Methods and systems for obtaining language models for transcribing communications

A system for producing speech recognition results on a receiving device, comprising:

• a sending device, including:
• a first memory containing a first program for performing automatic speech recognition;
• and
• a first processor which, when executing the first program, performs a first operation that includes:
• receiving audio,
• creating first speech recognition results using a first language model and the audio, wherein the first language model represents information stored on the sending device, and
• sending the first speech recognition results;
• a receiving device, including:
• a second memory containing a second program for performing automatic speech recognition;
• and
• a second processor which, when executing the second program, performs a second operation that includes:
• receiving first speech recognition results, and
• creating second speech recognition results using a second language model and the first speech recognition results, wherein the second language model represents information stored on the receiving device.

A computer-readable medium containing a program which, when executed, performs a method of producing and presenting speech recognition results, the method comprising:

• receiving first speech recognition results;
• obtaining a language model, wherein the language model represents information stored on the device;
• using the first speech recognition results and the language model to generate second speech recognition results;
• and
• presenting the second speech recognition results to a user.