Assuming the voice recognition part worked perfectly:
1) query song database for input 2) play result that is most popular (most plays by manual selection in eg desktop client etc)
The only tricky part is to determine whether the query is an artist or a title but again in most cases this will be solved by checking popularity.
What's a plausible explanation that they mess this up so badly?
Assuming the voice recognition part worked perfectly:
1) query song database for input 2) play result that is most popular (most plays by manual selection in eg desktop client etc)
The only tricky part is to determine whether the query is an artist or a title but again in most cases this will be solved by checking popularity.
What's a plausible explanation that they mess this up so badly?