Back to results
US 6,151,573 AGranted
Source normalization training for HMM modeling of speech
AssigneeTexas Instruments Incorporated
InventorYifan Gong
Life of this patent
Estimating the term…
Abstract
A maximum likelihood (ML) linear regression (LR) solution to environment normalization is provided where the environment is modeled as a hidden (non-observable) variable. By application of an expectation maximization algorithm and extension of Baum-Welch forward and backward variables (Steps 23a-23d) a source normalization is achieved such that it is not necessary to label a database in terms of environment such as speaker identity, channel, microphone and noise type.
Claims6
An improved speech recognition system comprising:
- a speech recognizer;
- and
- a source normalization model coupled to said recognizer;
- said model derived by a method of source normalization training for HMM modeling of speech comprising the steps of:
- (a) providing an initial model;
- (b) on said initial model or following new models performing the following steps to get a new model:
- b.sub.1) estimation of intermediate quantities;
- b.sub.2) performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability;
- b.sub.3) deriving mean vector and bias vector;
- b.sub.4) solving jointly for mean vector and bias vector using linear equations and determining variances and transformation;
- b.sub.5) replacing old model parameters for the calculated ones;
- and
- (c) determining after a new model is formed if it differs significantly from the previous model and if so repeating steps b.sub.1 -b.sub.5.
10 more elements
A method of speech recognition comprising:
- source normalization training for HMM modeling of speech comprising the steps of:
- (a) providing an initial model;
- (b) on said initial model or following new models performing the following steps to get a new model:
- b.sub.1) estimation of intermediate quantities;
- b.sub.2) performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability;
- b.sub.3) deriving mean vector and bias vector;
- b.sub.4) solving jointly for mean vector and bias vector using linear equations and determining variances and transformation;
- b.sub.5) replacing old model parameters for the calculated ones;
- and
- (c) determining after a new model is formed if it differs significantly from the previous model and if so repeating steps b.sub.1 -b.sub.5 ;
- receiving an input signal;
- and
- comparing said input signal to said new model.
10 more elements
Dependencies are inferred from the claim text.