The Limited Times

Now you can see non-English news...

VALL-E, artificial intelligence capable of imitating any voice after listening to a 3-second audio


It is a technology developed by Microsoft. How to test it.

As the sophistication of


grows and the debate on artificial intelligence intensifies,


is in the midst of developing its own technology.

This is 


and he has the ability to

learn and imitate any voice

just by taking a three-second recording as an example. 

The company founded by Bill Gates is also working on projects to add

the chat developed by OpenAI ChatGPT

to its browsers and to the Office suite, according to several US media outlets.

Among others,

Word, PowerPoint and Outlook

would be integrated .

It also plans to use it in its


search engine and thus enter into competition with Google.

How is VALL-E, Microsoft's artificial intelligence

The VALL-E model.

The Redmond technology giant presented its AI project


, a Text-to-Speech (TTS) language model capable of synthesizing text to transform it into speech.

“Specifically, we trained a neural codec language model using discrete codes derived from an out-of-the-box neural audio codec model, and considered TTS as a conditional language modeling task rather than continuous signal regression as in work. above”, explains the company on its website.

The machine is thoroughly prepared


During the run-up, TTS training data at 60,000 hours of English speaking was entered, “hundreds of times larger than existing systems.”

The novelty of this technology developed by Microsoft is

its ability to learn

in context, which, through audio recordings of just three seconds, is capable of imitating the voices of these recordings.

“VALL-E emerges in-context learning capabilities and can be used to synthesize high-quality personalized speech with just a three-second recorded recording of an invisible speaker as an acoustic prompt,” they said.

The American multinational is very satisfied with the results, understanding that they "significantly exceed the latest generation TTS system in terms of speech naturalness and speaker similarity."

Its developers also point out that the samples taken suggest that VALL-E could "preserve the emotion of the speaker and the acoustic environment of the message".

The Redmond giant points everything to AI.

(Photo: Reuters)

The news does not end here.

VALL-E is that it is being developed to work with "other generative AI models", such as GPT-3.

In the not too distant future, this feature offers possibilities to integrate VALL-E into other technologies such as ChatGPT.

In the same vein as Microsoft, other industry giants have also entered the field of these smart technologies. 

Meta (Facebook) researchers recently developed a program named Cicero, after the Roman statesman Cicero.

The software tested Diplomacy, a board game that requires participants to display their negotiating talents.

"If you don't speak like a real person - showing empathy, building relationships and speaking correctly - you won't be able to forge alliances with other players," the social media giant explained in a statement.

, a startup founded by former Google engineers, put an experimental chatbot online in October that can take on any personality.

Users create characters based on a short description and can then "chat" with a fake Sherlock Holmes, Socrates or even Donald Trump.

This degree of sophistication fascinates, but also worries many observers with the idea that these technologies are not used to deceive humans, spreading false information, for example, or creating increasingly credible scams.


look also

Microsoft wants to integrate the artificial intelligence of ChatGPT into its programs: prepares a million-dollar offer

The best free courses from Google to train in the digital world and improve your CV: how to enroll

Source: clarin

All tech articles on 2023-01-13

You may like

Life/Entertain 2023-01-30T15:41:33.012Z

Trends 24h


© Communities 2019 - Privacy

The information on this site is from external sources that are not under our control.
The inclusion of any links does not necessarily imply a recommendation or endorse the views expressed within them.