DETECTION OF ACOUSTIC IMPULSE EVENTS IN VOICE APPLICATIONS USING A NEURAL NETWORK

• US 20180102136A1
• Filed: 05/01/2017
• Published: 04/12/2018
• Est. Priority Date: 10/11/2016
• Status: Active Grant

• Current Assignee: Cirrus Logic Incorporated
• Original Assignee: Cirrus Logic International Semiconductor Ltd. (Cirrus Logic Incorporated)
• Inventors: EBENEZER, Samuel Pon Varma
• Granted Patent: US 10,475,471 B2
• Time in Patent Office: Days
• CPC Class Codes: G10L 15/02 Feature extraction for speech recognition; Selection of recognition unit
• CPC Class Codes: G10L 15/16 using artificial neural networks
• CPC Class Codes: G10L 2021/02166 Microphone arrays; Beamforming
• CPC Class Codes: G10L 21/02 Speech enhancement, e.g. noise reduction or echo cancellation reducing echo effects in line transmission systems H04B3/20; echo suppression in hands-free telephones H04M9/08
• CPC Class Codes: G10L 21/0216 characterised by the method used for estimating noise
• CPC Class Codes: G10L 21/0232 Processing in the frequency domain
• CPC Class Codes: G10L 25/21 the extracted parameters being power information
• CPC Class Codes: G10L 25/30 using neural networks
• CPC Class Codes: G10L 25/78 Detection of presence or absence of voice signals switching of direction of transmission by voice frequency in two-way loud-speaking telephone systems H04M9/10
• CPC Class Codes: G10L 25/84 for discriminating voice from noise

Abstract

In accordance with embodiments of the present disclosure, an integrated circuit for implementing at least a portion of an audio device may include an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device, a microphone input configured to receive an input signal indicative of ambient sound external to the audio device, and a processor configured to implement an impulsive noise detector. The impulsive noise detector may comprise a plurality of processing blocks for determining a feature vector based on characteristics of the input signal and a neural network for determining based on the feature vector whether the impulsive event comprises a speech event or a noise event.

Claims

1. An integrated circuit for implementing at least a portion of an audio device, comprising:

an audio output configured to reproduce audio information by generating an audio output signal for communication to at least one transducer of the audio device;

a microphone input configured to receive an input signal indicative of ambient sound external to the audio device; and

a processor configured to implement an impulsive noise detector comprising;

a plurality of processing blocks for determining a feature vector based on characteristics of the input signal; and

a neural network for determining based on the feature vector whether an impulsive event comprises a speech event or a noise event.

2. The integrated circuit of claim 1, wherein the processor is further configured to modify a characteristic associated with the audio information in response to detection of a noise event.

3. The integrated circuit of claim 2, wherein the characteristic comprises one or more of an amplitude of the audio information and spectral content of the audio information.

4. The integrated circuit of claim 2, wherein the characteristic comprises at least one coefficient of a voice-based processing algorithm including at least one of a noise suppressor, a background noise estimator, an adaptive beamformer, dynamic beam steering, always-on voice, and a conversation-based playback management system.

5. The integrated circuit of claim 1, wherein the feature vector comprises statistics indicative of harmonicity, sparsity, and degree of temporal modulation of a signal spectrum of the input signal to determine whether the impulsive event comprises a speech event or a noise event.

6. The integrated circuit of claim 1, wherein the feature vector comprises a statistic indicative of an acoustic energy present in the input signal.

7. The integrated circuit of claim 1, wherein the feature vector comprises a statistic indicative of an occurrence of a signal burst event of the input signal.

8. The integrated circuit of claim 1, wherein the feature vector comprises a statistic indicative of mel cepstral coefficients of the input signal.

9. The integrated circuit of claim 1, further comprising a pre-processing block interfaced between the plurality of processing blocks and the neural network and configured to:

augment the feature vector with at least one previous frame of the feature vector to generate an augmented feature vector;

normalize statistics of the feature vector with respect to each other; and

reduce feature dimensions of the statistics of the feature vector prior to training by the neural network.

10. A method for impulsive noise detection comprising:

receiving an input signal indicative of ambient sound external to an audio device;

determining a feature vector based on characteristics of the input signal;

using a neural network to determine based on the feature vector whether an impulsive event comprises a speech event or a noise event; and

reproducing audio information by generating an audio output signal for communication to at least one transducer of an audio device based on the input signal and the determination of whether the impulsive event comprises a speech event or a noise event.

11. The method of claim 10, further comprising modifying a characteristic associated with the audio information in response to detection of a noise event.

12. The method of claim 11, wherein the characteristic comprises one or more of an amplitude of the audio information and spectral content of the audio information.

13. The method of claim 11, wherein the characteristic comprises at least one coefficient of a voice-based processing algorithm including at least one of a noise suppressor, a background noise estimator, an adaptive beamformer, dynamic beam steering, always-on voice, and a conversation-based playback management system.

14. The method of claim 10, wherein the feature vector comprises statistics indicative of harmonicity, sparsity, and degree of temporal modulation of a signal spectrum of the input signal to determine whether the impulsive event comprises a speech event or a noise event.

15. The method of claim 10, wherein the feature vector comprises a statistic indicative of an acoustic energy present in the input signal.

16. The method of claim 10, wherein the feature vector comprises a statistic indicative of an occurrence of a signal burst event of the input signal.

17. The method of claim 10, wherein the feature vector comprises a statistic indicative of mel cepstral coefficients of the input signal.

18. The method of claim 10, further comprising pre-processing the feature vector prior to using the neural network, wherein pre-processing comprises:

augmenting the feature vector with at least one previous frame of the feature vector to generate an augmented feature vector;

normalizing statistics of the feature vector with respect to each other; and

reducing feature dimensions of the statistics of the feature vector prior to training by the neural network.