Apparatus and method for noise attenuation in a speech recognition system
AssigneesSony Corporation, Sony Electronics Inc.
InventorsXavier Menéndez-Pidal, Miyuki Tanaka, Ruxin Chen
Life of this patent
Estimating the term…
Abstract
The noise suppressor utilizes statistical characteristics of the noise signal to attenuate amplitude values of the noisy speech signal that have a probability of containing noise. In one embodiment, the noise suppressor utilizes an attenuation function having a shape determined in part by a noise average and a noise standard deviation. In a further embodiment, the noise suppressor also utilizes an adaptive attenuation coefficient that depends on signal-to-noise conditions in the speech recognition system.
Claims39
An apparatus for noise attenuation in an electronic system, comprising:
- a noise suppressor configured to selectively attenuate additive noise in an electronic signal, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selectively attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor generating an attenuated noisy speech signal according to a formula:
- Yat k = Y k 1 + A e - 1 2 ( Y k - α μ k σ k ) 2 if Y k > α μ k Yat k = Y k 1 + A otherwise
- where Yatk is said attenuated noisy speech signal for a frequency k, Yk is said noisy speech signal for said frequency k, μk is said noise average for said frequency k, σk is said noise standard deviation for said frequency k, α is a overestimation coefficient, and A is an attenuation coefficient;
- and
- a processor coupled to said electronic system to control said noise suppressor.
An apparatus for noise attenuation in an electronic system, comprising:
- a noise suppressor configured to selectively attenuate additive noise in an electronic signal, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selective attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor generating an attenuated noisy speech signal according to a formula:
- A k ( t ) = A log 2 ( 1 + Sp k ( t ) α μ k ( prev ) ) t ∈ utterance A k ( t ) = A log 2 ( 1 + Sp k ( prev ) α μ k ( t ) ) t ∈ noise period
- where Yatk is said attenuated noisy speech signal for a frequency k, Yk is said noisy speech signal for said frequency k, μk is said noise average for said frequency k, σk is said noise standard deviation for said frequency k, αv is an overestimation coefficient related to said noise standard deviation, and A is an attenuation coefficient;
- and
- a processor coupled to said electronic system to control said noise suppressor.
An apparatus for noise attenuation in an electronic system, comprising:
- a noise suppressor configured to selectively attenuate additive noise in an electronic signal, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selectively attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor calculating said noise average according to a formula:
- μk(t)=βμk(t−1)+(1−β)Nk(t)
- where μk(t) is said noise average for a frequency index k at a frame t, Nk(t) is a noise energy amplitude value for frequency index k at frame t, and β is a noise forgetting coefficient;
- and
- a processor coupled to said electronic system to control said noise suppressor.
A method for noise attenuation in an electronic system, comprising the steps of:
- selectively attenuating additive noise in an electronic signal using a noise suppressor, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selectively attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor generating an attenuated noisy speech signal according to a formula:
- Yat k = Y k 1 + A e - 1 2 ( Y k - α μ k σ k ) 2 if Y k > α μ k Yat k = Y k 1 + A otherwise
- where Yatk said attenuated noisy speech for signal for a frequency k, Yk is said noisy speech signal for said frequency k, μk is said noise average for said frequency k, σk is said noise standard deviation for said frequency k, α is a overestimation coefficient, and A is an attenuation coefficient;
- and
- controlling said noise suppressor with a processor coupled to said electronic system.
A method for noise attenuation in an electronic system, comprising the steps of:
- selectively attenuating additive noise in an electronic signal using a noise suppressor, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selectively attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor generating an attenuated noisy speech signal according to a formula:
- Yat k = Y k 1 + A ⅇ - 1 2 ( Y k - ( μ k + α v σ k ) σ k ) 2 if Y k > μ k + α v σ k Yat k = Y k 1 + A otherwise
- where Yatk is said attenuated noisy speech signal for a frequency k, Yk is said noisy speech signal for said frequency k, μk is said noise average for said frequency k, σk is said noise standard deviation for said frequency k, αv is an overestimation coefficient related to said noise standard deviation, and A is an attenuation coefficient;
- and
- controlling said noise suppressor with a processor coupled to said electronic system.
A method for noise attenuation in an electronic system, comprising the steps of:
- selectively attenuating additive noise in an electronic signal using a noise suppressor, said electronic signal being a noisy speech signal that includes a noise signal combined with a speech signal, said noise suppressor selectively attenuating said noise signal by utilizing statistical characteristics of amplitude energy values of said noise signal, said statistical characteristics of said amplitude energy values of said noise signal include a noise average and a noise standard deviation, said noise suppressor calculating said noise average according to a formula:
- μk(t)=βμk(t−1)+(1−β)Nk(t)
- where μk(t) is said noise average for a frequency index k at a frame t, Nk(t) is a noise energy amplitude value for frequency index k at frame t, and β is a noise forgetting coefficient;
- and
- controlling said noise suppressor with a processor coupled to said electronic system.
An apparatus for noise attenuation in an electronic system, comprising:
- a noise suppressor configured to selectively attenuate additive noise in an electronic signal, said noise suppressor determining a noise average and a noise standard deviation of energy amplitude values of a noisy speech signal, said noise suppressor utilizing said noise average and said noise standard deviation to identify said amplitude energy values of said noisy speech signal that have a statistical probability of containing said additive noise, said noise suppressor selectively attenuating said amplitude energy values of said noisy speech signal according to said statistical probability, said noise suppressor calculating said noise average according to a formula:
- μk(t)=βμk(t−1)+(1−β)Nk(t)
- where μk(t) is said noise average for a frequency index k at a frame t, Nk(t) is a noise energy amplitude value for frequency index k at frame t, and β is a noise forgetting coefficient;
- and
- a processor coupled to said electronic system to control said noise suppressor.
Dependencies are inferred from the claim text.