公开(公告)号：WO2017213696A1

公开(公告)日：2017-12-14

申请号：PCT/US2016/065759

申请日：2016-12-09

Applicant: GOOGLE LLC

Inventor： CHUA, Mason Vijay ,  RAO, Kanury Kanishka ,  VAN ESCH, Daniel Jacobus Josef

IPC: G10L13/10 ,  G10L25/30 ,  G10L15/187

CPC classification number: G10L13/10 ,  G10L13/0335 ,  G10L13/047 ,  G10L13/08 ,  G10L15/02 ,  G10L15/063 ,  G10L15/16 ,  G10L15/1815 ,  G10L15/187 ,  G10L17/18 ,  G10L25/30 ,  G10L2015/027

Abstract: Methods, systems, and apparatus, including computer programs encoded on computer storage media, for generating word pronunciations. One of the methods includes determining, by one or more computers, spelling data that indicates the spelling of a word, providing the spelling data as input to a trained recurrent neural network, the trained recurrent neural network being trained to indicate characteristics of word pronunciations based at least on data indicating the spelling of words, receiving output indicating a stress pattern for pronunciation of the word generated by the trained recurrent neural network in response to providing the spelling data as input, using the output of the trained recurrent neural network to generate pronunciation data indicating the stress pattern for a pronunciation of the word, and providing, by the one or more computers, the pronunciation data to a text-to-speech system or an automatic speech recognition system.

Abstract translation: 包括在计算机存储介质上编码的计算机程序的方法，系统和装置，用于生成单词发音。 其中一种方法包括由一个或多个计算机确定指示单词拼写的拼写数据，将拼写数据作为输入提供给训练的递归神经网络，训练后的递归神经网络被训练以指示基于单词发音的特征 至少在指示单词拼写的数据上，接收指示由训练的回归神经网络响应于提供拼写数据作为输入而生成的单词的发音的压力模式的输出，使用训练的回归神经网络的输出来生成发音 指示单词发音的压力模式的数据，以及通过一个或多个计算机将发音数据提供给文本到语音系统或自动语音识别系统。