Method and system for providing speech recognition
View Patent ↗An approach for providing speech recognition is disclosed. A name is retrieved from a user based on data provided by the user. The user is prompted for a name of the user. A first audio input is received from the user in response to the prompt. Speech recognition is applied to the first audio input using a name grammar database to output a recognized name. A determination is made whether the recognized name matches the retrieved name. If no match is determined, the user is re-prompted for the name of the user for a second audio input. Speech recognition is applied to the second audio input using a confidence database having entries less than the name grammar database.
1. A method comprising:
receiving a first audio input representing a combination of a spoken name of a user and spoken letters of the name of the user;
applying, via at least one processor, speech recognition to the first audio input using a name grammar database to output a combination of a name and letters of the name;
wherein the speech recognition includes determining, via the at least one processor, whether there is a combination of a name in the name grammar database and letters of the name in the name grammar database, which matches the combination of the spoken name of the user and spoken letters of the name of the user, wherein a determination that there is no combination in the name grammar database, which matches the combination of the spoken name of the user and spoken letters of the name of the user indicates an out of grammar condition;
receiving, if an out of grammar condition exists, a second audio input representing the combination of the spoken name of the user and the spoken letters of the name of the user; and
applying, via the at least one processor, speech recognition to the second audio input using a confidence database that is separate from the name grammar database.
2. A method according to claim 1 , wherein the confidence database is configured to store a subset of entries of the name grammar database.
3. A method according to claim 2 , wherein the confidence database includes one or more entries that are derived from the name grammar database and are ranked by confidence level.
4. A method according to claim 2 , further comprising:
determining additional entries for the confidence database using a decoy application.
5. A method according to claim 1 , further comprising:
determining a confidence level of a comparison between the retrieved combination and the recognized combination.
6. A method according to claim 1 , further comprising:
generating a prompt to acquire data relating to the user, wherein the data includes one of business information or personal information, and is used to obtain the retrieved combination.
7. A method according to claim 1 , further comprising:
confirming the recognized name with the user.
8. A method according to claim 1 , further comprising:
determining a failed condition if no match is found with the retrieved combination after a predetermined number of iteratively prompting the user for the spoken name and the spoken letters of the name.
9. A method according to claim 1 , further comprising:
generating a first prompt to acquire the first audio input from the user; and
selectively generating, based on the determination, a second prompt to acquire the second audio input from the user.
10. An apparatus comprising:
at least one processor; and
at least one memory including computer program code for one or more programs,
the at least one memory and the computer program code configured to, with the at least one processor, cause the apparatus to perform at least the following,
receive a first audio input representing a combination of a spoken name of a user and spoken letters of the name of the user,
apply speech recognition to the first audio input using a name grammar database to output a combination of a name and letters of the name,
wherein the speech recognition includes determining whether there is a combination of a name in the name grammar database and letters of the name in the name grammar database, which matches the combination of the spoken name of the user and spoken letters of the name of the user, wherein a determination that there is no combination in the name grammar database, which matches the combination of the spoken name of the user and spoken letters of the name of the user indicates an out of grammar condition,
receive, if an out of grammar condition exists, a second audio input representing the combination of the spoken name of the user and the spoken letters of the name of the user, and
apply speech recognition to the second audio input using a confidence database that is separate from the name grammar database.
11. An apparatus according to claim 10 , wherein the confidence database is configured to store a subset of entries of the name grammar database.
12. An apparatus according to claim 11 , wherein the confidence database includes one or more entries that are derived from the name grammar database and are ranked by confidence level.
13. An apparatus according to claim 11 , wherein the apparatus is further caused to:
determine additional entries for the confidence database using a decoy application.
14. An apparatus according to claim 10 , wherein the apparatus is further caused to:
determine a confidence level of a comparison between the retrieved combination and the recognized combination.
15. An apparatus according to claim 10 , wherein the apparatus is further caused to:
generate a prompt to acquire data relating to the user, wherein the data includes one of business information or personal information, and is used to obtain the retrieved combination.
16. An apparatus according to claim 10 , wherein the apparatus is further caused to:
confirm the recognized name with the user.
17. An apparatus according to claim 10 , wherein the apparatus is further caused to:
determine a failed condition if no match is found with the retrieved combination after a predetermined number of iteratively prompting the user for the spoken name and the spoken letters of the name.
18. An apparatus according to claim 10 , wherein the apparatus is further caused to:
generate a first prompt to acquire the first audio input from the user; and
selectively generate, based on the determination, a second prompt to acquire the second audio input from the user.
19. A system, comprising:
a voice response unit, including a processor, configured to receive a first audio input representing a combination of a spoken name of a user and spoken letters of the name of the user; and
a speech recognition logic, executed by another processor, configured to output a combination of a name and letters of the name, responsive to the first audio input, and in accordance with a name grammar database;
wherein the voice response unit is further configured to receive a second audio input representing a reutterance of the combination of the spoken name of the user and the spoken letters of the name of the user if a determination is made that there is no combination in the name grammar database, which matches the combination of the spoken name of the user and spoken letters of the name of the user, and
wherein the speech recognition logic is further configured to recognize the second audio input using a confidence database that is separate from the name grammar database.
20. A system according to claim 19 , wherein the confidence database is configured to store a subset of entries of the name grammar database.