Audio classifier that includes analog signal voice activity detection and digital signal voice activity detection

1. An audio classifier comprising:

a first processor having hard-wired logic configured to receive an audio signal and detect audio activity from the audio signal, wherein the first processor is an analogue processor; and

a second processor having reconfigurable logic configured to classify the audio signal as a type of audio signal in response to the first processor detecting audio activity, wherein the second processor is a digital processor;

in which the second processor is a voice activity detector, in which the second processor is configured to classify the audio signal as either speech or not speech;

in which the second processor is configured to determine at least three features of the audio signal and classify the audio signal as either speech or not speech in accordance with the at least three features, in which the at least three features comprises:

short term energy;

tonal power ratio; and

spectral crest factor;

wherein the second processor is configured to compute the tonal power ratio and the crest factor using common computed quantities and is configured to classify the audio signal as speech only if each of the short term energy, the tonal power ratio, and the spectral crest factor exceeds a corresponding feature-specific predetermined threshold.

2. The audio classifier of claim 1 in which the second processor is configured to perform the classification in conjunction with software or firmware.

3. The audio classifier of claim 1 comprising an analogue-to-digital converter configured to digitize the analogue audio signal, in which the second processor is configured to classify a digitized audio signal.

4. The audio classifier of claim 1 in which the at least three features further comprises a zero crossing rate.

5. The audio classifier of claim 1 in which the second processor is configured to generate one or more metrics associated with the audio signal.

6. The audio classifier of claim 5 in which the metrics include an average background level of the audio signal over an interval of time.

7. The audio classifier of claim 1 in which the first processor is configured to determine an energy of the audio signal in order to detect audio activity.

8. The audio classifier of claim 1 in which the first processor is configured to operate on an analogue audio signal.

9. An audio recognition system comprising:

the audio classifier having;

a first processor having hard-wired logic configured to receive an audio signal and detect audio activity from the audio signal, wherein the first processor is an analogue processor; and

a second processor having reconfigurable logic configured to classify the audio signal as a type of audio signal in response to the first processor detecting audio activity, wherein the second processor is a digital processor;

in which the second processor is a voice activity detector, in which the second processor is configured to classify the audio signal as either speech or not speech;

in which the second processor is configured to determine at least three features of the audio signal and classify the audio signal as either speech or not speech in accordance with the at least three features, in which the at least three features comprises:

short term energy;

tonal power ratio; and

crest factor; and

wherein the second processor is configured to compute the tonal power ratio and the crest factor using common computed quantities and is configured to classify the audio signal as speech only if each of the short term energy, the tonal power ratio, and the spectral crest factor exceeds a corresponding feature-specific predetermined threshold;

an audio recognition unit configured to determine one or more audio segments from the audio signal in response to the second processor classifying the audio as a particular type of audio signal.

10. The audio recognition system of claim 9 in which the audio recognition system is a voice recognition system and the audio recognition unit is a voice recognition unit configured to determine one or more words from the audio signal in response to the second processor classifying the audio signal as a voice signal.

11. The audio recognition system of claim 9 in which the audio recognition system is a music recognition system and the audio recognition unit is a music recognition unit configured to recognize a piece of music from the audio signal in response to the second processor classifying the audio signal as music.

12. A mobile computing device comprising the voice recognition system of claim 9 .

13. An audio classifier comprising:

a first processor having hard-wired logic configured to receive an audio signal and detect audio activity from the audio signal, wherein the first processor is an analogue processor; and

a second processor having reconfigurable logic configured to classify the audio signal as a type of audio signal in response to the first processor detecting audio activity, wherein the second processor is a digital processor;

in which the second processor is a voice activity detector, in which the second processor is configured to classify the audio signal as either speech or not speech;

in which the second processor is configured to determine at least three features for each frame of the audio signal and classify the audio signal as either speech or not speech in response to the at least three features, wherein the at least three features include short-term energy, spectral crest factor, and tonal power ratio; and

wherein the second processor is configured to compute the tonal power ratio and the crest factor using common computed quantities and is configured to classify the audio signal as speech only if each of the short term energy, the tonal power ratio, and the spectral crest factor exceeds a corresponding feature-specific predetermined threshold;

wherein the common computed quantity used by the second processor to compute the tonal power ratio and the crest factor comprises M t [n], where M t [n] is the magnitude of the Fourier transform at frame t and frequency bin n.

14. The audio classifier of claim 1 wherein the common computed quantity used by the second processor to compute the tonal power ratio and the crest factor comprises M t [n], where M t [n] is the magnitude of the Fourier transform at frame t and frequency bin n.