If you noticed Google Voice Search queries are snappier and more accurate than they might have been previously — it’s not just you. Google announced today on their Google Research Blog that they’ve officially made the switch to a newer technology powering voice search, essentially turbo charging the service over on their end.
“Today, we’re happy to announce we built even better neural network acoustic models using Connectionist Temporal Classification (CTC) and sequence discriminative training techniques. These models are a special extension of recurrent neural networks (RNNs) that are more accurate, especially in noisy environments, and they are blazingly fast!”
Google also mentions that they included artificial noise and reverb in their training data, which helps with voice recognition in noisy environments. In addition to being more accurate and quicker to respond, Google’s newer technology requires much lower computational resources. It’s pretty technical, but if you’ve like to give the entire blog post a once over, hit up the link below.
In the meantime, Google’s new acoustic models are already working in voice search for both Android and iOS, so feel free to try it out if you haven’t in a while.