Asahi Kasei Kabushiki Kaisha

Asahi Kasei Kogyo Kabushiki Kaisha

Totoku Electric Co., Ltd

Kaga Electronics Co., Ltd.

Toshiyuki Miyazaki

Shigeo Hayashi

Yoji Ishikawa

Norihito Sogo

Tsukasa Tashiro

Tomoyuki Kumai

Tohru Yamamoto

The present disclosure provides an electronic device, a control method therefor, and a control program therefor capable of preventing an operation for activating a function protected by user authentication from becoming complicated. An electronic device includes: a keyword management DB for storing identification information of a registrant and a registered keyword in association with each other; a command management DB for storing a command and required authentication scores in association with each other; a data generator for creating grammar data including a registered keyword and a command; an utterance recognizer for matching the grammar data and extracted data extracted from an utterance of a user and acquiring a recognized authentication score and a recognized command; and an authenticator for determining that the command is recognized by comparing the required authentication score associated with the command determined to be the same as the recognized command and the recognized authentication score.

Electronic device, control method for electronic device, and control program for electronic device

In accordance with alphabet input method information for each user, a word formed of an alphabet string is registered in a word dictionary, in a state where 'dotto' being added before each alphabet and one of a set of alphabets difficult to distinguish from each other like 'M and N' and &#x201c;B and P&#x201d; is repeated twice. For example, a word &#x201c;PAM&#x201d; and a feature of time series corresponding to &#x201c;dotto P P doddo A dotto M&#x201d; are registered in association with each other. When a user performs a speech input of &#x201c;PAM&#x201d;, in accordance with the user's alphabet input method information, the user utters &#x201c;dotto P P dotto A dotto M&#x201d;. A speech recognition is performed on this sound data using the word dictionary corresponding to the user's alphabet input method information.

Speech recognition apparatus for recognizing user's utterance

A weight coefficient generation device, a speech recognition device, a navigation system, a vehicle, a vehicle coefficient generation method, and a weight coefficient generation program are provided for the purpose of improving a speech recognition performance of place names. In order to address the above purpose, an address databasehas address information data items including country names, city names, street names, and house numbers, and manages the address information having a tree structure indicating hierarchical relationships between the place names from wide area to a narrow area. Each of the place names stored in the address databaseis taken as a speech recognition candidate. A weight coefficient calculation unitof a weight coefficient generation devicecalculates a weight coefficient of the likelihood of the aforementioned recognition candidate based on the number of the street names belonging to the lower hierarchy below the city names.

Weight coefficient generation device, voice recognition device, navigation device, vehicle, weight coefficient generation method, and weight coefficient generation program

A speech recognition device which can preferably be used for reducing the memory capacity required for speaker-independent speech recognition is provided. A matching unit loads speech models belonging to a first speech model network and a garbage model in a RAM, and gives a speech parameter extracted by a speech parameter extraction unit to the speech model in the RAM, and when an occurrence probability output from the garbage model is equal to or greater than a predetermined value, the matching unit loads speech models belonging to any of speech model groups in the RAM based on the occurrence probability output from the speech model belonging to the first speech model network.

Speech recognition device for recognizing a word sequence using a switching speech model network

Each word to be recognized is represented by gender-specific hidden Markov models that are stored in a ROMalong with output probability functions and preset transition probabilities. A speech recognizerdetermines an occurrence probability of a feature parameter sequence detected by a feature value detectorusing the hidden Markov models. The speech recognizerdetermines the occurrence probability by giving each word a state sequence of one hidden Markov model common to the gender-specific hidden Markov models, multiplying each preset pair of an output probability function value and a transition probability together among the output probability functions and transition probabilities stored in the ROM, selecting the largest product as the probability of each state of the common hidden Markov model, determining the occurrence probability based on the selected product, and recognizing the input speech based on the occurrence probability thus determined.

Speech recognition device and speech recognition method

A CRT display device on which an input signal which has been processed can form an image signal which results in an image being displayed. The CRT display device has a separate message section which can be a dot matrix display. On this separate message section there is a display where displayed messages indicative of the input signal. The message display section displays messages related to the input signal even when there is no image on the cathode ray tube of the CRT display device so that a user based on these messages can input parameters to provide an image on the CRT. The messages on the display device can be shown in various languages.

CRT display device

A main magnetic field is applied to a target to excite the nuclear spin of a chosen type of atoms in a selected slice of the target. Subsequently, first and second gradient fields, which are parallel to the main magnetic field noted above and the strengths of which vary in the directions of respective first and second crossing axes in the slice, are applied to the target for predetermined period of time. Then, a readout magnetic gradient field, which is parallel to the first gradient field, and the strength of which varies in the direction of the first axis, is applied to the target to detect a free induction signal from the target. The detection of the free induction signal is repeatedly performed with a plurality of different strengths of the first and second gradient fields, whereby NMR data containing chemical shift data is obtained from the slice of the target noted above.

Growing community of inventors

Tokyo, Japan

Toshiyuki Miyazaki