METHOD, APPARATUS, AND PROGRAM FOR GENERATING TRAINING SPEECH DATA FOR TARGET DOMAIN,申请号US201414251772-传众专利搜索

METHOD, APPARATUS, AND PROGRAM FOR GENERATING TRAINING SPEECH DATA FOR TARGET DOMAIN

申请公布号：US2014337026(A1)

申请号：US201414251772

申请日期：2014.04.14

申请公布日期：2014.11.13

申请人：

INTERNATIONAL BUSINESS MACHINES CORPORATION

发明人：Ichikawa Osamu;Rennie Steven J.

分类号：G10L15/06;G10L15/14

主分类号：G10L15/06

地址：Armonk NY US

摘要：A method and system for generating training data for a target domain using speech data of a source domain. The training data generation method including: reading out a Gaussian mixture model (GMM) of a target domain trained with a clean speech data set of the target domain; mapping, by referring to the GMM of the target domain, a set of source domain speech data received as an input to the set of target domain speech data on a basis of a channel characteristic of the target domain speech data; and adding a noise of the target domain to the mapped set of source domain speech data to output a set of pseudo target domain speech data.

主权项：1. A method for generating training data for a target domain using speech data of a source domain, the training data generation method comprising: reading out a Gaussian mixture model (GMM) of a target domain trained with a clean speech data set of the target domain; mapping, by referring to the GMM of the target domain, a set of source domain speech data received as an input to the set of target domain speech data on a basis of a channel characteristic of the target domain speech data; and adding a noise of the target domain to the mapped set of source domain speech data to output a set of pseudo target domain speech data.