NAME RECOGNITION SYSTEM

• US 20170323637A1
• Filed: 07/07/2017
• Published: 11/09/2017
• Est. Priority Date: 06/08/2012
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: NAIK, Devang K.
• Granted Patent: US 10,079,014 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/187 Phonemic context, e.g. pronunciation rules, phonotactical constraints or phoneme n-grams
• CPC Class Codes: G10L 15/30 Distributed recognition, e.g. in client-server systems, for mobile phones or network applications
• CPC Class Codes: G10L 2015/025 Phonemes, fenemes or fenones being the recognition units
• CPC Class Codes: G10L 2015/0633 using lexical or orthographic knowledge sources

Abstract

A speech recognition system uses, in one embodiment, an extended phonetic dictionary that is obtained by processing words in a user'"'"'s set of databases, such as a user'"'"'s contacts database, with a set of pronunciation guessers. The speech recognition system can use a conventional phonetic dictionary and the extended phonetic dictionary to recognize speech inputs that are user requests to use the contacts database, for example, to make a phone call, etc. The extended phonetic dictionary can be updated in response to changes in the contacts database, and the set of pronunciation guessers can include pronunciation guessers for a plurality of locales, each locale having its own pronunciation guesser.

Claims

1-20. -20. (canceled)

21. :

A non-transitory machine-readable storage medium storing one or more programs, comprising instructions, which when executed by one or more processors of an electronic device, cause the electronic device to;

detect a change in a user'"'"'s set of one or more databases;

responsive to detecting the change in the user'"'"'s set of one or more databases,

obtain words from the user'"'"'s set of one or more databases; and

process, using a set of one or more pronunciation guessers, the words from the user'"'"'s set of one or more databases, the processing producing additional phonetic data derived from the words, the additional phonetic data forming an extended phonetic dictionary for the user;

receive a speech input;

process the speech input by comparing phonemes detected in the speech input to a phonetic dictionary and to the extended phonetic dictionary to determine a set of one or more matches;

determine a best match from the set of one or more matches; and

provide an output associated with the best match.

22. :

The non-transitory medium as in claim 21 wherein providing the output associated with the best match comprises displaying a speech recognition output associated with the best match on a screen of the electronic device.

23. :

The non-transitory medium as in claim 21 wherein the change in the user'"'"'s set of one or more databases comprises a change in at least one of;

a contacts database, a calendar database, and a media database.

24. :

The non-transitory medium as in claim 21 wherein the user'"'"'s set of one or more databases comprises a contacts database and wherein the change the in user'"'"'s set of one or more databases comprises an addition of a name of a contact to the contacts database.

25. :

The non-transitory medium as in claim 21 wherein the user'"'"'s set of one or more databases comprises a contacts database with names of people and telephone numbers, wherein the change comprises a change in the contacts database, wherein the phonetic dictionary is for natural language speech recognition, and wherein the speech input is for calling a telephone number or sending a text message to another device.

26. :

The non-transitory medium as in claim 25, wherein the non-transitory computer-readable storage medium further comprises instructions, which when executed by the one or more processors of the electronic device, cause the device to;

obtain the change in the contacts database in response to the change being made; and

process, using the set of one or more pronunciation guessers, the change in the contacts database to update the extended phonetic dictionary based on the change in the contacts database.

27. :

The non-transitory medium as in claim 26, wherein the set of one or more pronunciation guessers comprise pronunciation guessers for a plurality of locales, each locale having its own pronunciation guesser.

28. :

The non-transitory medium as in claim 26, wherein the set of one or more pronunciation guessers comprises different pronunciation guessers for the same locale.

29. :

The non-transitory medium as in claim 27, wherein the non-transitory computer-readable storage medium further comprises instructions, which when executed by the one or more processors of the electronic device, cause the device to;

automatically determine a set of languages or locales from the words in the user'"'"'s set of one or more databases;

select a subset of the set of one or more pronunciation guessers, wherein the subset is selected based upon the set of languages or locales that were automatically determined from the words in the user'"'"'s set of one or more databases; and

wherein the processing which produces the additional phonetic data uses only the subset of the set or one or more pronunciation guessers when producing the additional phonetic data.

30. :

The non-transitory medium as in claim 26, wherein obtaining the words from the user'"'"'s set of one or more databases comprises obtaining the words in the contacts database from an external electronic device, wherein receiving the speech input comprises receiving the speech input from the external electronic device, and wherein providing the output associated with the best match comprises transmitting the best match to the external electronic device.

31. :

The non-transitory medium as in claim 30 wherein the electronic device executes the one or more programs for a plurality of users, and each user of the plurality of users has a dedicated extended phonetic dictionary that is unique to each user.

32. :

A method comprising;

detecting a change in a user'"'"'s set of one or more databases;

responsive to detecting the change in the user'"'"'s set of one or more databases,

obtaining words from the user'"'"'s set of one or more databases; and

processing, using a set of one or more pronunciation guessers, the words from the user'"'"'s set of one or more databases, the processing producing additional phonetic data derived from the words, the additional phonetic data forming an extended phonetic dictionary for the user;

receiving a speech input;

processing the speech input by comparing phonemes detected in the speech input to a phonetic dictionary and to the extended phonetic dictionary to determine a set of one or more matches;

determining a best match from the set of one or more matches; and

providing an output associated with the best match.

33. :

A data processing system comprising;

an input device for receiving a speech input from a user;

a set of one or more processors coupled to the input device; and

a memory coupled to the set of one or more processors, the memory storing a phonetic dictionary for speech recognition and storing an extended phonetic dictionary for the user,

wherein the extended phonetic dictionary is produced by;

responsive to detecting a change in a set of one or more databases of the user, processing, using the set of one or more processors, words in the user'"'"'s set of one or more databases using a set of one or more pronunciation guessers,

wherein the set of one or more processors processes the speech input by comparing phonemes detected in the speech input to the phonetic dictionary and to the extended phonetic dictionary to determine a best match.