FACEBOOK’S NEW ARTIFICIAL INTELLIGENCE CAN LEARN SPEECH WITHOUT HUMAN HELP

Speech recognition is an important detail in the artificial intelligence engine. This technology controls the voice assistants in our phones, cars, and smart speakers.

But despite its ubiquity, development is still ongoing. Facebook today announced a major breakthrough. The company has developed a speech recognition system that learns without any human input.

Breakthrough innovation

Modern speech recognition systems are trained on audio recordings of conversations and their text transcripts. These transcripts are handwritten by humans. This is a long and boring work since training artificial intelligence requires a huge amount of educational material.

Facebook’s new system, Wav2vec-U, avoids this. Artificial intelligence learns to recognize speech without any decryption. It is enough to “feed” her an audio recording of the speech and a text written in the same language. Audio and text may not be related to each other in any way. Further, the generative-adversarial network repeatedly “runs” speech samples until it finds a correspondence between sound combinations and words.

This is a truly breakthrough technology that allows you to train AI to recognize even very rare languages. As part of the tests, Facebook engineers taught the system to understand Swahili, Kyrgyz, and Crimean Tatar languages. It took about 10 hours of recorded speech and 3000 lines of text to learn each language.

Why is this needed?

The development allows you to create a speech recognition system for literally every living language on the planet, including the rarest languages ​​of very small peoples. And if the algorithm can translate a language into text on the fly, then it can provide this text with subtitles in another language or simultaneous translation.

In fact, Facebook has almost completely destroyed language barriers. Imagine a world where everyone can understand everyone thanks to a smart gadget with translator software.

Facebook is already gearing up to begin building speech recognition systems for a huge number of languages ​​and dialects around the world.

Related Posts

iPhone 14 Pro and Pro Max have problems while charging

The new iPhone 14 Pro and Pro Max have been found to have serious battery issues. The fact is that they periodically reboot when users put their…

Google recommends updating your Chrome browser

At the end of last week, an urgent update of the Google Chrome browser was released, designed to eliminate a zero-day vulnerability – this is the class…

iPhone 14 Pro was shown in photos and videos

The presentation of the iPhone 14 Pro will take place, most likely, on September 7. Meanwhile, more and more information about the gadget dreamed of by many…

Lenovo Legion Y70 is officially presented

The Lenovo company officially presented its first smartphone on the flagship Qualcomm Snapdragon 8 Plus Gen 1 platform – it was the new gaming Lenovo Legion Y70….

The new low-cost iPad has been put into mass production

ITsider previously reported that the new iPad Pro 2022 with a notch will be equipped with the Apple M2 chipset. And today it became known that Apple…

Vivo Y35 is officially presented

The company Vivo without loud announcements presented a new affordable smartphone Vivo Y35. The model received 44W FlashCharge fast charging (most similar solutions, it should be noted,…

Leave a Reply

Your email address will not be published. Required fields are marked *