Sharp Kabushiki Kaisha Corporation

Computer Basic Technology Research Association

Atsuo Tanaka

Fumio Togawa

Shin Kamiya

Hirokazu Izumi

Takao Fukuda

Toshihiko Sugimura

An image processing apparatus of the present invention includes: an appearance data generating sectionfor generating appearance data according to a drawing appearance of a processed document; a classification information producing sectionfor producing, from the appearance data, classification information for classifying the processed document; a data file save processing section(saving section) for saving in a storage section a data file of the processed document together with the classification information of the data file; an appearance information inputting section(inputting section) for inputting the appearance information of the processed document desired by a user; an appearance information converting sectionfor converting the appearance information into classification information to output the classification information; and a searching sectionfor searching the storage sectionto find the data file of the processed document consistent with the outputted classification information. This enables the user to search the processed document easily and quickly to reuse it.

Image processing apparatus, image forming apparatus, method for searching processed document, program for searching processed document, and recording medium

A voice recognition system is disclosed which has incorporated therein information on the phonological effects on syllables. The system receives a voice signal and tentatively identifies syllable arrays and provides a collection of data on syllables in the arrays. The data are used to generate hypothetical syllable arrays from the tentatively identified arrays. The hypothetical arrays are evaluated via arithmetic operations, taking into consideration the effects of context, the speaker's habit and dialect, thereby determining a reliable representation of the input voice signal.

Voice recognition method by analyzing syllables

Syllables are recognized in voice data obtained from an input voice signal. Character arrays are used to represent the types and time frames of syllables with which the voice data are compared.

Syllable recognition system

Spoken words are recognized in a sequence of steps: first finding candidate words in the form of mono-syllabic sequences; then associating (correcting) each mono-syllabic sequence to more speech-like sounds, then comparing with pre-stored dictionary words for final recognition.

Recognition of speech or speech-like sounds using associative memory

A computer for calculating the similarity between first and second patterns, each represented by a sequence of feature vectors, comprises a calculating circuit for calculating a weighting factor from feature vectors in the first pattern, a weighting circuit for applying the weighting factor to the feature vectors of the second pattern to calculate an estimated vector for the second pattern, and a similarity calculating circuit for calculating and determining the similarity between the first and the second patterns on the basis of the feature vector of the first pattern and of the estimated vector of the second pattern.

Growing community of inventors

Mie, Japan

Atsuo Tanaka