Artificial intelligence is one of the definitive development of the 21st century. The time is not far when we’ll have a robot write a blog post for us. AI is a powerful tool that is supporting different organizations, brands, and their customer service by making the experience less complex. Google is one such company which has rightly used AI technology into its Google Assistant. Also Read - UEFA Euro 2020: Colourful Google Doodle kicks off European Football ChampionshipAlso Read - Android 12 beta 2 rolling out: New privacy features, tweaked design and more
A paper, titled Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions, has been published by Google highlights a new Google text-to-speech system, called Tacotron 2, which is capable of a near-human level of AI voice reproduction. Also Read - Sundar Pichai: 5 interesting facts about Google CEO you never heard before
The paper explains that the AI’s speech from text is so human-like that it cannot be differentiated from that of a person reading the text. Google explains that to achieve Tacotron 2 they used a pair of neural networks- one to create a visual representation of specific audio frequencies and a second, WaveNet that helped recreate this visual data as sound.
Alongside the paper, Google as also launched a website that contains audio samples from “Natural TTS Synthesis by Conditioning WaveNet on Mel Spectrogram Predictions” and how the technology sounded when in practice.
Recently, Google announced a major expansion of its Google Assistant across Android Marshmallow and Nougat devices. Like we know, there is no Google Assistant app to download and so Google making the feature available via an update to Google Play Services. Google Assistant also rolling out to users in Italy, Japan, Germany, Brazil and Korea.