Patent US5359695A successfully refreshed from Google Patents.
US5359695A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Speech perception apparatus
Assignee: Canon Inc
•
Filing: 1993-10-19
•
Granted: 1994-10-25
•
Expires: 2013-10-19
Abstract
Abstract Speech perception is performed by obtaining similarity between an input speech and a reference speech and discriminating the input speech; selectively outputting discrimination information or color information corresponding to the similarity derived; and displaying the discrimination information or color information output selectively by a predetermined symbol or color. With this apparatus, the person who utters can know the condition of his utterance and accuracy of speech perception of the apparatus.
Inventors
- 👤 Yasunori Ohora
- 👤 Koichi Miyashiba
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-05 15:14
CPC Classifications
G; G10; G10L; G10L21/00; G10L21/06; G10L15/00; G10L15/08; G10L15/10
Claims Analysis
Total Claims: 21
Claim 1
Independent Claim
176 words
A speech recognition apparatus comprising: memory means for storing a plurality of reference speech data; input means for inputting ordinary speech data; deriving means, coupled to said input means and to said memory means, for comparing the input ordinary speech data with each of the stored plurality of reference speech data, and for deriving similarity data indicative of similarity between said ordinary speech data and said reference speech data in response to the comparing result; data generating means, coupled to said deriving means, for generating level data indicative of a level of said similarity data derived by said deriving means; and output control means for displaying a plurality of patterns in colors indicative of the level data indicative of a level of similarity between the reference speech data corresponding to the displayed patterns and the input ordinary speech data, wherein based on the color of one of the patterns displayed by said output control means, the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 2
Dependent Claim
176 words
A speech recognition apparatus comprising: memory means for storing a plurality of reference speech data; input means for inputting ordinary speech data; deriving means, coupled to said input means and to said memory means, for comparing the input ordinary speech data with each of the stored plurality of reference speech data, and for deriving similarity data indicative of similarity between said ordinary speech data and said reference speech data in response to the comparing result; data generating means, coupled to said deriving means, for generating level data indicative of a level of said similarity data derived by said deriving means; and output control means for displaying a plurality of patterns in colors indicative of the level data indicative of a level of similarity between the reference speech data corresponding to the displayed patterns and the input ordinary speech data, wherein based on the color of one of the patterns displayed by said output control means, the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 3
Dependent Claim
17 words
A speech recognition apparatus according to claim 1, further comprising means for storing said reference speech data.
Claim 4
Dependent Claim
45 words
A speech recognition apparatus according to claim 1, wherein said pattern comprises a character so that said pattern output means displays a character corresponding to said reference speech data in a color indicative of the level of similarity data generated by said data generating means.
Claim 5
Dependent Claim
44 words
A speech recognition apparatus according to claim 1, further comprising register means for comparing the input ordinary speech data and the plurality of reference speech data and registering the input ordinary speech data that is most similar to the plurality of reference speech data.
Claim 6
Dependent Claim
23 words
A speech recognition apparatus according to claim 4, wherein said pattern output means displays a pattern which is registered by said register means.
Claim 7
Dependent Claim
38 words
Apparatus according to claim 1, further comprising: switching means for switching said apparatus between a registration mode in which said apparatus registers reference speech data and a speech recognition mode in which said apparatus recognizes ordinary speech data.
Claim 8
Dependent Claim
21 words
A speech recognition apparatus according to claim 6, wherein said memory means stores a reference speech data in a registration mode.
Claim 9
Dependent Claim
25 words
A speech recognition apparatus according to claim 6, wherein said deriving means compare two speech data, and derives similarity data in a speech recognition mode.
Claim 10
Dependent Claim
21 words
A speech recognition apparatus according to claim 6, wherein said data generating means generates the data in a speech recognition mode.
Claim 11
Dependent Claim
126 words
A speech recognition apparatus comprising: input means for inputting speech data; deriving means for deriving similarity data indicative of similarity between said input speech data and a reference speech data; value data generating means for weighting the plurality of similarity data derived by said deriving means based on prior recognition data of each reference speech data, thereby producing value data; and pattern output means for displaying a plurality of patterns in colors indicative of the level of the value data of the reference speech data corresponding to the patterns, wherein based on the color of one of the patterns displayed by said pattern output means, the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 12
Dependent Claim
126 words
A speech recognition apparatus comprising: input means for inputting speech data; deriving means for deriving similarity data indicative of similarity between said input speech data and a reference speech data; value data generating means for weighting the plurality of similarity data derived by said deriving means based on prior recognition data of each reference speech data, thereby producing value data; and pattern output means for displaying a plurality of patterns in colors indicative of the level of the value data of the reference speech data corresponding to the patterns, wherein based on the color of one of the patterns displayed by said pattern output means, the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 13
Dependent Claim
156 words
A speech recognition method comprising the steps of: inputting ordinary speech data into a speech recognition apparatus; comparing the input ordinary speech data with each of a plurality of reference speech data stored in the speech recognition apparatus; deriving similarity data indicative of the similarity between said input ordinary speech data and said reference speech data in response to the result of said comparing step; generating level data indicative of a level of said similarity data derived in said deriving step; and displaying a plurality of pattern characters in colors indicative of the level data indicative of a level of similarity between the input ordinary speech data and the reference speech data corresponding the displayed pattern, wherein based on the color of one of the pattern characters displayed in said displaying step, the one of the pattern characters can be discriminated from another of the pattern characters displayed together with the one of the pattern characters.
Claim 14
Dependent Claim
156 words
A speech recognition method comprising the steps of: inputting ordinary speech data into a speech recognition apparatus; comparing the input ordinary speech data with each of a plurality of reference speech data stored in the speech recognition apparatus; deriving similarity data indicative of the similarity between said input ordinary speech data and said reference speech data in response to the result of said comparing step; generating level data indicative of a level of said similarity data derived in said deriving step; and displaying a plurality of pattern characters in colors indicative of the level data indicative of a level of similarity between the input ordinary speech data and the reference speech data corresponding the displayed pattern, wherein based on the color of one of the pattern characters displayed in said displaying step, the one of the pattern characters can be discriminated from another of the pattern characters displayed together with the one of the pattern characters.
Claim 15
Dependent Claim
46 words
A speech recognition apparatus according to claim 10, wherein said pattern comprises a character so that said pattern output means displays a character corresponding to said reference speech data in a color indicative of the level of value data generated by said value data generating means.
Claim 16
Dependent Claim
123 words
A speech recognition method comprising the steps of: storing a plurality of reference speech data in a speech recognition apparatus; inputting ordinary speech data into the speech recognition apparatus; comparing the input ordinary speech data with each of the stored plurality of reference speech data; deriving similarity data indicative of the similarity between said input ordinary speech data and said reference speech data in response to the result of said comparing step; generating level data indicative of a level of said similarity data derived in said deriving step; and displaying a pattern character in a color indicative of the level data indicative of a level of similarity between the input ordinary speech data and the reference speech data corresponding the displayed pattern and.
Claim 17
Dependent Claim
123 words
A speech recognition method comprising the steps of: storing a plurality of reference speech data in a speech recognition apparatus; inputting ordinary speech data into the speech recognition apparatus; comparing the input ordinary speech data with each of the stored plurality of reference speech data; deriving similarity data indicative of the similarity between said input ordinary speech data and said reference speech data in response to the result of said comparing step; generating level data indicative of a level of said similarity data derived in said deriving step; and displaying a pattern character in a color indicative of the level data indicative of a level of similarity between the input ordinary speech data and the reference speech data corresponding the displayed pattern and.
Claim 18
Dependent Claim
41 words
A speech recognition method according to claim 13, wherein said displaying step comprises the step of displaying a character corresponding to said reference speech data in a color indicative of the level of similarity data generated in said data generating step.
Claim 19
Dependent Claim
132 words
A speech recognition method comprising the steps of: inputting speech data into a speech recognition apparatus; deriving similarity data indicative of the similarity between said input speech data and reference speech data; processing a plurality of similarity data and a plurality of input speech data, and weighting the plurality of similarity data derived in said deriving step based on prior recognition data of each reference speech data, thereby producing value data; and displaying a plurality of patterns in colors indicative of the level of the value data of the reference speech data corresponding to the patterns, wherein based on the color of one of the patterns displayed in said displaying step the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 20
Dependent Claim
132 words
A speech recognition method comprising the steps of: inputting speech data into a speech recognition apparatus; deriving similarity data indicative of the similarity between said input speech data and reference speech data; processing a plurality of similarity data and a plurality of input speech data, and weighting the plurality of similarity data derived in said deriving step based on prior recognition data of each reference speech data, thereby producing value data; and displaying a plurality of patterns in colors indicative of the level of the value data of the reference speech data corresponding to the patterns, wherein based on the color of one of the patterns displayed in said displaying step the one of the patterns can be discriminated from another of the patterns displayed together with the one of the patterns.
Claim 21
Dependent Claim
42 words
A speech recognition method according to claim 15, wherein said displaying step comprises the step of displaying a character corresponding to said reference speech data in a color indicative of the level of value data generated in said value data generating step.
References Cited (Backward Citations)
US3639691A
Cited
US3634759A
Cited
USRE31188E
Cited
US4335276A
Cited
US4718095A
Cited
US4641343A
Cited
US4866778A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1997-10-24 | 1998-04-25 | 1998-10-25 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2001-10-24 | 2002-04-25 | 2002-10-25 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2005-10-24 | 2006-04-25 | 2006-10-25 | $7700.00 | Window Closed / Lapsed |