Enhancement of intelligibility in noisy environment
AssigneeGoogle Inc.
InventorsWillem Bastiaan Kleijn, Petko N. Petkov
Life of this patent
Estimating the term…
Abstract
Provided are methods and systems for enhancing the intelligibility of an audio (e.g., speech) signal rendered in a noisy environment, subject to a constraint on the power of the rendered signal. A quantitative measure of intelligibility is the mean probability of decoding of the message correctly. The methods and systems simplify the procedure by approximating the maximization of the decoding probability with the maximization of the similarity of the spectral dynamics of the noisy speech to the spectral dynamics of the corresponding noise-free speech. The intelligibility enhancement procedures provided are based on this principle, and all have low computational cost and require little delay, thus facilitating real-time implementation.
Claims10
A method for enhancing intelligibility of a speech signal rendered in a noisy environment, the method comprising:
- adapting a sequence of features for a signal rendered in a noisy environment to approximate the sequence of features for the signal rendered in a noise-free environment;
- imposing a constraint on each of the features for the signal rendered in the noisy environment,
- defining a fidelity measure to approximate the sequence of features for the signal rendered in the noisy environment to correspond with the sequence of features for the signal rendered in the noise-free environment;
- and
- distributing signal power across frequency bins of the adapted sequence of features to maximize the fidelity measure.
A system for enhancing intelligibility of a speech signal rendered in a noisy environment, the system comprising:
- one or more processors;
- and
- a non-transitory computer-readable medium coupled to said one or more processors having instructions stored thereon that, when executed by said one or more processors, cause said one or more processors to perform operations comprising:
- adapting a sequence of features for a signal rendered in a noisy environment to approximate the sequence of features for the signal rendered in a noise-free environment;
- and
- imposing a constraint on each of the features for the signal rendered in the noisy environment
- defining a fidelity measure to approximate the sequence of features for the signal rendered in the noisy environment to correspond with the sequence of features for the signal rendered in the noise-free environment;
- and
- distributing signal power across frequency bins of the adapted sequence of features to maximize the fidelity measure.
Dependencies are inferred from the claim text.