Sony Corporation

Hongchang Bao

Naoto Iwahashi

Hitoshi Honda

It is intended to increase the recognition rate in speech recognition and image recognition. An observation vector as input data, which represents a certain point in the observation vector space, is mapped to a distribution having a spread in the feature vector space, and a feature distribution parameter representing the distribution is determined. Pattern recognition of the input data is performed based on the feature distribution parameter.

Feature extraction apparatus and method and pattern recognition apparatus and method

The silence-acoustic-model correcting division generates a silence acoustic model that is used for recognizing the silent section Ts which exists in the beginning of the speech recognition section, on the basis of the environment noise that is included in the noise observation section Tn.

Pattern recognizing device and method, and providing medium

A feature extraction and pattern recognition system in which an observation vector forming input data, which represents a certain point in the observation vector space, is mapped to a distribution having a spread in the feature vector space, and a feature distribution parameter representing the distribution is determined. Pattern recognition of the input data is performed based on the feature distribution parameter.

Growing community of inventors

Tokyo, Japan

Hongchang Bao