首页> 外国专利> TRAINING METHOD FOR MULTIPLE PERSONALIZED ACOUSTIC MODELS, AND VOICE SYNTHESIS METHOD AND DEVICE

TRAINING METHOD FOR MULTIPLE PERSONALIZED ACOUSTIC MODELS, AND VOICE SYNTHESIS METHOD AND DEVICE

机译：多种个性化声学模型的训练方法，语音合成方法及装置

页面导航

摘要
著录项
相似文献

摘要

A training method for multiple personalized acoustic models, and a voice synthesis method and device, for voice synthesis. The method comprises: training a reference acoustic model, based on first acoustic feature data of training voice data and first text annotation data corresponding to the training voice data (S11); acquiring voice data of a target user (S12); training a first target user acoustic model according to the reference acoustic model and the voice data (S13); generating second acoustic feature data of the first text annotation data, according to the first target user acoustic model and the first text annotation data (S14); and training a second target user acoustic model, based on the first text annotation data and the second acoustic feature data (S15).

机译：用于多个个性化声学模型的训练方法以及用于语音合成的语音合成方法和装置。该方法包括：基于训练语音数据的第一声学特征数据和与训练语音数据相对应的第一文本注释数据（S 11 ），训练参考声学模型;获取目标用户的语音数据（S 12 ）;根据参考声学模型和语音数据（S 13 ）训练第一目标用户声学模型;根据第一目标用户声学模型和第一文本标注数据，生成第一文本标注数据的第二声学特征数据（S 14 ）;基于第一文本注释数据和第二声学特征数据（S 15 ）训练第二目标用户声学模型。 展开▼

著录项

公开/公告号US2018254034A1

专利类型

公开/公告日2018-09-06

原文格式PDF

申请/专利权人 BAIDU ONLINE NETWORK TECHNOLOGY (BEIJING) CO. LTD;
展开▼

申请/专利号US201615758280

发明设计人 XIULIN LI;
展开▼

申请日2016-06-27

分类号G10L13/02;G10L13/08;G10L15/06;G10L15/02;G10L15/18;G10L15/04;G10L15/183;G10L15/14;

国家 US

入库时间 2022-08-21 12:55:52

相似文献

专利

外文文献

中文文献

1. 个性化多声学模型的训练方法、语音合成方法及装置 [P] . 中国专利： CN105185372B . 2017.03.22

2. 个性化多声学模型的训练方法、语音合成方法及装置 [P] . 中国专利： CN105185372A . 2015-12-23

3. Training method for multiple personalized acoustic models, and voice synthesis method and device [P] . 美国专利： US10410621B2 . 2019-09-10

机译：多种个性化声学模型的训练方法，语音合成方法及装置

4. TRAINING METHOD FOR MULTIPLE PERSONALIZED ACOUSTIC MODELS, AND VOICE SYNTHESIS METHOD AND DEVICE [P] . 世界知识产权组织专利： WO2017067206A1 . 2017-04-27

机译：多种个性化声学模型的训练方法，语音合成方法及装置

5. ACOUSTIC MODEL TRAINING DEVICE, ACOUSTIC MODEL TRAINING METHOD, VOICE RECOGNITION DEVICE, AND VOICE RECOGNITION METHOD [P] . 美国专利： US2019096392A1 . 2019-03-28

机译：声学模型训练装置，声学模型训练方法，语音识别装置和语音识别方法

1. A training image optimization method in multiple-point geostatistics and its application in geological modeling [J] . WANG Lixin, YIN Yanshu, FENG Wenjie, 石油勘探与开发:英文版 . 2019,第004期

2. A Hierarchical Modeling and Fault Diagnosis Method for Complex Electronic Devices [J] . Bing Long, Shu-Lin Tian, Hou-Jun Wang 中国电子科技：英文版 . 2009,第004期

3. Computational performance of analytical methods for the acoustic modelling of automotive exhaust devices incorporating monoliths [J] . Denia F. D., Martinez-Casas J., Carballeira J., Journal of Computational and Applied Mathematics . 2018,第期

4. A Training Method of Average Voice Model for HMM-Based Speech Synthesis [J] . Junichi YAMAGISHI, Masatsune TAMURA, Takashi MASUKO, IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences . 2003,第8期

5. Methods for Modeling Realistic Playing in Acoustic Guitar Synthesis [J] . Laurson M, Erkut C, Välimäki V, Computer Music Journal . 2001,第3期

6. Singing voice conversion method based on many-to-many eigenvoice conversion and training data generation using a singing-to-singing synthesis system [C] . Doi Hironori, Toda Tomoki, Nakano Tomoyasu, 2012 Asia-Pacific Signal and Information Processing Association Annual Summit and Conference. . 2012

7. Effects of feed training methods and light intensity on survival and feed training success of largemouth bass Micropterus salmoides and effectiveness of new bird repellant devices in an aquaculture setting [D] . Sims, Derek W. 2007

8. Modeling of paclitaxel biosynthesis elicitation in Corylus avellana cell culture using adaptive neuro-fuzzy inference system-genetic algorithm (ANFIS-GA) and multiple regression methods [O] . Siamak Farhadi, Mina Salehi, Ahmad Moieni, 2020

9. Modeling and measurement methods for acoustic waves and for acoustic microdevices [O] . M.G. Beghi 2013

10. Methods, Devices and Kits for Multiplex Blotting of Biological Samples from Multi-Well Plates. [R] . Knezevic, V., Hartmann, D. P., Emmert-Buck, M. R. 2006

1. A training image optimization method in multiple-point geostatistics and its application in geological modeling [J] . WANG Lixin ,YIN Yanshu ,FENG Wenjie . 石油勘探与开发 . 2019,第004期

2. Computational Methods in the Theory of Synthesis of Radio and Acoustic Radiating Systems [J] . Petro Savenko . 应用数学（英文） . 2013,第3期

3. A Hierarchical Modeling and Fault Diagnosis Method for Complex Electronic Devices [J] . Bing Long ,Shu-Lin Tian ,Hou-Jun Wang . 电子科技学刊 . 2009,第004期

4. 基于语音声学模型的蒙古语族语言亲属关系探究 [C] . Degjirhu ,德格吉呼 ,Batgerel . 第十二届全国语音学学术会议 . 2016

5. 连续语音识别声学模型训练方法 [A] . 林常志 . 2005