Voiced/unvoiced speech classifier

• US 6,640,208 B1
• Filed: 09/12/2000
• Issued: 10/28/2003
• Est. Priority Date: 09/12/2000
• Status: Active Grant

• Current Assignee: Google Technology Holdings LLC (Alphabet Inc.)
• Original Assignee: Motorola, Inc. (Motorola Solutions, Inc.)
• Inventors: Song, Jianming, Zhang, Yaxin, Madievski, Anton
• Primary Examiner(s): Dorvil, Richemond
• Assistant Examiner(s): Azad, Abul K.
• Application Number:
  US09/659,318
• Time in Patent Office: 1,141 Days
• Field of Search: 704/205-221, 704/224
• US Class Current: 704/214
• CPC Class Codes: G10L 25/93 Discriminating between voiced and unvoiced parts of speech signals G10L25/90 takes precedence

Abstract

A voiced/unvoiced speech classifier (30) includes a speech segmentor (34) which segments an input digitized speech waveform into frames of speech and a band-pass filter (36) which filters the frames of speech. A relative energy generator (38) generates a relative energy value for each filtered frame of speech and a decision parameter generator (52) including an autocorrelation calculator (54) and a pitch calculator (56) generates a decision parameter based on an autocorrelation function and a pitch frequency index for the filtered frames of speech. A normalized energy calculator (46) adjusts the threshold and then normalizes the relative energy. A comparator (60) 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.

Claims

1. A voiced/unvoiced speech classifier comprising:

an input terminal for receiving a digitized speech signal;

a feature extractor having an input coupled to the input terminal and an output providing feature vectors of the input speech signal;

a correlator having an input coupled to the output of the feature extractor and an output providing an autocorrelation value of the feature vectors of the input speech signal;

a decision maker having a first input coupled to the output of a combiner, a second input for receiving a threshold value and an output providing a signal indicative of whether a measure of the input speech signal partly based on the autocorrelation value of the feature vectors of the input speech signal is above or below the threshold value;

a Signal to Noise Ratio (SNR) calculator having an input coupled to the input terminal and an output providing a SNR signal;

a threshold value adjuster having an input coupled to the output of the SNR calculator and an output coupled to the second input of the comparator to provide thereto the threshold value adjusted according to the SNR signal;

a signal energy calculator having an input coupled to the input terminal and an output providing an indication of the energy of the input speech signal; and

a combiner having a first Input coupled to the output of the correlator, an output coupled to the first input of the comparator and a second input coupled to the output of the signal energy calculator providing the measure of the input speech signal.

2. A voiced/unvoiced speech classifier according to claim 1, wherein the measure of the input speech signal is based at least on the autocorrelation value of the input speech signal and on the energy of the input speech signal.

3. A system for speech recognition incorporating a voiced/unvoiced speech classifier according to claim 1.

4. A system for speech coding incorporating a voiced/unvoiced speech classifier according to claim 1.

5. A voiced/unvoiced speech classifier comprising:

an input terminal for receiving a digitized speech signal;

a feature extractor having an input coupled lo the input terminal and an output providing feature vectors of the input speech signal;

a correlator having an input coupled to the output of the feature extractor and an output providing autocorrelation value of the feature vectors of the input speech signal; and

a decision maker having a first input coupled to the output of a combiner, a second input for receiving a threshold value and an output providing a signal indicative of whether a measure of the input speech signal partly based on the autocorrelation value of the feature vectors of the input speech signal is above or below the threshold value, wherein the measure (M) of the input speech signal is provided by;

6. A voiced/unvoiced speech classifier according to claim 5, wherein α

₁ has a value between 0.1 and 0.5.

7. A voiced/unvoiced speech classifier according to claim 6, wherein α

₁ has a value of 0.3.

8. A voiced/unvoiced speech classifier according to claim 5, wherein α

₂ has a value between 0.5 and 0.9.

9. A voiced/unvoiced speech classifier according to claim 8, wherein α

₂ has a value of 0.7.

10. A system for speech recognition incorporating a voiced/unvoiced speech classifier according to claim 5.

11. A system for speech coding incorporating a voiced/unvoiced speech classifier according to claim 5.

12. A voiced/unvoiced speech classifier according to claim 6, wherein α

₁ has a value of 0.3.

13. A voiced/unvoiced speech classifier according to claim 5, wherein α

₁ has a value between 0.5 and 0.9.

14. A voiced/unvoiced speech classifier according to claim 8, wherein α

₂ has a value of 0.7.

15. A voiced/unvoiced speech classifier comprising:

an input terminal for receiving a digitized speech signal;

a feature extractor having an input coupled to the input terminal and an output providing feature vectors of the input speech signal;

a correlator having an input coupled to the output of the feature extractor and an output providing an autocorrelation value of the feature vectors of the input speech signal;

a decision maker having a first input coupled to the output a combiner, a second input for receiving a threshold value and an output providing a signal indicative of whether a measure of the input speech signal partly based on the autocorrelation value of the feature vectors of the input speech signal is above or below the threshold value;

a signal energy calculator having an input coupled to the input terminal and an output providing an indication of the energy of the input speech signal; and

a combiner having a first input coupled to the output of the correlator, an output coupled to the first input of the comparator and a second input coupled to the output of the signal energy calculator providing the measure of the input speech signal, wherein the measure (M) of the input speech signal is provided by;

16. A voiced/unvoiced speech classifier according to claim 15, further comprising:

a Signal to Noise Ratio (SNR) calculator having an input coupled to the input terminal and an output providing a SNR signal; and

a threshold value adjuster having an input coupled to the output of the SNR calculator and an output coupled to the second input of the comparator to provide thereto the threshold value adjusted according to the SNR signal.

17. A voiced/unvoiced speech classifier according to claim 16, wherein α

₁ has a value between 0.1 and 0.5.