Audio processing device and a method for estimating a signal-to-noise-ratio of a sound signal
A hearing aid includes a) at least one input unit for providing a time-frequency representation Y(k,n) of an electric input signal representing sound consisting of target speech and noise signal components, where k and n are frequency band and time frame indices, respectively, b) a noise reduction system configured to b1) determine an a posteriori signal to noise ratio estimate γ(k,n) of the electric input signal, and to b2) determine an a priori signal to noise signal ratio estimate ζ(k,n) of the electric input signal from the a posteriori signal to noise ratio estimate γ(k,n) based on a recursive algorithm providing non-linear smoothing. The a posteriori signal to noise ratio estimate of said electric input signal is provided as a mixture of first and second different a posteriori signal to noise ratio estimates. The invention may be used in audio processing devices, such as hearing aids, headsets, etc.
1. A hearing aid, comprising:
at least one input unit for providing a time-frequency representation Y(k,n) of an electric input signal representing a time variant sound signal consisting of target speech signal components S(k,n) from a target sound source TS and noise signal components N(k,n) from other sources than the target sound source, where k and n are frequency band and time frame indices, respectively; and
a noise reduction system configured to:
determine an a posteriori signal to noise ratio estimate γ(k,n) of said electric input signal,
determine an a priori signal to noise ratio estimate ζ(k,n) of said electric input signal from said a posteriori signal to noise ratio estimate γ(k,n) based on a recursive algorithm comprising a recursive loop, and
determine said a priori signal to noise ratio estimate ζ(k,n) by non-linear smoothing of said a posteriori signal to noise ratio estimate γ(k,n), or a parameter derived therefrom, said non-linear smoothing being controlled by one or more bias and/or smoothing parameters,
wherein said a posteriori signal to noise ratio estimate γ(k,n) of said electric input signal Y(k,n) is provided as a combined a posteriori signal to noise ratio generated as a mixture of at least a first and a second different a posteriori signal to noise ratio estimates.
2. A hearing aid according to claim 1 wherein said first and second a posteriori signal to noise ratio estimates originate from said hearing aid and from a contra-lateral hearing aid, respectively, of a binaural hearing aid system.
3. A hearing aid according to claim 1 wherein an a priori SNR estimate of said hearing aid that forms part of a binaural hearing aid system is based on a posteriori SNR estimates from both hearing aids of the binaural hearing aid system.
4. A hearing aid according to claim 1 wherein said first a posteriori signal to noise ratio estimate is based on spatial properties of at least two microphone signals.
5. A hearing aid according to claim 1 wherein said second a posteriori signal to noise ratio estimate is based on features obtained from a single microphone signal.
6. A hearing aid according to claim 1 wherein said first and second a posteriori signal to noise estimate estimates and the combined a posteriori signal to noise ratio estimate is determined by use of supervised learning techniques.
7. A hearing aid according to claim 1 wherein said combined a posteriori signal to noise ratio estimate is determined by a neural network using said first and second a posteriori signal to noise estimate estimates as inputs.
8. A hearing aid according to claim 1 wherein said one or more bias and/or smoothing parameters are determined based on supervised learning.
9. A hearing aid according to claim 1 wherein a selector is located in the recursive loop, wherein said selector is configured to select an input to determine said one or more bias and/or smoothing parameters based on a select control parameter.
10. A hearing aid according to claim 9 wherein said select control parameter is determined using one or more neural networks.
11. A hearing aid according to claim 10 wherein said select control parameter for a given frequency index k is determined in dependence of the a posteriori and/or the a priori signal to noise ratio estimates corresponding to a multitude of frequency indices.
12. A hearing aid according to claim 11 wherein said multitude of frequency indices include one or more neighboring frequency indices.
13. A hearing aid according to claim 11 wherein said multitude of frequency indices comprises the immediately neighboring frequency indices (k−1, k, k+1).
14. A hearing aid according to claim 11 wherein said one or more neighboring frequency indices are determined according to a predefined or adaptive scheme.
15. A hearing aid according to claim 1 wherein said select control parameter for a given frequency index k is additionally determined in dependence of inputs from one or more detectors.
16. A hearing aid according to claim 15 wherein said one or more detectors comprise a general onset detector for detecting sudden changes in the time variant input sound, a wind noise detector, a voice detector, a head movement detector, a wireless transmission detector, voice detectors from microphones in other audio devices, and combinations thereof.
17. A hearing aid according to claim 15 wherein at least one of said one or more detectors is based on binaural detection.
18. A hearing aid according to claim 1 configured to provide a noise reduction gain G NR in dependence of said second—a priori—signal to noise ratio estimate ζ(k,n), and to apply said noise reduction gain G NR to said electric input signal or a signal derived therefrom.
19. A hearing aid according to claim 1 comprising a filter bank comprising an analysis filter bank for providing said time-frequency representation Y(k,n) of said electric input signal.
20. A hearing system comprising first and second hearing aids according to claim 1 configured to implement a binaural hearing aid system.
21. A method of estimating an a priori signal to noise ratio ζ(k,n) of a time-frequency representation Y(k,n) of an electric input signal representing a time variant sound signal consisting of target speech components and noise components, where k and n are frequency band and time frame indices, respectively, the method comprising:
determining an a posteriori signal to noise ratio estimate γ(k,n) of said electric input signal Y(k,n);
determining an a priori signal to noise signal ratio estimate ζ(k,n) of said electric input signal from said a posteriori signal to noise ratio estimate γ(k,n) based on a recursive algorithm; and
determining said a priori signal to noise ratio estimate ζ(k,n) by non-linear smoothing of said a posteriori signal to noise ratio estimate γ(k,n), or a parameter derived therefrom, said non-linear smoothing being controlled by one or more bias and/or smoothing parameters;
wherein said a posteriori signal to noise ratio estimate γ(k,n) of said electric input signal Y(k,n) is provided as a combined a posteriori signal to noise ratio generated as a mixture of first and second different a posteriori signal to noise ratio estimates.
22. A method according to claim 21 wherein said combined a posteriori signal to noise ratio estimate is determined by a neural network using said first and second a posteriori signal to noise estimate estimates as inputs.
23. A method according to claim 21 comprising:
providing a noise reduction gain G NR in dependence of said second signal to noise ratio estimate ζ(k,n); and
applying said noise reduction gain G NR to said electric input signal or a signal derived therefrom.
24. A data processing system comprising a processor and program code means for causing the processor to perform the method of claim 21 .
25. A non-transitory computer readable medium storing a computer program comprising instructions which, when the program is executed by a computer, cause the computer to carry out the method of claim 21 .
26. An audio processing device, comprising:
at least one input unit for providing a time-frequency representation Y(k,n) of an electric input signal representing a time variant sound signal consisting of target speech signal components S(k,n) from a target sound source TS and noise signal components N(k,n) from other sources than the target sound source, where k and n are frequency band and time frame indices, respectively; and
a noise reduction system configured to:
determine an a posteriori signal to noise ratio estimate γ(k,n) of said electric input signal,
determine an a priori signal to noise ratio estimate ζ(k,n) of said electric input signal from said a posteriori signal to noise ratio estimate γ(k,n) based on a recursive algorithm comprising a recursive loop, and
determine said a priori signal to noise ratio estimate ζ(k,n) by non-linear smoothing of said a posteriori signal to noise ratio estimate γ(k,n), or a parameter derived therefrom, said non-linear smoothing being controlled by one or more bias and/or smoothing parameters;
wherein said a priori signal to noise ratio estimate ζ(k,n) of said electric input signal Y(k,n) is influenced by a multitude of different a posteriori signal to noise ratios generated from different electric input signals or combinations of electric input signals.