīng)令人印象深刻，但其76%的峰值準確率仍有很大的進步空間。張復(fù)倫及其團隊承認：“這些方法面臨的一個主要挑戰(zhàn)就是在單次試驗中達到較高的準確率?！?/p>

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.

一個字母一個字母地拼寫出想法肯定比把整個想法輸入BCI要慢，但前者會更準確嗎？為了得到答案，張氏實驗室招募了一名志愿者——早在2019年，這名志愿者顱內(nèi)就植入了一個明信片大小、包含16個電極的腦皮層電極陣列芯片。張氏實驗室稱，這名志愿者患有“嚴重的肢體和聲道麻痹”。

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.

張復(fù)倫和他的團隊成員，包括加州大學(xué)舊金山分校的神經(jīng)科學(xué)家肖恩·梅茨格和戴維·摩西，一起教受試志愿者北約音標字母。他們讓受試志愿者在腦子里想出每個字母對應(yīng)的北約音標代碼，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讀取受試志愿者的腦電波，再由一種算法盡力將其腦電波與一本“詞典”中的1152個單詞進行比對。想法，或者說至少是算法對想法的最佳翻譯，以每分鐘29個字母的速度在電腦屏幕上滾動出現(xiàn)。

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

該系統(tǒng)的正確率比較高。受試志愿者有兩次想的是thank you（謝謝你），翻譯后的文本在屏幕上顯示出來的就是thank you（謝謝你）。

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.

但該系統(tǒng)并不完美。第一次試驗中，good morning（早上好）顯示為good morning（早上好），但第二次就顯示成good for legs（對腿好）。此外，you are not going to believe this（你不會相信的）這句話完全迷惑了BCI 及其算法，第一次翻譯出來的文本是一句含糊不清的you plan to go in on a bit love this（你打算參與其中有一點愛這個），第二次則顯示出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.

總的來說，該系統(tǒng)的“字符錯誤率中位值”為6%。張復(fù)倫的團隊將數(shù)據(jù)規(guī)模擴大到9000個單詞的假設(shè)詞匯量，得出的結(jié)論是錯誤率只會略高一點，僅為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.

張復(fù)倫、梅茨格、摩西，以及他們的合著者在研究論文中寫道：“這些結(jié)果說明，無聲控制的言語神經(jīng)假體通過一種基于拼寫的方法從大量詞匯中生成句子，這在臨床上是可行的?！痹撜撐慕?jīng)過同行評審，發(fā)表于《自然·通訊》雜志。

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(xué)的神經(jīng)生物學(xué)家塞繆爾·安德魯·海爾斯未參與這項研究，但研究成果令他印象深刻。他說：“普通人針對現(xiàn)代文本進行預(yù)測的速度大約是每分鐘30到35個字，青少年也許會更快。在張氏實驗室的試驗中，受試志愿者的速度只減慢了大約6倍?？紤]到他們既不能移動也不能說話，試驗結(jié)果令人贊嘆。我不確定我使用手機時的單詞錯誤率是多少，但感覺大約每10個單詞中就有1個是錯的，這與解碼大腦的錯誤率相當(dāng)?！?/p>

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，不要指望這種拼寫方法能在一夜之間改變世界。我們離實現(xiàn)一個耐用、快捷、準確、價格低廉、可供各類言語障礙者在公共場合使用的思想轉(zhuǎn)文字系統(tǒng)，還有很長的路要走。

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.

耐用性是一個問題。顱內(nèi)植入一個設(shè)備可引起損傷，而且存在風(fēng)險。理想情況下，一個設(shè)備在需要修理或更換之前可以工作很多很多年。摩西說，在這方面，受試志愿者的腦皮層電極陣列芯片在兩年半以后仍然工作得很好，這是一個好消息。

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.

但為了證明該系統(tǒng)的廣泛有效性，還需要進行更多的試驗。摩西說：“我們認為最需要確認的是我們的BCI可以幫助身患不同殘疾的各類用戶?！?/p>

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.”

不管是張氏實驗室還是其他實驗室，只有進行更多的測試后，才能考慮將該技術(shù)授權(quán)給公眾使用。到了那時，研究人員面對的挑戰(zhàn)將是如何使BCI變得小巧耐用、便攜廉價。摩西說他設(shè)想的是“一個完全可植入的神經(jīng)接口”，可以“與手機、平板電腦或筆記本電腦進行無線通信，以實現(xiàn)便攜式使用”。

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.

設(shè)想的BCI應(yīng)用場景包括辦公室、教室，甚至酒吧和餐館。張復(fù)倫的團隊寫道：“腦機接口能讓用戶重新與人交流。”對于能清晰思考卻什么都說不出來的言語訥吃患者，盤旋在他們大腦中的所有被壓抑的想法都可以傾吐出來了，一個字母一個字母地說出來。

（譯者為“《英語世界》杯”翻譯大賽獲獎?wù)撸?/p>