首页>
外国专利>
Synchronized pattern recognition source data processed by manual or automatic means for creation of shared speaker-dependent speech user profile
Synchronized pattern recognition source data processed by manual or automatic means for creation of shared speaker-dependent speech user profile
展开▼
机译:通过手动或自动方式处理的同步模式识别源数据,用于创建共享的与说话者相关的语音用户配置文件
展开▼
页面导航
摘要
著录项
相似文献
摘要
An apparatus for collecting data from a plurality of diverse data sources, the diverse data sources generating input data selected from the group including text, audio, and graphics, the diverse data sources selected from the group including real-time and recorded, human and mechanically-generated audio, single-speaker and multispeaker, the apparatus comprising: means for dividing the input data into one or more data segments, the dividing means acting separately on the input data from each of the plurality of diverse data sources, each of the data segments being associated with at least one respective data buffer such that each of the respective data buffers would have the same number of segments given the same data; means for selective processing of the data segments within each of the respective data buffers; and means for distributing at least one of the respective data buffers such that the collected data associated therewith may be used for further processing.
展开▼