新湖畔网 （随信APP) | 智能眼镜的这个功能被忽视了，但现在已经成为必不可少的。

新湖畔网 （随信APP) | 智能眼镜的这个功能被忽视了，但现在已经成为必不可少的。
【微信/公众号/视频号/抖音/小红书/快手/bilibili/微博/知乎/今日头条同步报道】

字幕，已经成了现代人的「外挂」。通勤嘈杂，摸鱼易露馅，学习会分心，听和看并用，才能避免进度条白白走了冤枉路。

然而，对一些人来说，字幕不只是锦上添花。

当《失控玩家》的男主角戴上眼镜，他看到了原本无法察觉的信息，不再是个被动的 NPC。

现实里也存在一种智能眼镜，可以提供「行走的弹幕」。尽管没那么科幻，但它同样通向一个信息量更大的世界。

我可以看到你说的话了

科技的意义在于，当上帝关上一道门的时候，打开一扇窗。

一位听障博主的开箱视频，在 TikTok 拿下了 80 万点赞，夙愿得偿，喜极而泣，最纯粹的情感迸发的力量，打动了素昧平生的观众。

她手里拿着一个盒子，边笑边流泪，比着手语，努力地说出完整的句子：「我等待这个盒子里的技术很多年了。」

盒子里装的是一款字幕眼镜，外形和普通眼镜没什么两样，却让她可以「看到」周围的声音，那些过去听不清的声音，变成了一行行亮绿色的、科幻感的字幕。

根据视频里的信息，这位博主用的眼镜叫作 Hearview，专为听障人士设计，今年 5 月发布，来自国内的一家科技公司，但不面向国内，市场在海外。

它可以用来娱乐，看电影、看视频、看《黑神话：悟空》的游戏直播。

从刷《老友记》的体验视频来看，文本略有些滞后但准确，配对的手机 app 还可以区分不同的说话人。

同时，它也可以用在面对面的对话，方便听障人士在餐厅点餐、在超市购物、和导购聊天、开车时导航……

HearView 的原理说起来并不复杂，和手机 app 配对，通过智能手机的麦克风捕获声音，AI 算法实时语音转文字，字幕显示在眼镜上。

如果听障人士需要回复他人，可以在 app 输入消息，将文字转换成语音。过往的字幕，也保存在 app 中。

HearView 自称，语音转文字的准确性达到 95%，最远转录 10 米外的语音。说到这里，一个问题呼之欲出：菜市场等吵闹环境里表现会变差吗？

虽然 HearView 表示手机 app 具备噪音消除功能，但我翻遍了各种体验视频，并没有找到嘈杂环境里的实测，所以很难探究效果如何。

官网只提到了一些参数信息，续航 7 小时，重 52 克，适合全天佩戴，还配备了振动和视觉警告，提醒用户注意可能的危险。

轻便，耐用，听起来让人很想剁手，但它实在太贵，很难交个朋友——1799 美元，约 12800 元人民币。

而且，Hearview 存在很大的进步空间，目前它只支持英语和西班牙语，计划支持德语和法语，还不能实现语言的互相翻译。

文本的颜色只有亮绿色，虽然确保了在各种屏幕和照明条件下都可读，然而用户没有选择，就是美中不足。

但存在，便意味着价值。字幕早已是很多人生活的一部分，这还不够，它理应以更方便、直观的形式，陪伴在最需要的人左右。

字幕眼镜虽多，但生活里的挑战更多

实时字幕眼镜，其实并非新鲜事，放在 2 年前，甚至是一个热潮，诞生过不少有趣的项目，但都很难尽善尽美。

英国 AR 初创公司 XRAI，开发了兼容多款 AR 眼镜的语音转文字应用 XRAI Glass。

然而，《连线》杂志记者戴上一款和 XRAI Glass 兼容的 AR 眼镜后发现，语音转文字固然好，但使用过程中，总有这样那样的摩擦。

先是使用体验上的，如果佩戴人工耳蜗和助听器，再戴眼镜可能会不舒服，虽然这款 AR 眼镜已经很轻，但和普通眼镜相比依然厚重。

而且，语音转文字在背景噪音大和多人讲话的时候，效果并不好，实用性大打折扣。

价格也是一个问题，300 多美元的 AR 眼镜已经让钱包隐隐作痛，XRAI Glass 还需要每月花几十美元订阅套餐，像很多语音转文字的软件那样，只能说并不意外。

国内也有类似 Hearview 的产品——亮亮视野的听语者字幕眼镜，分为助听版和翻译版，可以理解普通话、方言和外语，并且支持跨语种翻译。

它的使用方式和 Hearview 相近，下载可译 app，眼镜和手机进行蓝牙配对，用 Wi-Fi 或者热点连接网络，手机端实时语音转文本，眼镜端显示文本。

不过有用户在 App Store 反馈，听语者对方言的支持还是不够多。这是一个非常必要、却也艰难的优化方向，听力不好、习惯说方言的老年人，恰恰最需要这类产品。

也有 YouTube 博主评测发现，听语者的语音识别率高，速度也快，但口音很重的话，识别率会变低。

如果不拘泥于眼镜的形态，耶鲁大学和斯坦福大学的学生设计的一个产品原型很有意思，叫作 Transcribe Glass。

它不是一副眼镜，而是一个平视显示器，可以卡在眼镜的镜框上，开箱即用，将设备连接到 iOS 和 Android 的配套 app，让用户选择自己喜欢的语音转文本软件。

生成的字幕会通过低功耗蓝牙传输到设备，并实时叠加在用户的现实视野中。难得的是定价也格外友好，95 美元，但连测试版都还在候补，直到现在也查不到落地的信息。

除了专注语音转文字的产品，面向所有人的多功能 AR 智能眼镜，往往也包含了字幕功能。

国内价位在两三千的一体化无线智能眼镜，基本都支持语音转文字和多种语言的实时翻译，但转译效率，可能不如专为听障人士打造的 AR 眼镜，持续开着语音转文字时，续航也是一个问题。

当我咨询某个头部的智能眼镜品牌，得到的答案是「不建议听障人士使用」。

其实，这种产品最适合大厂出手，特别是 Google，在语音识别、机器翻译和 AR 方面都有深厚的技术积累，实时语音转文字和翻译的能力都遥遥领先。

Google 在 2022 年 I/O 推出了一款可以实时翻译的 AR 眼镜，支持 24 种语言，甚至支持美国手语，字幕就在对话人旁边，不过也只是原型演示，没有下文了。

科技向善是字幕眼镜的大前提，种种的「吹毛求疵」，其实是抱着殷切的心情，希望产品不满现状，不断进化，再做一次，再改进一次，变得更好一点。

字幕是一种权利，像看电影一样看世界

世界卫生组织统计，全球约有 4.66 亿人患有听力损失，其中超过 900 万人为重度耳聋。

即使使用了人工耳蜗或助听器，听障人士理解别人在说什么，仍然需要集中注意力，同时，一些发音相近的词语，光靠唇读难以区分，在理想条件下，英语中只有约 40% 的语音信息，能通过说话者的唇部动作捕捉。

这也是为什么，一个听力障碍的世界，需要文字作为补充。很早之前，就有人为之努力了。

古巴裔美国默片演员艾默生·罗梅罗，同时也是一位听障人士，在 1947 年开创了有声电影的字幕。

默片时代，

英文版:

Subtitles have become a "cheat code" for modern people. During the commute, in noisy environments, or while slacking off, subtitles help to prevent distractions and keep the focus on both listening and watching to avoid wasted time.

However, for some people, subtitles are more than just an enhancement.

When the protagonist in "Ready Player One" puts on his glasses, he sees information that was previously unnoticed, no longer a passive NPC.

In reality, there are smart glasses that provide a "walking barrage". Although not as futuristic, they also lead to a world with more information.

### I Can See What You're Saying

The significance of technology lies in opening a window when God closes a door.

A TikTok unboxing video by a hearing-impaired blogger garnered 800,000 likes, fulfilling a long-standing wish and moving strangers with pure emotions.

Holding a box, smiling and crying, using sign language, she speaks out a complete sentence: "I have been waiting for the technology in this box for many years."

The box contains a pair of subtitle glasses, similar in appearance to regular glasses, but allowing her to "see" the surrounding sounds. Those previously incomprehensible sounds now appear as bright green, sci-fi subtitles.

According to the video, the glasses she uses are called Hearview, designed for the hearing-impaired, released in May of this year by a domestic tech company, but not targeted at the domestic market, focusing on overseas markets.

It can be used for entertainment, watching movies, videos, and live streaming of games like "Goddess of Myth: Wukong".

From the experience video of watching "Friends", the text is slightly delayed but accurate, and the paired mobile app can also differentiate between different speakers.

Additionally, it can be used in face-to-face conversations, making it convenient for the hearing-impaired to order at restaurants, shop at supermarkets, chat with salespeople, navigate while driving, and more.

The principle of Hearview is not complicated - paired with a mobile app, capturing sound through the smartphone's microphone, an AI algorithm for real-time speech-to-text conversion, and displaying subtitles on the glasses.

If the hearing-impaired person needs to reply to others, they can input messages in the app, converting text to speech. Past subtitles are also saved in the app.

Hearview claims an accuracy of 95% in speech-to-text conversion and can transcribe voices up to 10 meters away. A question arises - will its performance be affected in noisy environments like markets?

Although Hearview states that the mobile app has noise cancellation, I couldn't find real-world tests in noisy environments in various experience videos, making it difficult to assess its effectiveness.

The official website only mentions some parameter information - 7 hours of battery life, weighing 52 grams, suitable for all-day wear, with vibration and visual warnings to alert users of potential hazards.

Lightweight, durable, sounds tempting to buy, but it's too expensive, making it hard to afford - $1799, approximately 12800 Chinese Yuan.

Furthermore, Hearview still has a lot of room for improvement. Currently, it only supports English and Spanish, plans to support German and French, and cannot achieve mutual language translation.

The text color is only bright green, ensuring readability on various screens and lighting conditions, but lack of user choice is a drawback.

However, existing products mean value. Subtitles have long been part of many people's lives and should accompany those who need it in a more convenient and intuitive form.

### Challenges Outweigh the Subtitle Glasses

Real-time subtitle glasses are not a new concept. A few years ago, they even sparked a trend with several interesting projects but struggled to achieve perfection.

A UK AR startup, XRAI, developed the XRAI Glass app for voice-to-text compatible with multiple AR glasses.

However, a journalist from "Wired" magazine encountered various frictions while using AR glasses compatible with XRAI Glass - discomfort when wearing cochlear implants and hearing aids along with the glasses, despite the AR glasses being lightweight, they are still bulkier compared to regular glasses.

In addition, in noisy backgrounds and multi-person conversations, the effectiveness of voice-to-text is reduced, significantly impacting its practicality.

Price is also an issue - the $300 AR glasses are already a pain on the wallet, adding a monthly subscription package on XRAI Glass, similar to many other voice-to-text software, was not surprising.

In China, there is a product similar to Hearview - Liangliang Vision's Listen Speaker subtitle glasses, available in both hearing aid and translator versions, capable of understanding Mandarin, dialects, and foreign languages, supporting cross-language translation.

Its usage is similar to Hearview, downloading the CanTranslate app, pairing the glasses with a smartphone via Bluetooth, connecting to the network with Wi-Fi or a hotspot, real-time speech-to-text on the mobile end, and text display on the glasses end.

However, some feedback on the App Store indicates that Listen Speaker lacks sufficient support for dialects. This is a necessary but challenging optimization, especially for elderly people with hearing difficulties who are accustomed to speaking dialects and need such products the most.

A YouTube reviewer found that Listen Speaker has a high speech recognition rate and speed, but recognition drops with heavy accents.

If not restricted to the form of glasses, a product prototype designed by students from Yale and Stanford University is interesting - Transcribe Glass.

It is not a pair of glasses but a heads-up display that can be clipped onto glasses' frames, connected to the iOS and Android app, allowing users to select their preferred speech-to-text software.

The generated subtitles are transmitted via low-power Bluetooth to the device and overlaid in real-time on the user's field of vision. Impressively, it is priced at $95, but even the beta version is still on hold, with no information on its availability.

In addition to specialized voice-to-text products, multipurpose AR smart glasses for everyone often include subtitle features.

Integrated wireless smart glasses in China, priced between two to three thousand, generally support real-time translation in multiple languages but may not match the efficiency of AR glasses designed specifically for the hearing-impaired, with battery life becoming an issue during continuous speech-to-text usage.

When I inquired with a leading smart glasses brand, I was advised "not recommended for the hearing-impaired."

Ideally, such products are best suited for major companies, especially Google, with deep technical expertise in voice recognition, machine translation, and AR, leading in real-time speech-to-text and translation capabilities.

At the 2022 I/O event, Google unveiled AR glasses capable of real-time translation, supporting 24 languages, even American Sign Language, with subtitles displayed next to the speakers - although just a prototype demonstration, there have been no further updates.

The premise of subtitle glasses is benevolent technology. The various criticisms are actually hopeful concerns, expecting products to evolve, improve, and become better.

### Subtitles are a Right - See the World Like Watching a Movie

The World Health Organization estimates that globally, around 466 million people have hearing loss, with over 9 million being severely deaf.

Even with cochlear implants or hearing aids, understanding what others say requires focused attention. Additionally, similar-sounding words are hard to discern by lip-reading alone. In ideal conditions, only about 40% of spoken information in English can be captured through lip movements.

This is why a world with hearing impairments needs text as a supplement. Long ago, efforts were made for this.

Emerson Romero, a Cuban-American silent film actor who was also hearing-impaired, pioneered subtitles for talking movies in 1947.

During the silent film era, audiences could understand the story through film footage and inserted text, but with the rise of sound movies, many hearing-impaired viewers like him lost the opportunity to watch movies because they couldn't hear the dialogues and there were no subtitles.

As a result, Romero decided to manually create subtitles: at the time, movies were played on film reels, so he would slice the film and insert images with subtitles between the frames.

Subsequent subtitle technology can be seen as an extension of Romero's spirit, and more convenient designs have emerged to help the hearing-impaired watch movies, such as some U.S. cinemas offering pre-made subtitle glasses.

In 2012, Sony introduced CC subtitle glasses for select cinemas - unlike regular subtitles, CC subtitles include not only dialogue but also non-verbal information like background music, sound effects, and ambient sounds.

These glasses feature small projectors on each side, and the green subtitles appear as if floating in front of the big screen.

Audiences can clearly see the subtitles regardless of where they sit in the theater. Users can adjust the brightness, display distance, and angle of subtitles and switch between six languages.

This glasses even support 3D, so users don't have to carry an extra pair of glasses to watch a 3D movie. This is important to avoid a situation where you have to wear regular glasses, 3D glasses, and CC subtitle glasses all at once while watching a movie.

This scene is somewhat ironic but serves as a metaphor - to understand the world from a different perspective, some people always have to put in more effort.

The real-time subtitle glasses, although not perfect, offer glimpses of a better future, showing a positive possibility.

South Korean film director Bong Joon-ho said at the Oscars, "Once you overcome the 1-inch tall barrier of subtitles, you will be introduced to so many more amazing films."

With subtitles commonly seen in movies now entering our lives, they provide additional information to those who need them, granting them the right to stay engaged in conversations.

A line from Google's translation AR glasses ad is inspiring: "I gaze into your eyes, and you seem to be looking right into mine."

Almost unobtrusive is the best state of technology.

Under the condition of high efficiency and accuracy, communication can return to a natural state - hands-free, no need to look down on phones, no need to constantly stare at lips, but face-to-face, eye contact, as it has been for thousands of years.


智能眼镜这个被忽略的功能，他们已经离不开了
#智能眼镜这个被忽略的功能他们已经离不开了

关注流程：打开随信App→搜索新湖畔网随信号：973641 →订阅即可！

 

公众号：新湖畔网    抖音：新湖畔网

视频号：新湖畔网    快手：新湖畔网

小红书：新湖畔网    随信：新湖畔网

百家号：新湖畔网    B站：新湖畔网

知乎：新湖畔网      微博：新湖畔网

UC头条:新湖畔网      搜狐号：新湖畔网

趣头条：新湖畔网    虎嗅：新湖畔网

腾讯新闻：新湖畔网    网易号：新湖畔网

36氪：新湖畔网      钛媒体：新湖畔网

今日头条：新湖畔网    西瓜视频：新湖畔网