Abstract: An apparatus for providing a content-information service comprises: a user-content interface for receiving content-provision request information collected by several user I/O interfaces which includes a voice recognition interface, and providing content data corresponding to the provision request information to users; a content-provision relay for requesting the content data using content-associated information corresponding to the content-provision request information, and transmitting the content data to the user-content interface; a content-information manager for registering and managing the content-associated information associated with the content data; and a content-storage unit for storing and managing a plurality of providable content data.

Abstract: A system, method and computer-readable media are disclosed for improving speech synthesis. A text-to-speech (TTS) voice database for use in a TTS system is generated by a method comprising labeling a voice database phonemically and applying a pre-/post-vocalic distinction to the phonemic labels to generate a TTS voice database. When a system synthesizes speech using speech units from the TTS voice database, the database provides phonemes for selection using the pre-/post-vocalic distinctions which improve unit selection to render the synthetic speech more natural.

Abstract: Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

Abstract: Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

Abstract: Systems and methods for automatically segmenting speech inventories. A set of Hidden Markov Models (HMMs) are initialized using bootstrap data. The HMMs are next re-estimated and aligned to produce phone labels. The phone boundaries of the phone labels are then corrected using spectral boundary correction. Optionally, this process of using the spectral-boundary-corrected phone labels as input instead of the bootstrap data is performed iteratively in order to further reduce mismatches between manual labels and phone labels assigned by the HMM approach.

Abstract: A speed-variable audio play-back apparatus which includes a pitch detecting circuit for separating speech source components and audio characteristics from an input audio signal, a pitch modulating unit for deleting selected ones of the separated speech source components or adding another speech source components to the separated speech source components depending on a play-back speed, thereby adjusting the length of the audio signal to be played back, a speech synthesizing circuit for synthesizing the speech source components and audio characteristics modulated by the pitch modulating unit, thereby outputting a speed-varied audio signal; and a main controller for controlling the above components in accordance with control signals externally applied thereto.