Source normalization training for HMM modeling of speech
First Claim
Patent Images
1. 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;
b1) estimation of intermediate quantities;
b2) performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability;
b3) deriving mean vector and bias vector;
b4) solving jointly for mean vector and bias vector using linear equations and determining variances and transformation;
b5) 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 b1 -b5.
2 Assignments
0 Petitions
Accused Products
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.
37 Citations
6 Claims
-
1. 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; b1) estimation of intermediate quantities; b2) performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability; b3) deriving mean vector and bias vector; b4) solving jointly for mean vector and bias vector using linear equations and determining variances and transformation; b5) 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 b1 -b5. - View Dependent Claims (2, 3, 4, 5)
-
-
6. 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; b1) estimation of intermediate quantities; b2) performing re-estimation to determine initial state probability, transition probability, mixture component probability and environment probability; b3) deriving mean vector and bias vector; b4) solving jointly for mean vector and bias vector using linear equations and determining variances and transformation; b5) 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 b1 -b5 ; receiving an input signal; and comparing said input signal to said new model.
-
Specification