New pending patent applications are published in Thursdays. Both of today's Spotlight Applications concern aspects of digital watermarking. Assigned to The Nielsen Company, the first application discloses techniques for multiple scrambled layers for audio watermarking. Assigned to Nuance, the second application discloses techniques for watermarking of synthetic speech.
20210043217, "Multiple scrambled layers for audio watermarking," assigned to The Nielsen Company.
Apparatus, systems, articles of manufacture, and methods are disclosed for multiple scrambled layers for audio watermarking. An example system includes a processor to execute instructions to: divide the watermark into a plurality of watermark symbols; map the watermark symbols to a plurality of frequency bins according to a first distribution scheme to create a first watermark layer having a first combination of the frequency bins and a second watermark layer having a second combination of the frequency bins, subsets of adjacent ones of the plurality of frequency bins grouped into a corresponding plurality of frequency clumps; determine a sequence for shifting watermark symbols between the frequency clumps to cause different combinations of watermark symbols that include one watermark symbol from each watermark layer to share up to a first number of frequency bins, the first number of frequency bins to be less than a number of watermark symbols in respective ones of the different combinations; and generate a second distribution scheme to map the watermark symbols in accordance with the sequence.
20210050024, "Watermarking of synthetic speech," assigned to Nuance.
An audio watermark is embedded in synthetic speech, such as synthetic speech created using text-to-speech (TTS) synthesis. Such audio watermarks can, for example, be used to increase the accuracy of voice biometric (VB) and other systems in distinguishing synthetic speech from human speech. In addition to its use in voice biometrics, such audio watermarking can prevent misuse of human quality TTS, or other synthetic speech, in a variety of other contexts, such as incriminating recordings, spam messages, contact center denial of service, and protection of personal information in contact centers not utilizing VB.