Universal language translator

• US 9,864,745 B2
• Filed: 10/29/2015
• Issued: 01/09/2018
• Est. Priority Date: 07/29/2011
• Status: Active Grant

• Current Assignee: Reginald Dalce
• Original Assignee: Reginald Dalce
• Inventors: Dalce, Reginald
• Primary Examiner(s): THOMAS-HOMESCU, ANNE L
• Application Number:
  US14/926,698
• Publication Number:
  US 20160048508A1
• Time in Patent Office: 803 Days
• CPC Class Codes: G06F 40/58 Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation
• CPC Class Codes: G10L 13/02 Methods for producing synthetic speech; Speech synthesisers
• CPC Class Codes: G10L 13/033 Voice editing, e.g. manipulating the voice of the synthesiser
• CPC Class Codes: G10L 15/005 Language recognition
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence
• CPC Class Codes: G10L 21/0208 Noise filtering

Abstract

A universal language translator automatically translates a spoken word or phrase between two speakers. The translator can lock onto a speaker and filter out ambient noise so as to be used in noisy environments, and to ensure accuracy of the translation when multiple speakers are present. The translator can also synthesize a speaker'"'"'s voice into the dialect of the other speaker such that each speaker sounds like they'"'"'re speaking the language of the other. A dialect detector could automatically select target dialects either by auto-sensing the dialect by listening to aspects of each speaker'"'"'s phrases, or based upon the location of the device.

Claims

1. A translator device, comprising:

a microphone that receives a spoken phrase from a speaker;

a voice recognition module that detects auditory attributes comprising a speed of talking and an average auditory frequency of the speaker from the spoken phrase;

a dialect detector module that selects a dialect comprising slang words in a language specific to a region that are not in other dialects of the language outside the region, wherein the dialect detector module selects the dialect based upon a location of the device within the region;

a translation module that translates the spoken phrase spoken by the speaker to a translated second phrase of the selected dialect, wherein the dialect comprises slang words in a language specific to a region that are not in other dialects of the language outside the region; and

an auditory output module that synthesizes the translated phrase using the speed of talking and the average auditory frequency of the spoken phrase.

2. The translator device of claim 1, wherein at least one of the auditory attributes of the spoken phrase is also selected from the group consisting of pitch, and intonation.

3. The translator device of claim 1, wherein the voice filter module detects a speaker region within which the speaker is located and filters out ambient sounds generated outside the speaker region.

4. The translator device of claim 3, wherein the voice filter module moves the speaker region as the speaker moves.

5. The translator device of claim 1, wherein the voice filter module creates a voice signature for the speaker as a function of the spoken phrase and filters out ambient sounds that do not share attributes of the voice signature.

6. The translator device of claim 1, wherein the dialect detector module receives the location of the device from a GPS device.

7. The translator device of claim 1, wherein the dialect detector module receives the location of the device from a triangulation module.

8. The translator device of claim 1, wherein the microphone further records a second spoken phrase by a second speaker, and wherein the dialect detector module further selects the dialect based upon a detected dialect of the second spoken phrase.

9. The translator device of claim 1, wherein the dialect detector module has a library of at least 10000 dialects.

10. The translator device of claim 1, wherein the translation module has a library of at least 500 languages.

11. The translator device of claim 1, wherein the voice recognition module is further configured to continuously record present auditory attributes of the speaker'"'"'s voice, and wherein the auditory output module is configured to continuously modify the synthesized voice over time as a function of the present auditory attributes.

12. The translator device of claim 1, wherein the dialect detector module has a library of dialects that include Southern, Bostonian, British, Australian, and South African dialects of English.

13. The translator device of claim 1, further comprising a voice filter module that filters out ambient sounds generated by a non-speaker object.

14. The translator device of claim 13, further comprising a speaker selection user interface that allows a user of the device to select which speaker to listen to when multiple voices are detected by the microphone, wherein the voice filter module filters out non-selected speakers.