New AI Tech Hides Audio Issues On Google Duo Calls

Google Duo AH NS 01

Google Duo got better at masking audio issues on calls thanks to a new artificial intelligence technology. The solution, called WaveNetEQ, has been devised by one of the company’s DeepMind teams.

Pixel 4 owners who use Google Duo have unknowingly been testing WaveNetEQ since December. As of Monday, the AI feature began rolling out to several other devices as well. Unfortunately, Google has yet to provide a list of those. What it did deliver this week is an in-depth explanation of how this tech fixes Google Duo audio issues.

waveneteq data packet loss deepmind illustration
Google Duo audio issues most often stem from missing and wrongly ordered data packets.

Audio issues stemming from data packet loss affect 99% of Google Duo calls, according to Alphabet’s subsidiary. While that figure may seem shockingly high, it’s anything but. It is merely a reflection of how imperfect internet-based voice tech continues to be. DeepMind developed WaveNetEQ in response and claims the solution offers unprecedented packet loss mitigation.


Addressing Google Duo audio issues by predicting the future

In layman’s terms, the service analyzes call data and supplements it with predictive audio when necessary. The AI-created audio information replaces not just lost packets, but also wrongly ordered ones. DeepMind’s platform stems from WaveRNN, an efficient neural audio synthesis solution first conceptualized in a science paper two years ago. WaveRNN itself was preceded by WaveNet, a deep neural network touted as a major breakthrough in AI-infused audio processing back in 2017.

Ultra-complex AI isn’t the only way to combat audio issues on internet calls. However, DeepMind claims it delivers unparalleled results with gaps longer than 60 milliseconds. Encouraged by initial results, the company’s adamant to continue pursuing this packet loss concealement technique moving forward.

It’s unclear when WaveNetEQ might become more widely available. The feature’s backend doesn’t run entirely in the cloud, which rules out entry-level Android devices. Instead, it requires hosts with somewhat capable processors optimized for machine learning. That would be most modern flagship and mid-range chipsets.


Perhaps the biggest obstacle to WaveNetEQ’s wider deployment is the solution’s dependance on vast volumes of data. Like any other machine learning tech, DeepMind’s service requires tons of information to learn from before becoming remotely useful in any particular language. In other words, it’s implied only English-speaking Pixel 4 owners were unknowingly using the enhanced version of Google Duo since the turn of the year.

Be that as it may, DeepMind hasn’t been ignoring other languages since its WaveNet days. It should hence only be a matter of time before WaveNetEQ rolls out to more territories.