Abstract:
A device, a program, and a storage medium for generating improved tolerance and quality WM signals and for digital watermarking and a digital TV set including the digital watermarking function. A device (10) for generating a WM signal to be digitally embedded as a watermark into a real-time content comprises receiving means (12) for receiving a real-time content; an input buffer (14) in which the real-time content is held; generation means for generating a WM signal, corresponding to the predicted intensity of the real-time content, from the divided real-time content; and an output buffer (18) for holding the generated WM signal. The generation means comprises prediction means (16) for predicting the intensity of the WM signal; control means (20) for controlling embediment using a message to be embedded as a watermark into the divided real-time content; and means (22) for generating an output WM signal.
Abstract:
An objective is to provide a technique for accurately reproducing features of a fundamental frequency of a target-speaker's voice on the basis of only a small amount of learning data. A learning apparatus learns shift amounts from a reference source F0 pattern to a target F0 pattern of a target-speaker's voice. The learning apparatus associates a source F0 pattern of a learning text to a target F0 pattern of the same learning text by associating their peaks and troughs. For each of points on the target F0 pattern, the learning apparatus obtains shift amounts in a time-axis direction and in a frequency-axis direction from a corresponding point on the source F0 pattern in reference to a result of the association, and learns a decision tree using, as an input feature vector, linguistic information obtained by parsing the learning text, and using, as an output feature vector, the calculated shift amounts.
Abstract:
A device, a program, and a storage medium for generating improved tolerance and quality WM signals and for digital watermarking and a digital TV set including the digital watermarking function. A device (10) for generating a WM signal to be digitally embedded as a watermark into a real-time content comprises receiving means (12) for receiving a real-time content; an input buffer (14) in which the real-time content is held; generation means for generating a WM signal, corresponding to the predicted intensity of the real - time content, from the divided real-time content; and an output buffer (18) for holding the generated WM signal. The generation means comprises predicti on means (16) for predicting the intensity of the WM signal; control means (20) for controlling embediment using a message to be embedded as a watermark int o the divided real-time content; and means (22) for generating an output WM signal.
Abstract:
An apparatus 10 for generating wartermark signals to be embedded as a digital watermark in real-time contents includes: input means 12 for inputting the real-time contents; an input buffer 14 for storing the real-time contents; generation means for generating wartermark signals corresponding to predicted intensities of the real-time contents from divided real-time contents; and an output buffer 18 for storing the generated wartermark signals to be outputted. The generation means is configured by including prediction means 16 for predicting intensities of the wartermark signals; control means 20 for controlling embedding by use of a message to be embedded as the digital watermark in the divided real-time contents; and means 22 for generating the wartermark signals to be outputted.