Matsushita Electric Industrial Co., Ltd.

Panasonic Corporation

Steven Pearson

Jean-Claude Junqua

Roland Kuhn

Ted H Applebaum

Nicholas Kibre

Brian A Hanson

Peter Veprek

A speech processing system is provided for customizing speech parameters across speech applications in a networked environment. The speech processing system includes: a speech processing application residing on a first computing device, where the speech processing application is operable to capture customized speech parameters for a given user and communicate the customized speech parameters across a network; and an intermediary speech processor residing on a second computing device in the networked environment, where the intermediary speech processor adapted to receive the customized speech parameters and is operable to transform the customized speech parameters for use on a third computing device.

Intermediary speech processor in network environments transforming customized speech parameters

A new speaker provides speech from which comparison snippets are extracted. The comparison snippets are compared with initial snippets stored in a recorded snippet database that is associated with a concatenative synthesizer. The comparison of the snippets to the initial snippets produces required sound units. A greedy selection algorithm is performed with the required sound units for identifying the smallest subset of the input text that contains all of the text for the new speaker to read. The new speaker then reads the optimally selected text and sound units are extracted from the human speech such that the recorded snippet database is modified and the speech synthesized adopts the voice quality and characteristics of the new speaker.

Text selection and recording by feedback and adaptation for development of personalized text-to-speech systems

Growing community of inventors

Santa Barbara, CA, United States of America

Steven Pearson