Generation and detection of watermark for real-time voice conversion
AssigneeModulate, Inc.
InventorsWilliam Carter Huffman, Brendan Kelly
Life of this patent
Estimating the term…
Loading patent…
AssigneeModulate, Inc.
InventorsWilliam Carter Huffman, Brendan Kelly
Estimating the term…
A method watermarks speech data by using a generator to generate speech data including a watermark. The generator is trained to generate the speech data including the watermark. The training process generates first speech from the generator. The first speech data is configured to represent speech. The first speech data includes a candidate watermark. The training also produces an inconsistency message as a function of at least one difference between the first speech data and at least authentic speech data. The training further includes transforming the first speech data, including the candidate watermark, using a watermark robustness module to produce transformed speech data including a transformed candidate watermark. The transformed speech data includes a transformed candidate watermark. The training further produces a watermark-detectability message, using a watermark detection machine learning system, relating to one or more desirable watermark features of the transformed candidate watermark.
A method of watermarking speech data, the method comprising:
A system comprising:
A system for training machine learning to produce a speech watermark, the system comprising:
A computer program product for use on a computer system for training a system to generate a speech watermark, the computer program product comprising a tangible, non-transient computer usable medium having computer readable program code thereon, the computer readable program code comprising:
Dependencies are inferred from the claim text.