Method and apparatus for detecting user ID changes
View Patent ↗In many speech-enabled applications, adaptation of speech recognition and language understanding tools for different users are employed. With such adaptation, identifying the particular user precedes applying the speech recognition and language understanding tools. According to at least one example embodiment, a method and corresponding apparatus of identifying a user includes comparing personal information data received from a user network device against personal information accessible by the server; and identifying a speech profile specific to the user based on the results of comparing the personal information data retrieved from the first user network device against the personal information accessible by the server. The identified speech profile is used in processing a speech of the user. Through use of the method or corresponding apparatus, a user can proceed directly to the use of the speech recognition or other applications and bypassing a login sequence.
1. A computerized method for identifying a user, the method comprising:
responsive to a speech recognition request received at a server from a user network device:
comparing, by the server, a hash representation of non-voice personal information data retrieved from a memory of the user network device, the personal information data being separate from data identifying the user network device, against a known hash representation of non-voice personal information, the known hash representation accessible by the server;
identifying, at the server, a speech profile having an acoustic profile specific to the user and linguistic features specific to the user, the identifying being based on the results of comparing the hash representation of non-voice personal information data retrieved from the memory of the user network device against the known hash representation of the non-voice personal information accessible by the server; and
processing the speech recognition request, at the server, by applying features of the identified speech profile specific to the user in a speech enabled application;
wherein the received non-voice personal information data includes at least one of the following:
a list of contacts;
information associated with one or more applications;
information associated with one or more music files; and
information associated with one or more multimedia files.
2. A method according to claim 1 , wherein the user network device is a first user network device and wherein the non-voice personal information accessible by the server is associated with a second user network device different from the first user network device.
3. A method according to claim 1 further comprising retrieving the hash representation of the non-voice personal information data from the user network device.
4. A method according to claim 1 further comprising mapping a device ID of the user network device to the identified speech profile.
5. A method according to claim 1 , wherein comparing the hash representation of the non-voice personal information data received from the user network device against the known hash representation of the non-voice personal information accessible by the server includes comparing a list of non-voice personal information data received from the first user network device against a list of non-voice personal information accessible by the server using a shingling method.
6. A method according to claim 1 , wherein comparing the hash representation of the non-voice personal information data received from the user network device against the known hash representation of the non-voice personal information accessible by the server includes comparing voice recording data received from user network device with voice recording data accessible by the server.
7. A method according to claim 6 , wherein comparing voice recording data received from the user network device with voice recording data accessible by the server includes:
extracting parameters from voice recording data received from the user network device; and
comparing the extracted parameters to parameters associated with the voice recording data accessible by the server.
8. A computer server for identifying a user, the server comprising:
a communications interface configured to facilitate communication with a user network device through a communications network;
a memory with computer code instructions stored thereon; and
a processor;
the memory with the computer code instructions and the processor being configured to cause the server to:
responsive to a speech recognition request received at the server from the user network device:
compare non-voice a hash representation of personal information data retrieved from a memory of the user network device, the personal information data being separate from data identifying the user network device, against a known hash representation of non-voice personal information, the known hash representation accessible by the server;
identify a speech profile having an acoustic profile specific to the user and linguistic features specific to the user, the identifying based on the results of comparing the hash representation of non-voice personal information data received from the memory of the user network device against the known hash representation of the non-voice personal information accessible by the server; and
process the speech recognition request, at the server, by applying features of the identified speech profile specific to the user in a speech enabled applications;
wherein the received non-voice personal information data includes at least one of the following:
a list of contacts;
information associated with one or more applications;
information associated with one or more music files; and
information associated with one or more multimedia files.
9. A computer server according to claim 8 , wherein the user network device is a first user network device and wherein the non-voice personal information accessible by the server is associated with a second user network device different from the first user network device.
10. A computer server according to claim 8 , wherein the first user network device and the second user network device being associated with the user.
11. A computer server according to claim 8 , wherein the memory, with the computer code instructions, and the processor are further configured to cause the computer server to retrieve the hash representation of the non-voice personal information data from the user network device.
12. A computer server according to claim 8 , wherein the memory, with the computer code instructions, and the processor are further configured to cause the computer server to map a device ID of the user network device to the identified speech profile.
13. A computer server according to claim 8 , wherein, in comparing the hash representation of the non-voice personal information data received from the first user network device against the known hash representation of the non-voice personal information accessible by the server, the memory, with the computer code instructions, and the processor are configured to cause the computer server to compare a list of non-voice personal information data received from the user network device against a list of non-voice personal information accessible by the server using a shingling method.
14. A computer server according to claim 8 , wherein in comparing the hash representation of the non-voice personal information data retrieved from the first user network device against the known hash representation of the non-voice personal information accessible by the server, the memory, with the computer code instructions, and the processor being further configured to cause the computer server to compare voice recording data retrieved from first user network device with voice recording data accessible by the server.
15. A computer server according to claim 8 , wherein, in comparing voice recording data received from user network device with voice recording data accessible by the server, the memory, with the computer code instructions, and the processor are further configured to cause the computer server to:
extract parameters from voice recording data received from user network device; and
compare the extracted parameters to parameters associated with the voice recording data accessible by the server.
16. A non-transitory computer-readable medium with computer code instructions stored thereon, the computer code instructions when executed by a processor cause an apparatus to perform the following:
responsive to a speech recognition request received at a server from a user network device:
comparing a hash representation of non-voice personal information data retrieved from a memory of the user network device, the personal information data being separate from data identifying the user network device, against a known hash representation of non-voice personal information, the known hash representation accessible by the server; and
identifying a speech profile having an acoustic profile specific to the user and linguistic features specific to the user, the identifying being based on the results of comparing the hash representation of non-voice personal information data retrieved from the memory of the user network device against the known hash representation of the non-voice personal information accessible by the server;
processing the speech recognition request, at the server, by applying features of the identified speech profile specific to the user in a speech enabled applications;
wherein the received non-voice personal information data includes at least one of the following:
a list of contacts;
information associated with one or more applications;
information associated with one or more music files; and
information associated with one or more multimedia files.