Methods and apparatus for voice transformation, authentication, and metadata communication
AssigneeMcAfee, Inc.
InventorsSrikanth Nalluri, Dattatraya Kulkarni, Ayush Agarwal
Life of this patent
Estimating the term…
Abstract
Methods and apparatus for voice transformation, authentication, and metadata communication are disclosed. An example apparatus includes interface circuitry, machine readable instructions, and programmable circuitry to identify least significant bits of the voice signal, and embed metadata in the identified least significant bits of the voice signal to produce an embedded voice signal.
Claims20
An apparatus to at least one of embed or access information in a voice signal, the apparatus comprising:
- interface circuitry;
- machine readable instructions;
- and
- programmable circuitry to at least one of instantiate or execute the machine readable instructions to:
- access an original digital voice signal generated from user speech;
- generate a filtered voice signal based on application of at least one noise-reduction filter to the original digital voice signal;
- compare the original digital voice signal and the filtered voice signal to identify a set of bits modified by the noise-reduction filter;
- and
- embed metadata in the identified set of bits to generate an embedded voice signal.
A non-transitory machine readable storage medium comprising instructions to cause programmable circuitry to at least:
- access an original digital voice signal generated from user speech;
- access a filtered voice signal in response to application of at least one noise-reduction filter to the original digital voice signal;
- identify a set of bits modified by noise-reduction filter based on a comparison of the original digital voice signal and the filtered voice signal;
- and
- embed metadata in the identified set of bits to generate an embedded voice signal.
A method comprising:
- accessing an original digital voice signal generated from user speech;
- generating a filtered voice signal based on application of at least one noise-reduction filter to the original digital voice signal;
- comparing the original digital voice signal and the filtered voice signal to identify a set of bits modified by the noise-reduction filter;
- and
- embedding metadata in the identified set of bits to generate an embedded voice signal.
Dependencies are inferred from the claim text.