Motorola Corporation

Mark Thomson

Michael John Smithers

Simon Boland

Anton Madievski

Julien Epps

Zhenjie Wu

Trym Holter

Speech feature vectors () are provided and utilized to develop a corresponding estimated speaker dependent speech feature space model () (in one embodiment, it is not necessary that this model () have defined correlations with the verbal content of the represented speech itself). A model alignment unit () then contrasts this model () against the contents of a speaker independent speech feature space model () to provide alignment indices to a transformation estimation unit (). In one embodiment, these alignment indices are based, as least in part, upon a measure of the differences between likelihoods of occurrence for the elements that comprise the constituency of these models. The transformation estimation unit () utilizes these alignment indices to provide transformation parameters to a model transformation unit () that uses such parameters to transform a speaker independent speech recognition model set () and yield a resultant speaker adapted speech recognition model set ().

Method and apparatus for providing a speaker adapted speech recognition model set

An encoder () and system () for processing a sequence of input vectors (yto y) obtained from a speech signal. A filter () has both a current slowly evolving filter estimate output () and a previous slowly evolving filter estimate output (). The current slowly evolving filter estimate output () provides vectors of current filtered estimate element values of a slowly evolving component of the sequence of input vectors (yto y) and the previous slowly evolving filter estimate output () provides vectors of previous filtered estimate element values of the slowly evolving component of said sequence of input vectors (yto y). There is also a parameter estimator (), smoother module () and slowly evolving component encoder () that provides a digitized encoded slowly evolving component of the speech signal.

Vector estimation system, method and associated encoder

An encoder and associated vector estimation method and system () for processing a sequence of input vectors (yto y) each comprising a plurality of elements. The vector estimation system () has a digital filter () with a filter vector input () for receiving said sequence of input vectors (yto y) and a predictor gain input () for controlling characteristics of the filter (). The filter () is a Kalman filter and has both a current slowly evolving filter estimate output () and a previous slowly evolving filter estimate output (). The current slowly evolving filter estimate output () provides a current filtered estimate value of a slowly evolving component of said sequence of input vectors (yto y) and the previous slowly evolving filter estimate output () provides a previous filtered estimate value of the slowly evolving component of said sequence of input vectors (yto y). There is also a parameter estimator () having an estimator vector input () for receiving said sequence of input vectors (yto y) and a previous slowly evolving filter estimate input () coupled to the previous slowly evolving filter estimate output (). The parameter estimator further includes a predictor gain output coupled () to the predictor gain input (). In operation, when the vector estimation system () receives a current input vector that is one of the sequence of said input vectors (yto y), the parameter estimator () provides a current predictor gain value at the predictor gain output () thereby modifying the current filtered estimate value. The current predictor gain value is dependent upon both the previous filtered estimate value and the current input vector.

A method () and electronic device () for signal separation of mixed signals provided by sensors (), the mixed signals resulting from the sensors () detecting respective mixed waveforms comprising a plurality of source waveforms originating from waveform generating sources mixed in a mixing environment (). The method () and device (), in use, provide for configuring () communication between a processor () and a plurality of the sensors () in the mixing environment (), the configuring being effected dynamically depending upon variations in the number of sensors () in the environment. At a receiving step () the processor () receives respective mixed signals from the sensors () and a step of determining () un-mixing parameters for the environment based on the number of sensors () is then effected. Thereafter, a step of applying selectively () applies the un-mixing parameters to at least one of said mixed signals to thereby separate at least one of the mixed signals and provide at least one output source signal associated with one of the sensors (), the output source signal being indicative of an unmixed one of the source waveforms.

Growing community of inventors

Carlton, Australia

Mark Thomson