Motorola Corporation

Anton Madievski

Jianming Song

Yaxin Zhang

Mark Thomson

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.

Method and device for signal separation of a mixed signal

A voiced/unvoiced speech classifier ( ) includes a speech segmentor ( ) which segments an input digitized speech waveform into frames of speech and a band-pass filter ( ) which filters the frames of speech. A relative energy generator ( ) generates a relative energy value for each filtered frame of speech and a decision parameter generator ( ) including an autocorrelation calculator ( ) and a pitch calculator ( ) generates a decision parameter based on an autocorrelation function and a pitch frequency index for the filtered frames of speech. A normalized energy calculator ( ) adjusts the threshold and then normalizes the relative energy. A comparator ( ) provides a signal indicative of whether a frame of speech is voiced speech or unvoiced speech depending on a comparison of the decision parameter and the normalized relative energy value for each filtered frame of speech.

Voiced/unvoiced speech classifier

A method and apparatus for speech recognition involves classifying ( ) a digitized speech segment according to whether the speech segment comprises voiced or unvoiced speech and utilizing that classification to generate tonal feature vectors ( ) of the speech segment when the speech is voiced. The tonal feature vectors are then combined ( ) with other non-tonal feature vectors ( ) to provide speech feature vectors. The speech feature vectors are compared ( ) with previously stored models of speech feature vectors ( ) for different segments of speech to determine which previously stored model is a most likely match for the segment to be recognized.

Growing community of inventors

Maroubra, Australia

Anton Madievski