Deep scattering spectrum in acoustic modeling for speech recognition
AssigneeInternational Business Machines Corporation
InventorsPetr Fousek, Vaibhava Goel, Brian E.D. Kingsbury, Etienne Marcheret, Shay Maymon, David Nahamoo, Tara N. Sainath, Bhuvana Ramabhadran
Life of this patent
Estimating the term…
Abstract
Deep scattering spectral features are extracted from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal. The deep scattering spectral feature representation is input to a speech recognition engine. The acoustic input signal is decoded based on at least a portion of the deep scattering spectral feature representation input to a speech recognition engine.
Claims20
A method, comprising:
- extracting deep scattering spectral features from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal;
- inputting the deep scattering spectral feature representation to a speech recognition engine;
- and
- decoding the acoustic input signal based on at least a portion of the deep scattering spectral feature representation input to a speech recognition engine;
- wherein the extracting, inputting and decoding steps are executed via a computer system comprising a processing unit and a memory.
An article of manufacture, comprising a non-transitory computer readable storage medium having tangibly embodied thereon computer readable program code which, when executed, causes a processing unit to:
- extract deep scattering spectral features from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal;
- input the deep scattering spectral feature representation to a speech recognition engine;
- and
- decode the acoustic input signal based on at least a portion of the deep scattering spectral feature representation via the speech recognition engine.
An apparatus, comprising:
- a memory;
- and
- a processing unit operatively coupled to the memory and configured to:
- extract deep scattering spectral features from an acoustic input signal to generate a deep scattering spectral feature representation of the acoustic input signal;
- and
- decode the acoustic input signal based on at least a portion of the deep scattering spectral feature representation via a speech recognition engine.
Dependencies are inferred from the claim text.