The importance of video calls is easily visible during COVID-19 and to make it smoother, Google is about to make use of AI.
Bad connections during video calls occur due to audio gaps, and to put an end to low-quality video calls, Google is about to introduce Artificial Intelligence (AI). Utilizing AI can fill gaps of up to 120 milliseconds and can be trained to produce most syllable sounds. Irrespective of the dialect, this AI has been trained using the voices of 100 individuals in 48 languages to enable it to learn the general characteristics of a human voice.
A library of speech data developed from WaveNetEQ is used to continue short segments of conversations.
Voice transmitted in the form of data gets split into small chunks called packets while making any voice or video call. If these packets reach the other side in the wrong order or at the wrong time or even get lost in the mode of transmission, it results in poor quality connection.
To improvise on this, Google with the help of WaveNetEQ has decided to work, by specifically creating speech data to fill the gaps made by drops in audio.
In recent times, Google has reported that 99% of calls made via Duo app have experienced an audio-related issue. Out of this, 20% lose more than 3% of their total audio, while 10% lose almost a tenth.
“Duo’s end-to-end encryption should help alleviate any concerns about data-sharing,” states ProPrivacy Cybersecurity Researcher Douglas Crawford. He also mentioned to BBC, “As calls on the platform are secured using end-to-end encryption, outsourcing AI-processing of missing packets in order to reduce audio jitters was simply not an option for developers.”
To stop the transmission of data from third party, Google has prepared to take measures by performing needful processes on the device.
The latest Google Pixel 4 smartphone holds this system and its later plans include making it available for more Android devices by the end of this year.