首页>
外国专利>
HYPOTHETICAL RESCORING APPARATUS WHICH PERFORMS HYPOTHETICAL RESCORING IN SPEECH RECOGNITION SYSTEM
HYPOTHETICAL RESCORING APPARATUS WHICH PERFORMS HYPOTHETICAL RESCORING IN SPEECH RECOGNITION SYSTEM
展开▼
机译:在语音识别系统中执行假想记分的假想记分装置
展开▼
页面导航
摘要
著录项
相似文献
摘要
PROBLEM TO BE SOLVED: To rescore a hypothesis of an ASR (Automatic Speech Recognition) system by efficiently reflecting a wide speech context while lowering a data amount necessary for training of a speech model.;SOLUTION: A hypothetical rescoring apparatus includes a memory storing first, second and third acoustic models. The acoustic model corresponds to probability density functions p(X|A), p(X|A-) and p(X|A+) of an observed value X when a central phoneme basic unit A, a multi-phoneme context A- preceding the central phoneme basic unit A and a multi-phoneme context A+ following the central phoneme basic unit A are given. The apparatus further includes a rescoring unit calculating a given hypothetical acoustic score by an expression (1). The acoustic score of the j-th phoneme is given by an expression (2). Aj is the central phoneme basic unit including a given hypothetical j-th phoneme, Xj is a j-th observed value unit separated in a given hypothesis, and N is the number of the phonemes in the hypothesis.;COPYRIGHT: (C)2007,JPO&INPIT
展开▼
机译:解决的问题:通过有效地反映宽广的语音环境,同时降低训练语音模型所需的数据量,来重述ASR(自动语音识别)系统的假设。解决方案:一种假设的记录设备包括首先存储存储器的设备,第二和第三声学模型。声学模型对应于观测值X时的概率密度函数p(X | A),p(X | A - Sup>)和p(X | A + Sup>)。中央音素基本单元A,中央音素基本单元A之前的多音素上下文A - Sup>和中央音素基本单元A之后的多音素上下文A + Sup>给出。该设备还包括记录单元,该记录单元通过表达式(1)计算给定的假设声学得分。第j个音素的声学分数由表达式(2)给出。 A j Sub>是包含给定假设的第j个音素的中央音素基本单位,X j Sub>是在给定假设中分离的第j个观察值单位,N为假设中的音素数。;版权:(C)2007,JPO&INPIT
展开▼