Everyone knows what AI is all, out of 1 in 10 hollywood films, they show some features of Artificial Intelligence in Our World, Now Google has made his next Step towards the AI speech called TACOTRON 2
Google has created a new text-to-speech AI called Tacotron 2, which uses deep neural networks to perfectly imitate human speech. Google published a research paper(CLICK HERE) about the system, which is able to read text in a generated female voice that is indistinguishable from an actual human reading the same text.
The system is Google’s second official generation of the technology, which consists of two deep neural networks. The first network translates the text into a spectrogram, a visual way to represent audio frequencies over time. That spectrogram is then fed into WaveNet, a system from Alphabet’s AI research lab DeepMind, which reads the chart and generates the corresponding audio elements accordingly.
You can check out audio samples of Tacotron 2 and compare it to an actual human speaking the same text here. CLICK HERE
I hope this material is useful, Think big, Be Kind and Try Xtra, keep all your dreams alive !!!