Systems and methods for automatic phonetization of domain names

• US 9,947,311 B2
• Filed: 12/21/2015
• Issued: 04/17/2018
• Est. Priority Date: 12/21/2015
• Status: Active Grant

• Current Assignee: VeriSign, Inc.
• Original Assignee: VeriSign, Inc.
• Inventors: Raemy, Vincent, Russo, Vincenzo, Hennebert, Jean, Wicht, Baptiste
• Primary Examiner(s): ADESANYA, OLUJIMI A
• Application Number:
  US14/977,133
• Publication Number:
  US 20170178621A1
• Time in Patent Office: 848 Days
• Field of Search: 704 9, 704 10, 704256, 704258, 704270
• CPC Class Codes: G06F 40/205 Parsing
• CPC Class Codes: G06F 40/268 Morphological analysis
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/08 Text analysis or generation of parameters for speech synthesis out of text, e.g. grapheme to phoneme translation, prosody generation or stress or intonation determination
• CPC Class Codes: G10L 13/10 Prosody rules derived from text; Stress or intonation

Abstract

A method can include receiving, from a user, a string of characters. The method can also include determining components of the string of characters. The components of the string of characters may include one or more graphemes that are related in the string of characters. The method can include determining universal phonetic representations for the components of the string of characters. The method can also include determining pronunciations for the universal phonetic representations. Additionally, the method can include constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations. Further, the method can include sending, to the user, a sound file representing the pronunciation of the string of characters.

Claims

1. A method, comprising:

receiving, from a user, a string of characters;

determining components of the string of characters, wherein the components of the string of characters comprise one or more graphemes that are related in the string of characters;

determining universal phonetic representations for the components of the string of characters;

determining pronunciations for the universal phonetic representations;

constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations;

sending, to the user, a sound file representing the pronunciation of the string of characters;

receiving a user sound file created by the user using a microphone, the user sound file representing a custom pronunciation associated with a subset of the universal phonetic representations corresponding to a portion of the pronunciation of the string of characters;

constructing a new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation associated with the subset of the universal phonetic representations; and

sending, to the user, a new sound file representing the new pronunciation of the string of characters, wherein the new sound file comprises a combination of a portion of the sound file representing the pronunciation of the string of characters and the user sound file.

2. The method of claim 1, the method further comprising:

in response to sending the sound file, receiving, from the user, an indication that at least the portion of the pronunciation of the string of characters is incorrect.

3. The method of claim 1, wherein determining pronunciations for the universal phonetic representations, comprises:

determining that at least one pronunciation does not exist for at least one of the universal phonetic representations;

receiving, from the user, a custom pronunciation for at least one of the universal phonetic representations;

constructing a second new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation for the at least one of the universal phonetic representations; and

sending, to the user, a second new sound file representing the new second pronunciation of the string of characters.

4. The method of claim 1, wherein determining universal phonetic representations for the components of the string of characters, comprises:

accessing a first data structure that maps the components of the string of characters to the universal phonetic representations based on an international phonetic alphabet, wherein the first data structure comprises a plurality of first nodes with each first node of the plurality of first nodes having a respective weight assigned that corresponds to a pronunciation of a universal phonetic representation; and

determining the universal phonetic representations for the components of the string of characters based on the first data structure.

5. The method of claim 1, wherein the string of characters corresponds to a domain name.

6. The method of claim 5, the method further comprising:

registering the string of characters as the domain name; and

associating the new sound file with the domain name.

7. The method of claim 1, wherein constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations, comprises:

combining sound files for pronunciations for the universal phonetic representations.

8. A system, comprising:

a memory storing instructions; and

at least one processor, operably coupled to the memory, implemented at least in part in hardware, and configured to execute the instructions to perform a method comprising;

receiving, from a user, a string of characters;

determining components of the string of characters, wherein the components of the string of characters comprise one or more graphemes that are related in the string of characters;

determining universal phonetic representations for the components of the string of characters;

determining pronunciations for the universal phonetic representations;

constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations;

sending, to the user, a sound file representing the pronunciation of the string of characters;

receiving a user sound file created by the user using a microphone, the user sound file representing a custom pronunciation associated with a subset of the universal phonetic representations corresponding to a portion of the pronunciation of the string of characters;

constructing a new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation associated with the subset of the universal phonetic representations; and

sending, to the user, a new sound file representing the new pronunciation of the string of characters, wherein the new sound file comprises a combination of a portion of the sound file representing the pronunciation of the string of characters and the user sound file.

9. The system of claim 8, wherein the at least one processor is configured to execute the instructions to perform the method further comprising:

in response to sending the sound file, receiving, from the user, an indication that at least the portion of the pronunciation of the string of characters is incorrect.

10. The system of claim 8, wherein determining pronunciations for the universal phonetic representations, comprises:

determining that at least one pronunciation does not exist for at least one of the universal phonetic representations;

receiving, from the user, a custom pronunciation for at least one of the universal phonetic representations;

constructing a second new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation for the at least one of the universal phonetic representations; and

sending, to the user, a second new sound file representing the second new pronunciation of the string of characters.

11. The system of claim 8, wherein determining universal phonetic representations for the components of the string of characters, comprises:

accessing a first data structure that maps the components of the string of characters to the universal phonetic representations based on an international phonetic alphabet, wherein the first data structure comprises a plurality of first nodes with each first node of the plurality of first nodes having a respective weight assigned that corresponds to a pronunciation of a universal phonetic representation; and

determining the universal phonetic representations for the components of the string of characters based on the first data structure.

12. The system of claim 8, wherein the string of characters corresponds to a domain name.

13. The system of claim 12, wherein the at least one processor is configured to execute the instructions to perform the method further comprising:

registering the string of characters as the domain name; and

associating the new sound file with the domain name.

14. The system of claim 8, wherein constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations, comprises:

combining sound files for pronunciations for the universal phonetic representations.

15. A non-transitory computer-readable medium comprising instructions which, when executed by at least one processor, cause the at least one processor to perform a method comprising:

receiving, from a user, a string of characters;

determining components of the string of characters, wherein the components of the string of characters comprise one or more graphemes that are related in the string of characters;

determining universal phonetic representations for the components of the string of characters;

determining pronunciations for the universal phonetic representations;

constructing a pronunciation of the string of characters based at least partially on the pronunciations of the universal phonetic representations;

sending, to the user, a sound file representing the pronunciation of the string of characters;

receiving a user sound file created by the user using a microphone, the user sound file representing a custom pronunciation associated with a subset of the universal phonetic representations corresponding to a portion of the pronunciation of the string of characters;

constructing a new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation associated with the subset of the universal phonetic representations; and

sending, to the user, a new sound file representing the new pronunciation of the string of characters, wherein the new sound file comprises a combination of a portion of the sound file representing the pronunciation of the string of characters and the user sound file.

16. The non-transitory computer-readable medium of claim 15, the method further comprising:

in response to sending the sound file, receiving, from the user, an indication that at least the portion of the pronunciation of the string of characters is incorrect.

17. The non-transitory computer-readable medium of claim 15, wherein determining pronunciations for the universal phonetic representations, comprises:

determining that at least one pronunciation does not exist for at least one of the universal phonetic representations;

receiving, from the user, a custom pronunciation for at least one of the universal phonetic representations;

constructing a second new pronunciation of the string of characters based at least partially on the pronunciations for the universal phonetic representations and the custom pronunciation for the at least one of the universal phonetic representations; and

sending, to the user, a second new sound file representing the second new pronunciation of the string of characters.

18. The non-transitory computer-readable medium of claim 15, wherein determining universal phonetic representations for the components of the string of characters, comprises:

accessing a first data structure that maps the components of the string of characters to the universal phonetic representations based on an international phonetic alphabet, wherein the first data structure comprises a plurality of first nodes with each first node of the plurality of first nodes having a respective weight assigned that corresponds to a pronunciation of a universal phonetic representation; and

determining the universal phonetic representations for the components of the string of characters based on the first data structure.

19. The non-transitory computer-readable medium of claim 15, wherein the string of characters corresponds to a domain name.

20. The non-transitory computer-readable medium of claim 19, the method further comprising:

registering the string of characters as the domain name; and

associating the new sound file with the domain name.