首页>
外国专利>
A speech recognition system and method which mimics transform parameters and estimates the mimicked transform parameters
A speech recognition system and method which mimics transform parameters and estimates the mimicked transform parameters
展开▼
机译:一种模仿变换参数并估计模仿变换参数的语音识别系统和方法
展开▼
页面导航
摘要
著录项
相似文献
摘要
A speech recognition method comprising, receiving a speech input in a first noise environment which comprises a sequence of observations and determining the likelihood of a sequence of words arising from the sequence of observations using an acoustic model. The acoustic model comprising providing an acoustic model for performing speech recognition on a input signal which comprises a sequence of observations, wherein said model has been trained to recognise speech in a second noise environment, said model having a plurality of model parameters relating to the probability distribution of a word or part thereof being related to an observation. It also comprises adapting the model trained in the second environment to that of the first environment; the speech recognition method further comprising determining the likelihood of a sequence of observations occurring in a given language using a language model, combining the likelihoods determined by the acoustic model and the language model and outputting a sequence of words identified from said speech input signal. Adapting the model trained in the second environment to that of the first environment comprises adapting the model parameters of the model trained in the second noise environment to those of the first noise environment using transform parameters to produce a target distribution, wherein the transform parameters have a block diagonal form and are applied to regression classes, each regression class comprising a plurality of probability distributions and mimicking the target distribution using a linear regression type distribution, said linear regression type distribution comprising mimicked transform parameters and estimating the mimicked transformed parameters. The invention aims to derive a speech recognition method that is computationally on a par with a joint uncertainty decoding (JUD) method but which achieves accuracy similar to that of Vector Taylor Series (VTS) methods.
展开▼