首页 / 专利库 / 数学与统计 / 隐马尔可夫模型 / METHOD AND APPARATUS FOR CONTEXT-DEPENDENT ESTIMATION IN A SPEECH RECOGNITION SYSTEM

METHOD AND APPARATUS FOR CONTEXT-DEPENDENT ESTIMATION IN A SPEECH RECOGNITION SYSTEM

阅读:268发布:2021-08-21

专利汇可以提供METHOD AND APPARATUS FOR CONTEXT-DEPENDENT ESTIMATION IN A SPEECH RECOGNITION SYSTEM专利检索,专利查询,专利分析的服务。并且In a hidden Markov model-based speech recognition system (10), a specific method and apparatus are provided for use of multilayer perceptrons (MLPs) (14) in context-dependent estimation of a plurality of state-dependent observation probability distributions of phonetic classes. Estimation is obtained by the Bayesian factorization of the observation likelihood in terms of posterior probabilities of phone classes assuming the context and the input speech vector. The context-dependent estimation is employed as the state-dependent observation probabilities needed as parameter input to a hidden Markov model speech processor to identify the word sequence representing the unknown speech input of input speech vectors. Specifically, a multiple-output-layer multilayer perceptron-type neural network is uniquely equipped to compute one of the factors of Bayesian factorization.,下面是METHOD AND APPARATUS FOR CONTEXT-DEPENDENT ESTIMATION IN A SPEECH RECOGNITION SYSTEM专利的具体信息内容。

高效检索全球专利

专利汇是专利免费检索,专利查询,专利分析-国家发明专利查询检索分析平台,是提供专利分析,专利查询,专利检索等数据服务功能的知识产权数据服务商。

我们的产品包含105个国家的1.26亿组数据,免费查、免费专利分析。

申请试用

分析报告

专利汇分析报告产品可以对行业情报数据进行梳理分析,涉及维度包括行业专利基本状况分析、地域分析、技术分析、发明人分析、申请人分析、专利权人分析、失效分析、核心专利分析、法律分析、研发重点分析、企业专利处境分析、技术处境分析、专利寿命分析、企业定位分析、引证分析等超过60个分析角度,系统通过AI智能系统对图表进行解读,只需1分钟,一键生成行业专利分析报告。

申请试用

QQ群二维码
意见反馈