Systems and method for speech to speech translation using cores of a natural liquid architecture system

• US 9,477,658 B2
• Filed: 06/12/2014
• Issued: 10/25/2016
• Est. Priority Date: 10/26/2005
• Status: Active Grant

• Current Assignee: Cortica Ltd.
• Original Assignee: Cortica Ltd.
• Inventors: Raichelgauz, Igal, Odinaev, Karina, Zeevi, Yehoshua Y.
• Primary Examiner(s): Woo, Isaac M
• Application Number:
  US14/302,495
• Publication Number:
  US 20140297255A1
• Time in Patent Office: 866 Days
• Field of Search: 707600-899
• US Class Current: 1/1
• CPC Class Codes: G06F 16/41 Indexing; Data structures therefor; Storage structures
• CPC Class Codes: G06F 16/685 using automatically derived transcript of audio data, e.g. lyrics speech recognition G10L15/00
• 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

Abstract

A method and system for speech to speech translation using a plurality of computational cores of a natural liquid architecture are provided. The method includes receiving an audio signal; identifying a first concept related to the received audio signal; identifying a first language based on the first concept identified for the received audio signal; and determining a match between of the first concept and at least a second concept, wherein the at least second concept represents a target second language.

Claims

1. A method for speech to speech translation using a plurality of computational cores of a natural liquid architecture, comprising:

receiving an audio signal;

identifying a first concept related to the received audio signal;

identifying a first language based on the first concept identified for the received audio signal;

determining a match between the first concept and at least a second concept by;

identifying a first plurality of concepts in the first language, wherein the first plurality of concepts is statistically proximate to the first concept and previously matched to a second plurality of concepts, wherein the second plurality of concepts is respective of the second target language; and

identifying the second concept statistically proximate to the second plurality of concepts, wherein the statistical proximity is determined by use of a threshold, wherein

the at least second concept represents a target second language.

2. The method of claim 1, wherein the received audio signal is at least one of:

a digital representation of an audio signal, and a direct feed from at least one microphone device.

3. The method of claim 1, wherein a plurality of audio signals is received respective of a single source.

4. The method of claim 1, wherein identifying the first concept further comprises:

generating at least one signature respective of the received audio signal, and matching the generated at least one signature to at least another signature from a signature database, wherein the at least one signature is generated by the plurality of computational cores of the natural liquid architecture.

5. The method of claim 4, wherein the at least one signature is generated respective of at least one of:

the entire audio signal, a part of the audio signal, and a combination of entire or partial audio signals.

6. The method of claim 1, further comprising:

determining a match respective of the first concept and a third concept, wherein the third concept is respective of a second target language.

7. The method of claim 1, wherein the identification of matching concepts is performed by the plurality of computational cores of the natural liquid architecture.

8. A non-transitory computer readable medium having stored thereon instructions for causing one or more processing units to execute the method according to claim 1.

9. A system for speech to speech translation, comprising:

a processing element;

an interface coupled to the processing element, wherein the interface is configured to receive at least one audio signal; and

a memory communicatively connected to the processing element, wherein the memory contains instructions that, when executed by the processing element, configure the processing element to;

identify a first concept in the received at least audio input;

identify a first language based on the first concept identified for the received audio signal;

identify a first plurality of concepts in the first language, wherein the first plurality of concepts is statistically proximate to the first concept and previously matched to a second plurality of concepts, wherein the second plurality of concepts is in the target language; and

identify a second concept statistically proximate to the second plurality of concepts, wherein the statistical proximity is determined by use of a threshold in order to determine a match respective of the first concept and the second concept, wherein the second concept is respective of a target language.

10. The system of claim 9, wherein the processing element is configured to execute a plurality of computational cores of a natural liquid architecture.

11. The system of claim 10, the system is further configured to:

determine a match respective of the first concept and a third concept, wherein the third concept is respective of at least a second target language.

12. The system of claim 9, wherein the received audio signal is at least one of:

a digital representation of an audio signal, and a direct feed from at least one microphone device.

13. The system of claim 9, wherein a plurality of audio signals is received respective of a single source.

14. The system of claim 13, wherein the signature is generated respective of any one of:

the entire audio input, a part of the audio input, and a combination of entire or partial audio inputs.

15. The system of claim 9, wherein the system is further configured to:

generate at least one signature respective of the received audio signal and match the generated at least one signature to at least another signature from a signature database.