Patent · US Active

Rich context modeling for text-to-speech engines

US8340965B2 · kind B2 · utility

3Cited by

12References

23Claims

0Family size

Assignee

Microsoft Corporation · US

Inventors

Zhi-Jie Yan · Nanhu, CN
Yao Qian · Dublin, US
Frank Kao-Ping Soong · Beijing, CN

Key dates

Filing date	Dec 2, 2009
Grant date	Dec 25, 2012
Priority date	—
Expiry date	Apr 5, 2031

Classification

Technology area (CPC G)Physics
CPC primaryG10L13/08
WIPO fieldComputer technology
WIPO sectorElectrical engineering

Abstract

Embodiments of rich context modeling for speech synthesis are disclosed. In operation, a text-to-speech engine refines a plurality of rich context models based on decision tree-tied Hidden Markov Models (HMMs) to produce a plurality of refined rich context models. The text-to-speech engine then generates synthesized speech for an input text based at least on some of the plurality of refined rich context models.

Source: USPTO / EPO open patent data. Objective bibliographic and citation counts.