Patent · US Expired

Method and array for introducing temporal correlation in hidden markov models for speech recognition

US6832190B1 · kind B1 · utility

13Cited by

4References

7Claims

0Family size

Assignee

Siemens Aktiengesellschaft · DE

Inventors

Jochen Junkawitsch · Hersbruck, DE
Harald Höge · Gauting, DE

Key dates

Filing date	Nov 10, 2000
Grant date	Dec 14, 2004
Priority date	—
Expiry date	Nov 10, 2020

Classification

Technology area (CPC G)Physics
CPC primaryG10L2015/088
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

In the recognition of spoken language, phonemes of the language are modelled by hidden Markov models. A modified hidden Markov model includes a conditional probability of a feature vector dependent on chronologically preceding feature vectors and, optionally, additionally comprises a conditional probability of a respectively current status. A global search for recognizing a word sequence in the spoken language is implemented with the modified hidden Markov model.

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