Speech model-based neural network-assisted signal enhancement
AssigneeApple Inc.
InventorSean A. Ramprashad
Life of this patent
Estimating the term…
Abstract
Several embodiments of a digital speech signal enhancer are described that use an artificial neural network that produces clean speech coding parameters based on noisy speech coding parameters as its input features. A vocoder parameter generator produces the noisy speech coding parameters from a noisy speech signal. A vocoder model generator processes the clean speech coding parameters into estimated clean speech spectral magnitudes. In one embodiment, a magnitude modifier modifies an original frequency spectrum of the noisy speech signal using the estimated clean speech spectral magnitudes, to produce an enhanced frequency spectrum, and a synthesis block converts the enhanced frequency spectrum into time domain, as an output speech sequence. Other embodiments are also described.
Claims21
A digital speech signal enhancer, comprising:
- a neural network processor to process a plurality of noisy speech coding parameters that have been derived from an input speech sequence by a vocoder implementing a linear predictive model using a time-varying model for formant or formant and pitch, to produce a plurality of estimated clean speech coding parameters;
- a vocoder model generator and spectral magnitude generator, configured to process the estimated clean speech coding parameters into estimated clean speech spectral magnitudes;
- a magnitude modifier configured to modify an original frequency spectrum of the input speech sequence using the estimated clean speech spectral magnitudes, to produce an enhanced frequency spectrum;
- and
- a synthesis block configured to convert the enhanced frequency spectrum into time domain, as an output speech sequence.
A digital speech signal enhancement process comprising:
- processing using a neural network a plurality of noisy speech coding parameters that have been derived from an input speech sequence , by a vocoder implementing a linear predictive model using a time-varying model for formant or formant and pitch, to produce a plurality of estimated clean speech coding parameters;
- processing the estimated clean speech coding parameters into estimated clean speech spectral magnitudes;
- modifying an original frequency spectrum of the input speech sequence using the estimated clean speech spectral magnitudes, to produce an enhanced frequency spectrum;
- and
- converting the enhanced frequency spectrum into time domain, as an output speech sequence.
A digital speech signal enhancer comprising:
- an artificial neural network to process a plurality of noisy speech coding parameters that have been derived from an input speech sequence by a vocoder implementing a linear predictive model using a time-varying model for formant or formant and pitch, to produce a plurality of clean speech coding parameters;
- a speech coding model generator to process the clean speech coding parameters into formant information and pitch information;
- a pitch filter configured in accordance with the pitch information;
- and
- a formant filter configured in accordance with the formant information, wherein the pitch and formant filters are coupled in cascade to filter an input excitation signal and produce a synthesized speech signal.
A digital speech signal enhancement process comprising:
- processing by an artificial neural network a plurality of noisy speech coding parameters that have been derived from an input speech sequence by a vocoder implementing a linear predictive model using a time-varying model for formant or formant and pitch, to produce a plurality of clean speech coding parameters;
- processing the clean speech coding parameters into formant information and pitch information in accordance with a linear predictive speech production model;
- and
- filtering an excitation signal in accordance with both the pitch information and the formant information to produce a synthesized speech signal.
Dependencies are inferred from the claim text.