Patent · US Active

Custom language models for audio content

US8447608B1 · kind B1 · utility

39Cited by

2References

40Claims

0Family size

Assignee

Adobe Systems Incorporated · US

Inventors

Walter Chang · San Jose, US
Michael J. Welch · Los Angeles, US

Key dates

Filing date	Dec 10, 2008
Grant date	May 21, 2013
Priority date	—
Expiry date	Oct 26, 2031

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/228
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

This specification describes technologies relating to generating custom language models for audio content. In some implementations, a computer-implemented method is provided that includes the actions of receiving a collection of source texts; identifying a type from a collection of types for each source text, each source text being associated with a particular type; generating, for each identified type, a type-specific language model using the source texts associated with the respective type; and storing the language models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.