Invention Grant
US09542927B2 Method and system for building text-to-speech voice from diverse recordings
有权
从各种录音中构建文字到语音的方法和系统
- Patent Title: Method and system for building text-to-speech voice from diverse recordings
- Patent Title (中): 从各种录音中构建文字到语音的方法和系统
-
Application No.: US14540088Application Date: 2014-11-13
-
Publication No.: US09542927B2Publication Date: 2017-01-10
- Inventor: Ioannis Agiomyrgiannakis , Alexander Gutkin
- Applicant: Google Inc.
- Applicant Address: US CA Mountain View
- Assignee: Google Inc.
- Current Assignee: Google Inc.
- Current Assignee Address: US CA Mountain View
- Agency: McDonnell Boehnen Hulbert & Berghoff LLP
- Main IPC: G10L13/08
- IPC: G10L13/08 ; G10L13/02 ; G10L13/06 ; G10L25/03

Abstract:
A method and system is disclosed for building a speech database for a text-to-speech (TTS) synthesis system from multiple speakers recorded under diverse conditions. For a plurality of utterances of a reference speaker, a set of reference-speaker vectors may be extracted, and for each of a plurality of utterances of a colloquial speaker, a respective set of colloquial-speaker vectors may be extracted. A matching procedure, carried out under a transform that compensates for speaker differences, may be used to match each colloquial-speaker vector to a reference-speaker vector. The colloquial-speaker vector may be replaced with the matched reference-speaker vector. The matching-and-replacing can be carried out separately for each set of colloquial-speaker vectors. A conditioned set of speaker vectors can then be constructed by aggregating all the replaced speaker vectors. The condition set of speaker vectors can be used to train the TTS system.
Public/Granted literature
- US20160140951A1 Method and System for Building Text-to-Speech Voice from Diverse Recordings Public/Granted day:2016-05-19
Information query