Google Listens Faster, More Effectively With Improved ‘Deep Learning’ Neural

At the 2013 Google I/O developers conference, Amit Singhai, today a senior vice president and Google Fellow, said the future of search is in voice. It has added artificial noise and reverberation to the training data, all of which would result in better speech recognition even with ambient noise. This has involved moving from deep neural network technology to recurrent neural networks. That’s what the company says in a new blog post that details how it has ramped up performance of its search app on Android and iOS. Google explains all of these advances are as a result of the introduction of more highly effective neural team traditional acoustic types utilizing “Connectionist Temporal Classification (CTC) and system password exercising and training techniques”. And while it would normally be hard to…


Link to Full Article: Google Listens Faster, More Effectively With Improved ‘Deep Learning’ Neural

Pin It on Pinterest

Share This

Join Our Newsletter

Sign up to our mailing list to receive the latest news and updates about homeAI.info and the Informed.AI Network of AI related websites which includes Events.AI, Neurons.AI, Awards.AI, and Vocation.AI

You have Successfully Subscribed!