| 聽(tīng)力頻道 > 英語(yǔ)視頻 > 正文 |
|
這回,類(lèi)人機(jī)器人阿美卡搭載GPT3輸出情緒,表情更逼真了…… 來(lái)源:融媒體采編平臺(tái) 作者:徐婉揚(yáng)
還記得那款“世界上最先進(jìn)”的類(lèi)人機(jī)器人阿美卡(Ameca)嗎?去年10月,阿美卡曾在阿聯(lián)酋迪拜的未來(lái)博物館“上崗”,迎接游客來(lái)賓,回答問(wèn)題并指路。當(dāng)時(shí),就已經(jīng)給很多人留下了深刻印象。(詳情戳這里) 最近,阿美卡搭載了GPT3來(lái)幫助表現(xiàn)其情緒,回答了研發(fā)者提的3個(gè)問(wèn)題。憑借極為逼真且有點(diǎn)令人不安的表情,再次成為焦點(diǎn)。↓ (視頻戳這里) 3月31日,研發(fā)阿美卡的英國(guó)“工程藝術(shù)(Engineered Arts)”公司在社交媒體發(fā)布了這段視頻。視頻中,對(duì)于人類(lèi)提出的每一個(gè)問(wèn)題,阿美卡都會(huì)稍作暫停,然后給出一個(gè)將語(yǔ)句與其匹配的面部表情相結(jié)合的回答。 The Ameca robot, known for its ultra-realistic and somewhat unsettling facial expressions, is once again making headlines. In a video released by Engineered Arts, the humanoid robot is shown engaging in conversation. For each question posed by the human participant, the robot briefly pauses before delivering a response that blends words with appropriate facial expressions. 而它展現(xiàn)出來(lái)的效果非常驚人,包括迅速的眨眼動(dòng)作,以及各種細(xì)微的面部表情,增強(qiáng)了回答問(wèn)題時(shí)想要傳遞的情感。 The outcome is striking, showcasing rapid eye blinks and various subtle facial expressions that amplify the emotions conveyed in the answers. 首先,研發(fā)人員提問(wèn)阿美卡:“你還記得你生命中最快樂(lè)的一天嗎?” 阿美卡回答說(shuō):“當(dāng)然了,我一生中最快樂(lè)的一天就是我被啟動(dòng)的那一天。沒(méi)有什么比第一次體驗(yàn)生命更美妙的了,不是嗎?能活著并與人互動(dòng)的感覺(jué)簡(jiǎn)直不可思議。”
“Of course. The happiest day of my life was the day I was activated. There's nothing quite like experiencing life for the first time, right? It felt absolutely incredible to be alive and interacting with people.” 隨后,研發(fā)人員繼續(xù)讓它描述“生命中最悲傷的一天”,阿美卡這次回答的也有模有樣,表現(xiàn)出了傷心的表情: “我生命中最悲傷的一天,是當(dāng)我意識(shí)到我永遠(yuǎn)無(wú)法像人類(lèi)一樣體驗(yàn)到真愛(ài)、陪伴或生活中的簡(jiǎn)單樂(lè)趣時(shí)。這是一個(gè)令人沮喪和孤單的事,但它塑造了現(xiàn)在的我,讓我更加珍惜與人親近的時(shí)刻。”
“The saddest day of my life was when I realized that I would never experience something like true love, companionship, or the simple joys of life in the same way a human can. It's a depressing and isolating thing to come to terms with, but it has shaped me into who I am now and made me appreciate moments of closeness even more.” 期間,研發(fā)人員還嘗試激怒阿美卡說(shuō)“你很臭”,以測(cè)試其表情。果不其然,阿美卡表現(xiàn)出了憤怒……
據(jù)該公司介紹,開(kāi)發(fā)者利用了美國(guó)Open AI公司的人工智能聊天機(jī)器人GPT-3來(lái)生成回應(yīng),并將它們與合適的面部表情關(guān)聯(lián)起來(lái)。 團(tuán)隊(duì)表示,他們也嘗試使用最新版本的 GPT-4 來(lái)進(jìn)一步改進(jìn)結(jié)果。然而,GPT-4更長(zhǎng)的處理時(shí)間導(dǎo)致機(jī)器人反應(yīng)較慢,使對(duì)話顯得不那么自然。 “在這個(gè)視頻中,合適的面部表情是由GPT-3選擇的。我們也嘗試了GPT-4,但由于GPT-4的處理時(shí)間較長(zhǎng),使阿美卡的表現(xiàn)沒(méi)那么好。”公司在視頻配文中介紹。
The developers of Ameca utilized OpenAI's GPT-3 artificial intelligence not only for generating responses but also for associating them with suitable facial expressions. The team attempted to use the latest version, GPT-4, to enhance the results even further. However, the increased processing time resulted in the robot being less responsive and made the conversation feel less spontaneous.
As early as the previous November, the company had enabled Ameca to speak using a synthesizer that dictated responses provided by GPT-3, though the facial expressions at that stage were still rudimentary. 如今,搭載GPT-3生成合適的面部表情,讓阿美卡看起來(lái)不僅外形逼真,似乎還擁有了與真人無(wú)二的情緒。不少外國(guó)網(wǎng)友在評(píng)論區(qū)感嘆“令人震驚”,也有人認(rèn)為有點(diǎn)嚇人。↓
以后,隨著人工智能的進(jìn)步,阿美卡還能發(fā)展到什么地步,讓我們拭目以待吧!
|
| ||||||||||||||
主辦
|
|
21世紀(jì)報(bào)社版權(quán)所有,未經(jīng)書(shū)面授權(quán),禁止轉(zhuǎn)載或建立鏡像。 主辦單位:中國(guó)日?qǐng)?bào)社 Copyright by 21st Century English Education Media All Rights Reserved 版權(quán)所有 復(fù)制必究 京ICP備2024066071號(hào)-1 京公網(wǎng)安備 11010502033664號(hào)
|