Mitsubishi Electric Corporation

Hiroki Sakashita

Jun Ishii

Kazuyuki Nogi

Yoichi Kato

Yuki Furumoto

Masanobu Osawa

Michihiro Yamazaki

Because a voice recognition device in accordance with the present invention can change the position where or the display form in which a display item corresponding to a voice recognition result is displayed according to the degree of importance of a display area in which the display item is displayed when recognizing a voice uttered by the user, the voice recognition device can prevent the acquisition of other information important for the user from being blocked due to the display of the display item, and improve the user's convenience.

Voice recognition device and display method

A speech recognition device includes: a speech recognition unitthat performs speech recognition for input speech; a reading information conversion data base in which a reading information conversion rule L is registered; a reading information conversion unitthat converts reading information of the word among the languages based on the rule L; and a speech recognition control unitthat performs control such that, when a word in a different language that is different from a predetermined language is included in a recognition subject vocabulary in which a speech recognition unitrefers to recognition subject word information E, the unitconverts the reading information in the different language into reading information in the predetermined language, and that the unitperforms the speech recognition that makes reference to the recognition subject word information of the corresponding word, including the converted reading information in the predetermined language.

Speech recognition device

A voice recognition system includes: a voice input unitfor inputting a voice uttered a plurality of times; a registering voice data storage unitfor storing voice data uttered the plurality of times and input into the voice input unit; an utterance stability verification unitfor determining a similarity between the voice data uttered the plurality of times that are read from the registering voice data storage unit, and determining that registration of the voice data is acceptable when the similarity is greater than a threshold Tl; and a standard pattern creation unitfor creating a standard pattern by using the voice data where the utterance stability verification unitdetermines that registration is acceptable.

Voice recognition system for registration of stable utterances

A voice recognition device is provided with a sentence selecting unit for selecting sentences each having a predetermined number or less of acoustic units as sentences to be recognized from candidates for the sentences to be recognized. According to an exemplary embodiment, the sentence selecting unit may define the selected sentences as sentences to be recognized. According to another exemplary embodiment, when a candidate for a sentence to be recognized has a number of acoustic units exceeding the predetermined number, one or more acoustic units may be trimmed from the candidate, and the trimmed candidate may be defined as one of the sentences to be recognized.

Growing community of inventors

Tokyo, Japan

Hiroki Sakashita