Mobile speech-to-speech interpretation system

Patent metadata

Field	Value
Publication number	US-9251142-B2
Application number	US-201414326283-A
Country	US
Kind code	B2
Filing date	Jul 8, 2014
Priority date	Jan 9, 2008
Publication date	Feb 2, 2016
Grant date	Feb 2, 2016

Abstract

Interpretation from a first language to a second language via one or more communication devices is performed through a communication network (e.g. phone network or the internet) using a server for performing recognition and interpretation tasks, comprising the steps of: receiving an input speech utterance in a first language on a first mobile communication device; conditioning said input speech utterance; first transmitting said conditioned input speech utterance to a server; recognizing said first transmitted speech utterance to generate one or more recognition results; interpreting said recognition results to generate one or more interpretation results in an interlingua; mapping the interlingua to a second language in a first selected format; second transmitting said interpretation results in the first selected format to a second mobile communication device; and presenting said interpretation results in a second selected format on said second communication device.

First claim

We claim:

1. A communication device comprising:
a language input device configured to detect a first language signal associated with a first language; and
a recognition and interpretation engine coupled with the language input device and configured to:
obtain the first language signal from the language input device;
generate a first recognition result set from the first language signal according to at least one of a grammar and statistical language model of the first language, said language model comprising a mobile interference model;
generate an improved recognition result set from the first recognition result set by rescoring the first recognition result set according to a domain-specific language model;
generate at least one interpretation result from the improved recognition results set;
map the at least one interpretation result to a second language representation of a second language; and
cause an output device to present an output interpretation according to the second language derived from the second language representation.

2. The device of claim 1 , wherein the output interpretation comprises at least one of the following data formats: text, audio, images, and video.

3. The device of claim 1 , wherein the first language signal comprises an audio signal.

4. The device of claim 1 , wherein the first language signal comprises a voice signal.

5. The device of claim 1 , wherein the first language signal comprises a speech signal.

6. The device of claim 1 , further comprising a mobile device that includes the language input device, and the recognition and interpretation engine.

7. The device of claim 1 , wherein the output device comprises a second, different mobile device.

8. The device of claim 1 , wherein the output device comprises a mobile communication device.

9. The device of claim 1 , further comprising a server that includes the language input device and recognition and interpretation engine.

10. The device of claim 1 , wherein the domain-specific language model includes an interpreted “n best list”.

11. The device of claim 1 , wherein the domain-specific language model represents a user reject list of at least some of the first recognition results.

12. The device of claim 1 , wherein the domain-specific language model include an interpretation lattice result.

13. The device of claim 1 , wherein the domain-specific language model includes a location.

14. The device of claim 1 , wherein the interference model represents a model of at least one the following: a loss of the first language signal, a weak first language signal, a user profile, and a domain.

15. The device of claim 1 , wherein the domain specific model is a user selectable domain.

16. The device of claim 1 , wherein the language input device comprises a microphone.

17. The device of claim 1 , wherein the domain-specific language model relates to a pharmacist.

18. The device of claim 1 , wherein the domain-specific language model relates to a nurse.

19. The device of claim 1 , wherein the domain-specific language model relates to a tour guide.

20. The device of claim 1 , wherein the domain-specific language model relates to a sign language.

21. The device of claim 1 , wherein the grammar and statistical language models comprise empirically determined mixtures and weightings.

22. The device of claim 1 , wherein the second language representation comprises an language independent interlingua.

23. The device of claim 1 , wherein the second language comprises a sign language.

Assignees

• Nant Holdings Ip Llc

Inventors

• Ehsani Farzad
• Master Demitrios
• Zuber Elaine Drom

Classifications

• G06F40/58 Primary

  Use of machine translation, e.g. for multi-lingual retrieval, for server-side translation for client devices or for real-time translation · CPC title

• G06F40/51

  Translation evaluation · CPC title

• G10L15/26

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L13/00 Primary

  Speech synthesis; Text to speech systems · CPC title

• G06F40/40

  Processing or translation of natural language (natural language analysis G06F40/20; semantic analysis G06F40/30) · CPC title