Deriving acoustic features and linguistic features from received speech audio

1. A computer-implemented method comprising:

receiving (i) speech audio of dictation and (ii) a user ID associated with the speech audio;

deriving acoustic features from the speech audio;

storing the derived acoustic features in a user profile associated with the user ID;

receiving a request for acoustic features through an application programming interface (API), the request including the user ID;

retrieving the derived acoustic features in the user profile using the user ID included in the received request for acoustic features; and

sending the derived acoustic features, through the API, to an advertisement application.

2. A non-transitory computer readable medium storing instructions to cause one or more computers to perform the computer-implemented method of claim 1 .

3. A computer-implemented method comprising:

receiving (i) speech audio of dictation and (ii) a user ID associated with the speech audio;

deriving linguistic features from the speech audio;

storing the derived linguistic features in a user profile associated with the user ID;

receiving a request for linguistic features through an application programming interface (API), the request including the user ID;

retrieving the derived linguistic features in the user profile using the user ID included in the received request for linguistic features; and

sending the derived linguistic features, through the API, to an advertisement application.

4. A non-transitory computer readable medium storing instructions to cause one or more computers to perform the computer-implemented method of claim 3 .

5. The computer-implemented method of claim 1 , further comprising determining an accent property using at least one acoustic feature of the derived acoustic features and updating the user profile in dependence on the determined accent property.

6. The computer-implemented method of claim 5 , further comprising sending information through the API to allow for generating a voice instruction addressed to a user, wherein the voice instruction bears an accent that corresponds to the determined accent property.

7. The computer-implemented method of claim 5 , further comprising selecting an ad for display, wherein the ad is aimed at users of a specific demographic group indicated by the determined accent property.

8. The computer-implemented method of claim 1 , further comprising determining an age range property using at least one acoustic feature of the derived acoustic features and updating the user profile in dependence on the determined age range property.

9. The computer-implemented method of claim 8 , further comprising selecting an ad for display, wherein the ad is aimed at users having an age within an age range assigned to the age range property.

10. The computer-implemented method of claim 3 , further comprising determining a region property using the linguistic feature and updating the user profile in dependence on the determined region property.

11. The computer-implemented method of claim 10 , further comprising sending information through the API to allow for generating a voice instruction addressed to a user, wherein the voice instruction includes words from a vocabulary that depends on the determined region property.

12. The computer-implemented method of claim 10 , further comprising selecting an ad for display, wherein the ad comprises words from a vocabulary that corresponds to the determined region property.

13. The computer-implemented method of claim 3 , further comprising determining an age range property using the linguistic feature and updating the user profile in dependence on the determined age range property.

14. The computer-implemented method of claim 13 , further comprising selecting an ad for display, wherein the ad is aimed at users having an age within an age range assigned to the age range property.