The inference of genetic networks using a model based on a set of differential equations is generally time-consuming. In order to decrease its computational time, we have proposed the inference method using a normalized Gaussian network (NGnet) model. The inferred models however contain many false-positive regulations when we apply the NGnet approach to the genetic network inference problems. This paper proposes the reduced NGnet model and the gradual reduction strategy to overcome the drawbacks of the NGnet approach. Then, in order to verify their effectiveness, we apply the inference method using the proposed techniques to several artificial genetic network inference problems.

A large-vocabulary continuous-speech recognition (LVCSR) system was developed and evaluated. To evaluate the system, a Japanese business-newspaper speech corpus was designed and recorded. The corpus was designed so that is can be used for Japanese LVCSR research in the same way that the Wall Street Journal (WSJ) corpus, for example, is used for English LVCSR research. Since Japanese sentences are written without spaces between words, a morphological analysis was introduced to segment sentences into words so that word n-gram language models could be used. To enable the use of detailed word n-gram (n/spl ges/3) language models, a two-pass decoding strategy was applied. Context-dependent (CD) phone models and word trigram language models reduced the word error rate from 80.2% to 10.1% (an error reduction of about 88%). This result shows that CD phoneme modeling and word trigram language models can be used effectively in Japanese LVCSR.