Skip to Content
Artificial intelligence

Google’s AI can now translate your speech while keeping your voice

Researchers trained a neural network to map audio “voiceprints” from one language to another.
May 20, 2019
An image of U.N. Secretary-General Ban Ki-moon listening to a translation device
An image of U.N. Secretary-General Ban Ki-moon listening to a translation device
An image of U.N. Secretary-General Ban Ki-moon listening to a translation deviceEMILIO MORENATTI/AP

Listen to this Spanish audio clip.

This is how its English translation might sound when put through a traditional automated translation system.

Now this is how it sounds when put through Google’s new automated translation system.

The results aren’t perfect, but you can sort of hear how Google’s translator was able to retain the voice and tone of the original speaker. It can do this because it converts audio input directly to audio output without any intermediary steps. In contrast, traditional translational systems convert audio into text, translate the text, and then resynthesize the audio, losing the characteristics of the original voice along the way.

The new system, dubbed the Translatotron, has three components, all of which look at the speaker’s audio spectrogram—a visual snapshot of the frequencies used when the sound is playing, often called a voiceprint.  The first component uses a neural network trained to map the audio spectrogram in the input language to the audio spectrogram in the output language. The second converts the spectrogram into an audio wave that can be played. The third component can then layer the original speaker’s vocal characteristics back into the final audio output.

Not only does this approach produce more nuanced translations by retaining important nonverbal cues, but in theory it should also minimize translation error, because it reduces the task to fewer steps.

Translatotron is currently a proof of concept. During testing, the researchers trialed the system only with Spanish-to-English translation, which already took a lot of carefully curated training data. But audio outputs like the clip above demonstrate the potential for a commercial system later down the line. You can listen to more of them here.

Deep Dive

Artificial intelligence

conceptual illustration showing various women's faces being scanned
conceptual illustration showing various women's faces being scanned

A horrifying new AI app swaps women into porn videos with a click

Deepfake researchers have long feared the day this would arrive.

computation concept
computation concept

How AI is reinventing what computers are

Three key ways artificial intelligence is changing what it means to compute.

digital twins concept
digital twins concept

How AI digital twins help weather the world’s supply chain nightmare

Just-in-time shipping is dead. Long live supply chains stress-tested with AI digital twins.

still from Embodied Intelligence video
still from Embodied Intelligence video

These weird virtual creatures evolve their bodies to solve problems

They show how intelligence and body plans are closely linked—and could unlock AI for robots.

Stay connected

Illustration by Rose WongIllustration by Rose Wong

Get the latest updates from
MIT Technology Review

Discover special offers, top stories, upcoming events, and more.

Thank you for submitting your email!

Explore more newsletters

It looks like something went wrong.

We’re having trouble saving your preferences. Try refreshing this page and updating them one more time. If you continue to get this message, reach out to us at customer-service@technologyreview.com with a list of newsletters you’d like to receive.