METHOD AND APPARATUS FOR ELEMENT IDENTIFICATION IN A SIGNAL

• US 20130262116A1
• Filed: 03/27/2012
• Published: 10/03/2013
• Est. Priority Date: 03/27/2012
• Status: Active Grant

• Current Assignee: NovoSpeech Ltd.
• Original Assignee: NovoSpeech Ltd.
• Inventors: Ben-Ezra, Yossef
• Granted Patent: US 8,725,508 B2
• Time in Patent Office: Days
• US Class Current: 704/254
• CPC Class Codes: A61B 5/7246 using correlation, e.g. template matching or determination of similarity
• CPC Class Codes: G10L 15/04 Segmentation; Word boundary detection

Abstract

A computer-implemented method and apparatus for searching for an element sequence, the method comprising: receiving a signal; determining an initial segment of the signal; inputting the initial segment into an element extraction engine to obtain a first element sequence; determining one or more second segments, each of the second segments at least partially overlapping with the initial segment; inputting the second segments into the element extraction engine to obtain at least one second element sequence; and searching for an element subsequence common to at least a predetermined number of sequences of the first element sequence and the second element sequences.

Claims

1. A computer-implemented method performed by a computerized device, comprising:

receiving a signal;

determining an initial segment of the signal;

inputting the initial segment into an element extraction engine to obtain a first element sequence;

determining at least one second segment, the at least one second segment at least partially overlapping with the initial segment;

inputting the at least one second segment into the element extraction engine to obtain at least one second element sequence; and

searching for an element subsequence common to at least a predetermined number of sequences of the first element sequence and the at least one second element sequence.

2. The computer-implemented method of claim 1, further comprising outputting the element subsequence, subject to finding the element subsequence.

3. The computer-implemented method of claim 1, further comprising repeating determining at least one second segment, inputting the at least one second segment into the element extraction engine, and searching for the element subsequence.

4. The computer-implemented method of claim 1, further comprising repeating inputting the at least one second segment into the element extraction engine, and searching for the element subsequence, subject to not finding the element subsequence.

5. The computer-implemented method of claim 4, further comprising determining whether a stopping criterion has been met, and repeating inputting the at least one second segment into the element extraction engine, and searching for the element subsequence, only if the stopping criteria has not been met.

6. The computer-implemented method of claim 5, wherein the stopping criteria is selected from the group consisting of:

a predetermined number of segments has been selected and the initial segment is fully covered by the at least one second segment.

7. The computer-implemented method of claim 1, wherein the initial segment is determined using a method selected from the group consisting of:

energy-based;

autocorrelation;

zero crossing; and

arbitrary determination.

8. The computer-implemented method of claim 1, wherein the element extraction engine is selected from the group consisting of:

a Gaussian mixture model, an artificial neural network, a support vector machine, and a hidden Markov model.

9. The computer-implemented method of claim 1, wherein the signal is selected from the group consisting of:

an audio signal, a video signal, a motion signal, a seismic signal, ECG signal, and a bio-medical signal.

10. The computer-implemented method of claim 1, wherein the element is a phoneme.

11. An apparatus having a processing unit and a storage device, the apparatus comprising:

a signal receiving component for receiving a signal;

an initial segmentation component for determining an initial segment of the signal;

an additional segment determination component for determining at least one second segment, the at least one second segment at least partially overlapping with the initial segment;

an element extraction engine for receiving the initial segment and the at least one second segment, and providing a first element sequence and at least one second element sequence; and

an element sequence matching component for searching for a element subsequence common to at least a predetermined number of sequences of the first element sequence and the at least one second element sequence.

12. The apparatus of claim 11, wherein the element extraction engine is selected from the group consisting of:

a Gaussian mixture model, an artificial neural network, a support vector machine, and a hidden Markov model.

13. The apparatus of claim 11, wherein the signal is selected from the group consisting of:

an audio signal, a video signal, a motion signal, a seismic signal, ECG signal, and a bio-medical signal.

14. The apparatus of claim 11, wherein the element is a phoneme.

15. The apparatus of claim 11, further comprising a data and control flow management component.

16. A computer program product comprising:

a non-transitory computer readable medium;

a first program instruction for receiving a signal;

a second program instruction for determining an initial segment of the signal;

a third program instruction for inputting the initial segment into an element extraction engine to obtain a first element sequence;

a fourth program instruction for determining at least one second segment, the at least one second segment at least partially overlapping with the initial segment;

a fifth program instruction for inputting the at least one second segment into the element extraction engine to obtain at least one second element sequence; and

a sixth program instruction for searching for an element subsequence common to at least a predetermined number of sequences of the first element sequence and the at least one second element sequences,

wherein said first, second, third, fourth, fifth and sixth program instructions are stored on said non-transitory computer readable medium.