Google has improved its voice search to provide faster and more accurate results, even in noisy surroundings.
The service is device dependent and, in general, the company has made Google Voice 300 milliseconds faster, but some device users will be able to get it as much as 500 milliseconds faster.
Google said that it has built better neural network acoustic models using Connectionist Temporal Classification (CTC) and sequence discriminative training techniques.
Google said that its acoustic models rely on Recurrent Neural Networks (RNN), which picks up the tone of each word in a better way helping users get precise answers to the queries.
Google said: "We are happy to announce that our new acoustic models are now used for voice searches and commands in theGoogle app (on Android and iOS), and for dictation on Android devices.
"In addition to requiring much lower computational resources, the new models are more accurate, robust to noise, and faster to respond to voice search queries – so give it a try, and happy (voice) searching."
All the major OS makers have a voice-based assistant like Apple’s Siri, Microsoft’s Cortana and Amazon’s Alexa.
