scispace - formally typeset
Search or ask a question
Patent

Input device, input method and input system

TL;DR: In this paper, an input device is mounted in a mobile object, and provided with an input unit to which input information including a character string and correction information including one or more characters are inputted.
Abstract: This input device is mounted in a mobile object, and provided with: an input unit to which input information including a character string and correction information including one or more characters are inputted; a similarity calculation unit which edits the character string of the input information using the one or more characters of the correction information, and calculates similarity between the character strings of the input information before and after editing; and a correction processing unit which corrects the character string of the input information on the basis of the similarity calculated by the similarity calculation unit.
References
More filters
Patent
15 Aug 2013
TL;DR: In this paper, the authors proposed a system to provide a voice recognition result correction support system which can reduce recognition errors by a second utterance performed for an error recognition text correction of voice recognition.
Abstract: PROBLEM TO BE SOLVED: To provide a voice recognition result correction support system which can reduce recognition errors by a second utterance performed for an error recognition text correction of voice recognition.SOLUTION: A voice recognition result correction support system includes: voice recognition means 1 for recognizing an utterance of a user; voice recognition text display means 2 for displaying the recognized utterance as a recognition text; determination means 3 which acquires a text selected by the user from recognition texts as an error recognition text, and determines an optimum text range for making a second utterance from the recognition texts on the basis of a predetermined rule and the error recognition text; and correction utterance presentation means 4 for urging the user to provide the second utterance by displaying the optimum text range.

61 citations

Patent
28 Jan 2008
TL;DR: In this article, a vehicle number recognizing device comprising means (Step S203) for deciding the vehicle number by majority in case there are a plurality of vehicle number candidates obtained from frame images and for which the recognition results are identical to each other.
Abstract: Provided is a vehicle number recognizing device comprising means (Step S203) for deciding a vehicle number by majority in case there are a plurality of vehicle number candidates obtained from frame images and in case there are vehicle number candidates, for which the recognition results are identical to each other. Further comprised is means (Step S205) for detecting the letter numbers of a plurality of vehicle number candidates, in case the vehicle number candidates are different from each other, and for fixing, in case the letter numbers of the individual vehicle number candidates are identical, the letters, which are recognized as the mutually different results in the individual vehicle number candidates, according to the letter similarity. Further comprised is means (Step S207) for fixing the vehicle number, in case the letter numbers of the vehicle number candidates are different, from the letter positions in the vehicle number candidates and the recognition results of the individual letters.

14 citations

Patent
15 Apr 2005
TL;DR: In this article, the problem of determining a minimum cost of performing edit operations on a string to satisfy a string template is addressed. But the minimum cost is not the same as the cost of transforming a string into one or more string templates.
Abstract: Determining a set of edit operations to perform on a string, such as one generated by optical character recognition, to satisfy a string template by determining a minimum cost of performing edit operations on the string to satisfy the string template and then determining the set of edit operations corresponding to the minimum cost. Transforming a string to satisfy one or more string templates by determining a minimum cost of performing edit operations on the string to satisfy one or more string templates, selecting one or more minimum costs, determining a set of edit operations corresponding to the minimum costs, and then performing the set of edit operations on the string. Determining a minimum cost of performing edit operations on a string to satisfy a string template by determining set costs of performing sets of edit operations using costs associated with edit operations of the set and determining the minimum cost using the set costs.

5 citations

Patent
31 Oct 2013
TL;DR: In this article, a correction character string which is a normal voice recognition result of an erroneously recognized part (erroneously recognized character string) in the voice character strings from the driver via a touch pad attached to a steering (S230) is displayed.
Abstract: PROBLEM TO BE SOLVED: To provide a voice recognition device, etc. capable of easily and exactly correcting the erroneously recognized utterance content when the uttered content is erroneously recognized.SOLUTION: A voice recognition device accepts, after a voice recognition result (voice character strings) of the utterance content of a driver, etc. is displayed, input of a correction character string which is a normal voice recognition result of an erroneously recognized part (erroneously recognized character string) in the voice character strings from the driver via a touch pad attached to a steering (S230). Then, character strings with the same number of characters as that of the correction character string are extracted from the voice character strings, a character string with the most characters matched to those of the correction character string is detected as the erroneously recognized character string among the character strings (S240), and the voice character strings are corrected by replacing the erroneously recognized character string with the correction character string (S265).

3 citations

Patent
13 Oct 2016
TL;DR: In this paper, a correction speech detection device is proposed, which takes a sound signal as input, and presents a voice recognition result for the sound signal, based on the (m-1)th reaction time.
Abstract: PROBLEM TO BE SOLVED: To provide a correction speech detection device capable of determining whether a correction speech (correctly retried speech) has been performed or not, not on the basis of a change in a sound feature amount for each speechSOLUTION: A correction speech detection device of the present invention takes a sound signal as input, and presents a voice recognition result for the sound signal The correction speech detection device takes m as an integer of two or more and includes: a reaction time measuring unit for measuring a difference between a time at which a voice recognition result for a sound signal having been input at a (m-1)th time is presented and an input time of a sound signal having been input at a mth time, as a (m-1)th reaction time; and a determination unit for determining whether a correction speech is included or not in the sound signal having been input at the mth time, based on the (m-1)th reaction timeSELECTED DRAWING: Figure 1

2 citations

Trending Questions (1)
What is the input?

The input refers to the input information received by the input unit of the input device, which includes a character string and correction information.