This Guy Made His Own Real-Time Translator Because His Colleagues Kept Talking In Mandarin
Cases of colleagues being left out of work conversations because of language barriers are, unfortunately, a common issue in Malaysia.
In a now viral tweet, this guy shared his own personal experience with such colleagues.
On Tuesday, 9 July, Roshen Maghhan tweeted, "About six months ago, I worked at this software development company, and every morning, we'd have a casual meeting about the work.
"But half the time, during the meeting, most of them would converse in Mandarin, and so I'd always be pretty clueless half the time."
Roshen would ask his colleagues to converse in English during meetings, which they acknowledged - but eventually they would continue doing the same thing again
"Despite the amount of times I've I asked them to converse in English, they would acknowledge it, but eventually start conversing in Mandarin again after a while, and I believe its (sic) unintentional, [because] they're very nice," he continued.
"Then I remembered about the Google Pixel Buds, and how it's probably the tech solution to bridge the gap between language barriers," Roshen continued
He included a video that showed how the Google Pixel Buds - a pair of wireless earbuds that allow you to translate languages in real time, among other things - works:
Unfortunately, a pair of the wireless earbuds would cost close to RM800.
So Roshen put his skills to the test and, in his own words, built "the damn thing" himself.
Breaking down Roshen's tweets, for this project he needed:
- Google Pixel Buds' hardware information, obtained from the United States' Federal Communications Commission,
- Google Translate API (purchased),
- ResponsiveVoice API (voice synthesiser), and
- earphones with a microphone.
The result? A real-time language translator, based on the web and able to work on every platform.
Earlier in the thread, the developer said he wanted to make sure that the programme will be able to work on every platform, including Android, iOS, and Desktop, which is why he made it web-based.
"Also, I wanna make sure it's able to work with any earphone wired or wireless, as long as it has a microphone."
Roshen did not stop there either, as he even added in a few more tweaks so that the programme could differentiate voices and highlight topics that are being discussed
Roshen shared that he added the ability to differentiate voices, known as 'voice diarisation', so that even deaf people can be involved in the conversation.
"This way, you can just put your device on the table, and it'll immediately create a transcript of the entire conversation going on in your vicinity and in real time," he explained, adding that he developed the voice recognition and diarisation algorithms himself.
Further down the thread, he added, "Then, again, I was like why stop here.... [S]o I made it more informative, using machine learning, it checks every word in the convo, and if the word is a topic, it gets highlighted.
"And when you click the highlighted word, it'll give you information about that topic."
Ending his thread, Roshen said that "modern day problems require modern day solutions"
He cheekily added, "Now you can talk shit about me in any language and I'll still understand, and I can finally day dream during a convo and still stay in the loop."
Mad impressive skills, Roshen!