An anecdote: is that recently I was in a noisy restaurant with an open kitchen (think loud steam blasts and fryers and servers yelling out order numbers) and showing an older friend how far voice recognition had come and it successfully got most of our queries first try and if not, every time second try. This is with English language and asking it to play specific songs. We also have something of a strong accent compared to the san-fran types that presumably trained it (northern England)