User independent, real-time speech recognition system and method

• US 5,873,062 A
• Filed: 01/09/1997
• Issued: 02/16/1999
• Est. Priority Date: 11/14/1994
• Status: Expired due to Fees

• Current Assignee: Fonix Corp.
• Original Assignee: Fonix Corp.
• Inventors: Hansen, C. Hal, Shepherd, Dale Lynn, Moncur, Robert Brian
• Primary Examiner(s): Hudspeth, David R.
• Assistant Examiner(s): Chawan, Vijay B.
• Application Number:
  US08/781,625
• Time in Patent Office: 768 Days
• Field of Search: 395/2.63, 395/2.91, 395/2.92, 395/2.93, 395/2.94, 395/2.09, 704/254, 704/270, 704/500, 704/501, 704/502, 704/503, 704/504, 704/200, 704/251, 704/255
• US Class Current: 704/254
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/10 using distance or distortion measures between unknown speech and reference templates
• CPC Class Codes: G10L 25/09 the extracted parameters being zero crossing rates
• CPC Class Codes: G10L 25/18 the extracted parameters being spectral information of each sub-band
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence

Abstract

A system and method for identifying the phoneme sound types that are contained within an audio speech signal is disclosed. The system includes a microphone and associated conditioning circuitry, for receiving an audio speech signal and converting it to a representative electrical signal. The electrical signal is then sampled and converted to a digital audio signal with a digital-to-analog converter. The digital audio signal is input to a programmable digital sound processor, which digitally processes the sound so as to extract various time domain and frequency domain sound characteristics. These characteristics are input to a programmable host sound processor which compares the sound characteristics to standard sound data. Based on this comparison, the host sound processor identifies the specific phoneme sounds that are contained within the audio speech signal. The programmable host sound processor further includes linguistic processing program methods to convert the phoneme sounds into English words or other natural language words. These words are input to a host processor, which then utilizes the words as either data or commands.

Claims

1. A computer program product for use in a computerized sound recognition system that is adapted for receiving an audio speech signal and converting the audio speech signal into a representative audio electrical signal that is digitized, the computer program product comprising:

a computer readable medium for storing computer readable code means which, when executed by the computerized sound recognition system, will enable the system to identify phoneme sound types that are contained within the audio speech signal; and

wherein the computer readable code means is comprised of computer readable instructions for causing the computerized sound recognition system to execute a method comprising the steps of;

receiving an audio speech signal;

converting the audio speech signal into a representative audio electrical signal;

digitizing the audio electrical signal at a predetermined sampling rate so as to produce a digitized audio signal;

performing a time domain analysis on segmentized portions of the digitized audio signal so as to identify at least one time domain sound characteristic of said audio speech signal;

filtering the segmentized portions of the digitized audio signal using a plurality of filter bands having predetermined high and low cutoff frequencies;

measuring at least one frequency domain sound characteristic of each of said filtered segmentized portions; and

based on the at least one time domain characteristic and the at least one frequency domain characteristic, identifying at least one phoneme sound type contained within the audio speech signal.

2. A computer program product as defined in claim 1, wherein the at least one time domain characteristic includes at least one of the following:

an average amplitude of the audio speech signal;

an absolute difference average of the audio speech signal; and

a zero crossing rate of the audio speech signal.

3. A computer program product as defined in claim 1, wherein the at least one frequency domain characteristic includes at least one of the following:

a frequency of at least one of said filtered segmentized portions; and

an amplitude of at least one of said filtered segmentized portions.

4. A computer program product for use in a computerized sound recognition system that is adapted for receiving an audio speech signal and converting the audio speech signal into a representative audio electrical signal that is digitized, the computer program product comprising:

a computer readable medium for storing computer readable code means which, when executed by the computerized sound recognition system, will enable the system to identify phoneme sound types that are contained within the audio speech signal; and

wherein the computer readable code means is comprised of computer readable instructions for causing the computerized sound recognition system to execute a method comprising the steps of;

(a) receiving an audio speech signal;

(b) converting the audio speech signal into a representative audio electrical signal;

(c) digitizing the audio electrical signal at a predetermined sampling rate so as to produce a digitized audio signal that is segmentized to form a plurality of separate time sliced signals;

(d) performing a time domain analysis on the digitized audio signal so as to identify at least one time domain sound characteristic of said audio speech signal;

(e) using a plurality of filter bands having predetermined cutoff frequencies to successively filter the time sliced signals of the digitized audio signal;

(f) measuring at least one frequency domain sound characteristic from each of said filtered time sliced signals; and

(g) based on the at least one time domain characteristic and the at least one frequency domain characteristic, identifying at least one phoneme sound type contained within the audio speech signal.

5. A computer program product as defined in claim 4, wherein the said at least one time domain characteristic includes at least one of the following:

an average amplitude of the audio speech signal;

an absolute difference average of the audio speech signal; and

a zero crossing rate of the audio speech signal.

6. A computer program product as defined in claim 5, wherein the said at least one frequency domain characteristic includes at least one of the following:

a frequency of at least one of said filtered time sliced signals; and

an amplitude of at least one of said filtered time sliced signals.

7. A computer program product as defined in claim 6, wherein the at least one phoneme sound type contained within the audio speech signal is identified by comparing the at least one measured frequency domain characteristic to a plurality of sound standards each having an associated phoneme sound type and at least one corresponding standard frequency domain characteristic, wherein the at least one identified sound type is the sound standard type having a standard frequency domain characteristic that matches the measured frequency domain characteristic most closely.

8. A sound recognition system for identifying the phoneme sound types that are contained within an audio speech signal, the sound recognition system comprising:

a microphone capable of receiving the audio speech signal and converting it to an audio electrical signal;

audio processing circuitry, electrically connected to the microphone, that conditions the audio electrical signal so that it is placed in a representative electrical form that is suitable for digital sampling;

an analog-to-digital conversion circuit, electrically connected to the audio processing circuitry, that is capable of digitizing the audio electrical signal at a predetermined sampling rate so as to produce a digitized audio signal;

a plurality of bandpass filters, each having a predetermined high and low cutoff frequency, and through each of which segmentized time slices of the digitized audio signal are passed;

a sound recognition processor circuit comprising;

a programmable digital sound processor capable of performing the following programmable steps;

(a) performing a time domain analysis on the segmentized time slices of the digitized audio signal so as to identify at least one time domain sound characteristic of the audio speech signal; and

(b) measuring at least one frequency domain sound characteristic determined as a result of the segmentized time slices being filtered by the plurality of bandpass filters; and

a host sound processor capable of performing the following programmable steps;

(a) identifying at least one phoneme sound type contained within the audio speech signal based on the at least one time domain characteristic and the at least one frequency domain characteristic; and

(b) translating said at least one phoneme sound type into at least one representative word of a preselected language.

9. A sound recognition system as defined in claim 8, wherein the digital sound processor the host sound processor are comprised of a single programmable device.

10. A sound recognition system as defined in claim 8, wherein the plurality of bandpass filters are programmably implemented on the digital sound processor.

11. A sound recognition system as defined in claim 8, wherein the audio processing circuitry comprises:

signal amplifier that is capable of amplifying the audio electrical signal to a predetermined level;

a limiting circuit that is capable of limiting the level of the amplified audio electrical signal to a predetermined output level; and

an anti-aliasing filter circuit, connected to the limiting circuit, for limiting the audio electrical signal to a predetermined maximum frequency of interest.