Nuance Communications, Inc.

Dong-Jian Yue

Johan Wouters

Corinne Bos-Plachez

Paolo Mairano

Silvia Maria Antonella Quazza

Sourav Nandy

A text-to-speech (TTS) system includes components capable of supporting the generation of speech output in any of multiple styles, and may switch seamlessly from producing speech output in one style to producing speech output in another style. For example, a concatenative TTS system may include a speech base storing speech units associated with multiple speech styles, and a linguistic analysis component to generate a phonetic transcription specifying speech output in any of multiple styles. Text input may include a style indication associated with a particular segment of the input text. The linguistic analysis component may invoke encoded rules and/or components based upon the style indication, and generate a phonetic transcription specifying a speech style, which may be processed to generate output speech.

Growing community of inventors

Shanghai, China

Dong-Jian Yue