Abstract: According to various embodiments, an end-to-end TTS framework can integrate a watermarking process into the training of the TTS framework, which enables watermarks to be imperceptible within a synthesized/cloned audio segment generated by the TTS framework. The watermarks added in such a matter are statistically undetectable to prevent authorized removal. According to an exemplary method of training the TTS framework, a TTS neural network model and a watermarking neural network mode in the TTS framework are trained in an end to end manner, with the watermarking being part of the optimization process of the TTS framework. During the training, neuron values of the TTS neural network model are adjusted based on training data to prepare one or more spaces for adding a watermark in a synthesized audio segment to be generated by the TTS framework.

Abstract: Methods, apparatus, systems and articles of manufacture (e.g., physical storage media) to implement power efficient detection of watermarks in media signals are disclosed. Example metering apparatus disclosed herein include detector means for detecting watermarks in a media signal. Disclosed example metering apparatus also include controller means for operating the detector means to (1) detect a first watermark in the media signal, and (2) cycle between sleep intervals and active intervals to detect a second watermark at a second location in the media signal relative to a first location of the first watermark in the media signal after the first watermark has been verified.

Abstract: In one example, an apparatus includes: a wavelet transform engine to receive a first signal stream and perform a wavelet transform on a first time domain sample of the first signal stream, the first wavelet transform engine to output at least one first coefficient for a first frequency range; an energy calculation circuit to compute a first energy signature for the at least one first coefficient; and a correlation circuit to generate a correlation value using the first energy signature, a second energy signature and a plurality of previous energy signatures.

Abstract: Techniques for identifying aired content are described. A first audio sample is received and processed, using a computer processor, to extract an embedded audio watermark. A content identifier identifying a first item of programming content is determined, using the computer processor and based on the audio watermark. A timestamp associated with the first audio sample is also determined based on the audio watermark. An as-aired log is updated based on the content identifier and the timestamp. The computer processor is used to identify that the first item of programming content has aired, based on the as-aired log.

Abstract: Described herein are systems, methods, and apparatuses for providing the detection of displays or performances of copyrighted creative works, determining whether a license exists for those performances, and taking further action depending upon the results of that determination. The systems, methods, and apparatuses may include using a mobile device to capture occurrences of multimedia data as well as information relating to the location of those occurrences, and transmitting representations of those occurrences and information to a server computer. The server computer may identify the copyrighted work associated with the multimedia data, determine if a license for performance of that work exists, determine a price for its performance/display, and generate and then send an invoice for the performance of the copyrighted work.

Abstract: The present disclosure relates generally to data hiding for retail product packaging and other printed objects such as substrates. One embodiment embeds an information signal in a spot color for printing on various substrates. The spot color is screened, and overprinted with process color tint. The tint is modulated prior to overprinting with optimized signal tweaks. The optimization can include consideration of a detector spectral dependency (e.g., red and/or green illumination). Many other embodiments and combinations are described in the subject patent document.

Abstract: The present disclosure relates to advanced signal processing including signal embedding, digital watermarking and steganography.

Abstract: A system for decoding a video bitstream includes receiving a reference picture set associated with a frame including a set of reference picture identifiers. The reference picture set identifies one or more reference pictures to be used for inter-prediction of the frame based upon its associated least significant bits of a picture order count based upon the reference picture identifiers. The one or more reference pictures is a second or greater previous frame to the frame having the matching reference picture identifier.

Abstract: A system for decoding a video bitstream includes receiving a reference picture set associated with a frame including a set of reference picture identifiers. The reference picture set identifies one or more reference pictures to be used for inter-prediction of the frame based upon its associated least significant bits of a picture order count based upon the reference picture identifiers. The one or more reference pictures is a second or greater previous frame to the frame having the matching reference picture identifier.

Abstract: Method for coding or recognizing of surveillance videos is provided to improve compressing efficiency and recognizing accuracy of surveillance videos. The method for coding surveillance videos includes: establishing a background database and a foreground object database; wherein, the background database includes a set of background images; the foreground object database includes a set of foreground objects; coding a surveillance image by referring to a background image in the background database and a foreground object in the foreground object database.

Abstract: A spread spectrum data hiding for audio signals is described. A set of pseudo-random noise sequences is added to an audio signal according to a data to be embedded. A masking curve is used to shape the added noise. A transient detection step can be used to control whether a shaped noise sequence is to be added or not. Embedded information is detected by first performing a whitening step and then performing a phase-only correlation with a same set of pseudo-random noise sequences. A detection method that is based on correlation of multiplexed noise sequences with a noise sequence embedded in the audio is also described.

Abstract: A method for watermarking a sequence of images is provided. The method implements the following steps, for at least one current image: comparing the current image with a preceding image of the sequence, delivering a difference image representing a motion between the preceding image and the current image; if the difference between the current image and the preceding image is above a predetermined threshold, watermarking the current image by inserting a message comprising a field carrying an identifier of the current image and a field carrying a soft hash obtained from at least one portion of the difference image; and if not, watermarking the current image by inserting a message comprising a field carrying an identifier of the current image.

Abstract: Disclosed is a method and system for digital watermarking of multimedia signals. The input multimedia signal is represented using an inverse difference pyramid decomposition. Spectrum coefficients may be calculated for each level of the pyramid using a new kind of complex Hadamard transform, the matrix of which is distinguished from the known ones by the fact that only one-fourth of its coefficients are complex numbers. The phases of a previously selected part of the low-frequency coefficients are modified with the watermark data, limiting the angles of the phase changes in a gap of several degrees only. After an inverse complex Hadamard Transform, the values of the coefficients from all pyramid levels are summed up and the result is the watermarked signal. The watermark can contain multiple independent levels for each level of the pyramid.