发明申请
US20070112567A1 Techiques for model optimization for statistical pattern recognition
审中-公开
用于统计模式识别的模型优化技术
- 专利标题: Techiques for model optimization for statistical pattern recognition
- 专利标题(中): 用于统计模式识别的模型优化技术
-
申请号: US11594717申请日: 2006-11-07
-
公开(公告)号: US20070112567A1公开(公告)日: 2007-05-17
- 发明人: Wai Lau , Steven Lee
- 申请人: Wai Lau , Steven Lee
- 申请人地址: US MA Cambridge
- 专利权人: ScanScout, Inc.
- 当前专利权人: ScanScout, Inc.
- 当前专利权人地址: US MA Cambridge
- 主分类号: G10L15/00
- IPC分类号: G10L15/00
摘要:
In one embodiment, a statistical pattern recognition engine determines content for a statistical pattern recognition task. The content and/or information related to the content is analyzed to determine a model to use in the statistical pattern recognition. For example, models may be classified in a plurality of domains based on different sets of data used to train models in the domain. The models may be classified based on knowledge sources used to generate the models, such as a news knowledge source, entertainment knowledge source, business knowledge source, etc. A model in the plurality of models is then determined based on the analysis where the determined model is classified in a domain. The model is then used by the statistical pattern recognition engine to perform the statistical pattern recognition task. For example, spoken words are transcribed into text using the determined model.