Search International and National Patent Collections

1. (WO2017067246) ACOUSTIC MODEL GENERATION METHOD AND DEVICE, AND SPEECH SYNTHESIS METHOD AND DEVICE

Pub. No.:    WO/2017/067246    International Application No.:    PCT/CN2016/090044
Publication Date: Fri Apr 28 01:59:59 CEST 2017 International Filing Date: Fri Jul 15 01:59:59 CEST 2016
IPC: G10L 13/02
Applicants: BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO., LTD.
百度在线网络技术(北京)有限公司
Inventors: LI, Xiulin
李秀林
Title: ACOUSTIC MODEL GENERATION METHOD AND DEVICE, AND SPEECH SYNTHESIS METHOD AND DEVICE
Abstract:
An acoustic model generation method and device, and a speech synthesis method and device. The acoustic model generation method comprises: acquiring personalized data, wherein the personalized data is obtained after processing according to personalized speech data and corresponding personalized text data (S11); acquiring a pre-generated reference acoustic model, wherein the reference acoustic model is generated according to existing large-scale samples (S12); and carrying out self-adaptive model training according to the personalized data and the reference acoustic model to generate a personalized acoustic model (S13). According to the method, an acoustic model can be rapidly generated, and personalized requirements of users can be satisfied.