Abstract: A similarity determination method, system, and computer program product, including using a description of companies for making a list of query entities, calculating a set of similar companies for each company on the list of query entities, employing a voting scheme to rank the results of the calculating, ordering a final set of the results based on the voting scheme and presenting them back to the user as a first ranked list, iteratively repeating the calculating by adding a second set of new companies and recalculating a second ranked list of recommended companies based on the updated query list, combining the first ranked list and the second ranked into a single set of companies of a combined list while remembering which of the first ranked list and the second ranked list from which each company originated, and visualizing the combined list based on which original list the companies came from. The technique can be extended to an arbitrary number of lists.

Abstract: The present invention discloses a computer prosody user interface operable to visually tailor the prosody of a text to be uttered by a text-to-speech system. The prosody user interface, permits users to alter a synthesized voice along one or more dimensions on a word-by-word basis. In one embodiment of the present invention, the prosody user interface is operable to alter the speaking rate relative word duration and the word prominence of a synthesized voice. Specifically, one or more words are selected using presentation means, and speech parameters corresponding to the speaking rate relative word duration and the word prominence are manipulated using speech parameter manipulation means. Modifications to the speech parameters are accompanied by visual changes to the presentation means, thereby providing a visual feel to the computer prosody user interface.

Abstract: A speech synthesis method employs an acoustic element database that is established from phonetic sequences occurring in an interval of a speech signal. In establishing the database, trajectories are determined for each of the phonetic sequences containing a phonetic segment that corresponds to a particular phoneme. A tolerance region is then identified based on a concentration of trajectories that correspond to different phoneme sequences. The acoustic elements for the database are formed from portions of the phonetic sequences by identifying cut points in the phonetic sequences which correspond to time points along the respective trajectories proximate the tolerance region. In this manner, it is possible to concatenate the acoustic elements having a common junction phonemes such that perceptible discontinuities at the junction phonemes are minimized. Computationally simple and fast methods for determining the tolerance region are also disclosed.