CDNN: a context dependent neural network for continuous speech recognition
CDNN: a context dependent neural network for continuous speech recognition
复制标题
DOI：
10.1109/icassp.1992.226048
复制
发表时间：
1992-03
期刊：
影响因子：
--
通讯作者：
H. Bourlard;N. Morgan;Chuck Wooters;S. Renals
中科院分区：
文献类型：
--
作者：
H. Bourlard;N. Morgan;Chuck Wooters;S. Renals
一系列的理论和实验结果表明，多层感知器（mlp）是一种有效的算法家族，用于平滑估计高维概率密度函数，在连续语音识别中很有用。所有这些系统都专门使用了与上下文无关的语音模型，从某种意义上说，概率或成本是对简单的语音单位（如音素或单词）进行估计的，而不是对双音或三音进行估计。许多基于隐马尔可夫模型（hmm）的传统系统已经被报道使用三联音或三联音类似上下文依赖模型。在一种情况下，使用许多上下文相关的mlp（每个上下文类一个）的输出来帮助从由上下文相关的HMM系统确定的N个最佳句子中选择最佳句子。它显示了如何在没有任何简化假设的情况下，使用并不比上下文无关的mlp大得多的网络来估计上下文相关语音模型的可能性
A series of theoretical and experimental results have suggested that multilayer perceptrons (MLPs) are an effective family of algorithms for the smooth estimate of highly dimensioned probability density functions that are useful in continuous speech recognition. All of these systems have exclusively used context-independent phonetic models, in the sense that the probabilities or costs are estimated for simple speech units such as phonemes or words, rather than biphones or triphones. Numerous conventional systems based on hidden Markov models (HMMs) have been reported that use triphone or triphone like context-dependent models. In one case the outputs of many context-dependent MLPs (one per context class) were used to help choose the best sentence from the N best sentences as determined by a context-dependent HMM system. It is shown how, without any simplifying assumptions, one can estimate likelihoods for context-dependent phonetic models with nets that are not substantially larger than context-independent MLPs.>