Baidu is building on its Deep Voice engine Anthony Kwan/Bloomberg via Getty Images
Chinese search giant Baidu says it can create a copy of someone’s voice using neural networks – and all that’s needed to work from is less than a minute’s worth of audio of the person talking.
Baidu researchers say the technology could create digital duplicate voices for people who have lost the ability to talk. It could also be used to personalise digital assistants, video game characters or automatic speech translation services.
“A mum could easily configure an audio-book reader with her own voice to read bedtime…
Article amended on 28 February 2018
We corrected Nitesh Saxena's affiliation
