EP0472193A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Translation device based on voice recognition and voice synthesis
Assignee: Oki Electric Industry Co Ltd
•
Filing: 1991-08-22
•
Granted: —
•
Expires: 2011-08-22
Abstract
Abstract A voice processing device, such as a translation device based on voice recognition. The voice is inputted through microphone (10) while operation switch is held down. Voice recognition section (14, 20, 22) recognizes the word spoken in a certain language which is contained in this voice signal by searching voice recognition dictionary (22), and outputs an indication which represents the recognized word. The recognized word is visualized on display device (32). If the displayed word is what is wanted by a user, the user waits for prescribed duration (t0) from this point of time. When prescribed duration (t0) elapses, voice synthesis section (16) reads, decodes and decompresses the voice signal from translation dictionary (36) where the voice signal for the word expressed in other language is stored in the compression-encoded form, and vocally outputs it from speaker (12). Through this procedure, the word expressed in the different language is outputted from speaker (12), corresponding to the voice inputted through microphone (10). These vocally expressed words may be visualized on display device (32) by operating key (44). If the word, which is displayed on display device (32) by voice recognition, is not what the user wants, the user can operates key (44) to interrupt the voice, which is being outputted by voice synthesis section (16) and output prescribed common phrases in the vocal form. The word to be inputted may be a key word, and in this case, voice synthesis section (16) outputs the sentences associated with the key word.
Inventors
- 👤 Waichiro c/o OKI Electric Ind. Co. Ltd. Tsujita
- 👤 Kenichi c/o OKI Electric Ind. Co. Ltd. Hirayama
- 👤 Kyosuke c/o OKI Electric Ind. Co. Ltd. Hoshino
- 👤 Katsumi c/o OKI Electric Ind. Co. Ltd Takahashi
- 👤 Toru c/o OKI Electric Industry Co. Ltd. Miyamae
- 👤 Seiichi c/o OKI Electric Industry Co. Ltd. Wada
- 👤 Takanori c/o OKI Electric Ind. Co. Ltd. Murata
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-09 17:35
CPC Classifications
G; G10; G10L; G10L15/00; G10L15/26; G06; G06F; G06F40/00; G06F40/40; G06F40/55
Claims Analysis
Total Claims: 43
Claim 1
Independent Claim
230 words
A voice processing device, comprising: input means for receiving a voice signal representing a word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and producing an indication representing the recognized word; output means for reading out an output signal, corresponding to the indication, from a storage medium where the output signal is stored in correspondence to the indication; and control means interconnected to said voice recognition means and output means for controlling said voice recognition means and output means to cause the output signal corresponding to the voice signal to be developed; CHARACTERIZED IN THAT said control means (26, 34, 28, 30, 24, 44, 48) comprises: holding means (58) for holding the indication developed from said voice recognition means (20, 14, 22); and command means (44, 60) for entering a command causing the output signal developed from said output means (16, 40, 42, 12) to be developed again; said control means (26, 34, 28, 30, 24, 44, 48) being operative in response to the indication developed from said voice recognition (20, 14, 22) to transfer the indication to said output means (16, 40. 42, 12) and store the indication in said holding means (58), and in response to said command means (44, 60) to transfer the indication held in said holding means (58) to said output means (16, 40, 42, 12).
Claim 2
Dependent Claim
27 words
A device in accordance with claim 1, CHARACTERIZED IN THAT said output means comprises conversion means (16, 40) for converting the output signal to the voice signal.
Claim 3
Dependent Claim
65 words
A device in accordance with claim 2, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36), in correspondence to the indication; and said output means (16, 40, 42, 12) comprises reproduction means (42, 12), including loud speaker (12), for reproducing the voice signal developed from said conversion means (16, 40) in the form of a voice signal.
Claim 4
Dependent Claim
55 words
A device in accordance with claim 3, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium in the compression-encoded form; and said conversion means (16, 40) comprises supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42, 12) with the resulting signal.
Claim 5
Dependent Claim
45 words
A device in according with claim 2, CHARACTERIZED IN THAT the output signal representing the voice signal for a language different from the language recognized by said voice recognition means (20, 14, 22) is stored in said storage medium (36), in correspondence to the indication.
Claim 6
Dependent Claim
164 words
A voice processing device, comprising: input means for receiving a voice signal representing a word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and producing an indication representing the recognized word; output means for reading out an output signal, corresponding to the indication, from a storage medium where the output signal is stored in correspondence to the indication; and control means interconnected to said voice recognition means and output means for controlling said voice recognition means and output means to cause the output signal corresponding to the voice signal to be developed; CHARACTERIZED IN THAT said storage medium (36) is discrete memory device (144, 144a) by itself and is provided with memory locations where the output signal is stored in correspondence to the indication; and said output means (16, 40, 42, 12, 56, 46) comprises connecting means (56) for connecting removably said storage medium (36) to said output means (16, 40, 42, 12, 56, 46).
Claim 7
Dependent Claim
103 words
A device in accordance with claim 6, CHARACTERIZED IN THAT said storage medium (36) contains identification code (124) which shows the category of said storage medium (36), and the category of said storage medium (36) includes types and purposes of the output signal; said control means (26, 34, 28, 30, 24) comprises holding means (30) for holding identification code (124); and said control means (26, 34, 28, 30, 24) reads identification code (124) from said storage medium (36), compares it to the identification code held in said holding means (30), and activates said voice recognition means (20, 14, 22) if both codes match.
Claim 8
Dependent Claim
180 words
A device in accordance with claim 7, wherein said voice recognition means contains a recognition dictionary means where the reference voice signal, which is used for recognizing the word contained in the voice signal, is renewably cataloged; said voice recognition means being provided with first operation mode, and in the first operation mode, said voice recognition means catalogs the voice signal, which is received by said input means, in said recognition dictionary means as the reference voice signal which corresponds to the voice signal; said voice recognition means being provided with second operation mode, and in the second operation mode, the word contained in the voice signal is recognized by comparing the voice signal, which is received by said input means, to the reference voice signal; CHARACTERIZED IN THAT if identification code (124) read from said storage medium (36) does not match the identification code held in said holding means, said control means (26, 34, 28, 30, 24) controls said voice recognition means (20, 14, 22) so that said voice recognition means (20, 14, 22) moves to the first mode.
Claim 9
Dependent Claim
81 words
A device in accordance with claim 6, CHARACTERIZED IN THAT said device further comprises: display means (32) for visualizing the output signal; and command means (44) interconnected to said control means (26, 34, 28, 30, 24) for entering a command causing the output signal to be visualized; and said control means (26, 34, 28, 30, 24) being operative in response to said command means (44) to control said display means (32) to cause said display means to visualize the output signal.
Claim 10
Dependent Claim
33 words
A device in accordance with claim 6, CHARACTERIZED IN THAT said output means (16, 40, 42, 12, 56, 46) comprises conversion means (16, 40) for converting the output signal into the voice signal.
Claim 11
Dependent Claim
63 words
A device in accordance with claim 10, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in correspondence to the indication; said output means (16, 40, 42, 12, 56, 46) comprising reproduction means (42, 12) including a loud speaker (12) for reproducing the voice signal, which is outputted from said conversion means (16, 40), in the form of a voice.
Claim 12
Dependent Claim
55 words
A device in accordance with claim 11, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36) in the compression-encoded form; said conversion means (16, 40) comprising supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42, 12) with the resulting signal.
Claim 13
Dependent Claim
45 words
A device in accordance with claim 10, CHARACTERIZED IN THAT the output signal representing the voice signal in a language different from the language recognized by said voice recognition means (20, 14, 22) is stored in said storage medium (36), in correspondence to the indication.
Claim 14
Dependent Claim
215 words
A voice processing device comprising: input means for receiving the voice signal representing the word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and outputting first indication representing the recognized word; storage means provided with plural memory locations, at one of which the output signal representing the words is stored; output means interconnected to said storage means for reading out the output signal corresponding to the first indication, from said storage means; and control means interconnected to said voice recognition means and output means for controlling said voice recognition means and output means to output the output signal corresponding to the voice signal, CHARACTERIZED IN THAT said control means comprises correspondence establishing means (312, 306) for outputting the second indication which establishes a correspondence between the key word and one of the plural memory locations; said correspondence establishing means (312, 306) receiving the word outputted from said voice recognition means as key word (302) and transferring the second indication, which corresponds to key word (302), to said storage means (304, 314); said storage means (304, 314) reading the output signal, which is stored at the memory locations, from the memory locations represented by the second indication and outputs it to said output means (316, 318, 12).
Claim 15
Dependent Claim
55 words
A device in accordance with claim 14, CHARACTERIZED BY situation input means (320) for inputting a code expressing the situation; said correspondence establishing means (324, 312a, 306a, 310, 308) outputting the signal representing the memory location in said storage means (304, 314), as the second indication, in correspondence to key word (302) and the situation.
Claim 16
Dependent Claim
29 words
A device in accordance with claim 14, CHARACTERIZED IN THAT said output means (316, 318, 12) comprises conversion means (316) for converting the output signal to the voice signal.
Claim 17
Dependent Claim
60 words
A device in accordance with claim 16, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage means (304, 314), in correspondence to the indication; said output means (316, 318, 12) comprising reproduction means (12, 318) including loud speaker (12) for reproducing the voice signal outputted from said conversion means (316), in the vocal form.
Claim 18
Dependent Claim
56 words
A device in accordance with claim 17, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage means (304, 314), in the compression encoded form; said conversion means (316) comprising supply means (316) for decoding and decompressing the output signal and supplying said reproduction means (12, 318) with the resulting signal.
Claim 19
Dependent Claim
44 words
A device in accordance with claim 16, CHARACTERIZED IN THAT the output signal representing the voice signal of a language different from the language recognized by said voice recognition means (300) is stored in said storage means (304, 314), in correspondence to the indication.
Claim 20
Dependent Claim
218 words
A voice processing device comprising: input means for receiving the voice signal representing the word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and outputting the indication representing the recognized word; display means for visualizing the display; output means for reading out the output signal, which corresponds to the indication, from said storage medium where the output signal is stored in correspondence to the indication; and control means interconnected to said voice recognition means, display means and output means for controlling said voice recognition means, display means and output means so that the display is visualized on said display means and the output signal, which corresponds to the voice signal, is outputted to said output means; CHARACTERIZED IN THAT said device further comprises timer means (34) for clocking prescribed duration (t0), under the control of said control means (26, 34, 28, 30, 24, 44, 48); said control means (26, 34, 28, 30, 24, 44, 48) initiating, when the indication is outputted from said voice recognition means (20, 14, 22), the clocking of said prescribed duration (t0) by said timer means (34), and transferring, when the elapse of said prescribed duration (t0) is clocked by said timer means (34), the outputted indication to said display means (16, 40, 42, 12).
Claim 21
Dependent Claim
90 words
A device in accordance with claim 20, CHARACTERIZED BY command means (44) for entering the command to change the display visualized on said display means (32); said control means (26, 34, 28, 30, 24, 44, 48) making, when the command is inputted from said command means (44) before said timer means (34) finishes clocking the elapse of said prescribed duration (t0), said voice recognition means (20, 14, 22) output the indication which represents the next word in line among the words recognized by said voice recognition means (20, 14, 22).
Claim 22
Dependent Claim
31 words
A device in accordance with claim 20, CHARACTERIZED IN THAT said output means (16, 40, 42, 12) comprises conversion means (16, 40) for converting the output means to the voice signal.
Claim 23
Dependent Claim
62 words
A device in accordance with claim 22, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36), in correspondence to the indication; said output means (16, 40, 42, 12) comprising reproduction means (42, 12) including a loud speaker (12) for reproducing the voice signal outputted from said conversion means (16, 40) in the vocal form.
Claim 24
Dependent Claim
55 words
A device in accordance with claim 23, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage means (36), in the compression-encoded form; said conversion means (16, 40) comprising supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42, 12) with the resulting signal.
Claim 25
Dependent Claim
45 words
A device in accordance with claim 22, CHARACTERIZED IN THAT the output signal representing the voice signal in a language different from the language recognized by said voice recognition means (20, 14, 22) is stored in said storage medium (36), in correspondence to the indication.
Claim 26
Dependent Claim
269 words
A voice recognition means comprising: input means for receiving a voice signal representing a word; recognition dictionary means wherein the voice signal received by said input means is renewably cataloged as the reference voice signal; voice recognition means, interconnected to said input means and recognition dictionary means and also provided with the first operation mode, and the second operation mode, for recognizing the word represented by the received voice signal by comparing the voice signal received by said input means to the reference voice signal and outputting the indication representing the recognized word in the second mode; and control means interconnected to said voice recognition means for controlling said voice recognition means so that the voice signal received by said input means is cataloged in said recognition dictionary means, as the reference voice signal, in correspondence to the indication, CHARACTERIZED IN THAT said device further comprises command means (44) connected to said control means (26, 34, 28, 30, 24, 126) for entering the command to negate the cataloging of the reference voice signal, in correspondence to the indication; said control means (26, 34, 28, 30, 24, 126) comprising holding means (30, 126) for holding the command in correspondence to the indication; and said control means (26, 34, 28, 30, 24, 126) holds the command in said holding means (30, 126) corresponding to the indication when the command is inputted from said command means (44) in the first operation mode, and controls said voice recognition means (14) to prevent the reference voice signal from being cataloged for the indication corresponding to the command held in said holding means (30, 126).
Claim 27
Dependent Claim
74 words
A device in accordance with claim 26, CHARACTERIZED BY display means (32) for displaying visually the word to be cataloged; said control means (26, 34, 28, 30, 24, 126) controlling said display means (32) to cause the word to be cataloged to be displayed on said display device (32) and also said input means to be enabled, if the command is not held in said holding means (30, 126) in the first operation mode.
Claim 28
Dependent Claim
50 words
A device in accordance with claim 26, CHARACTERIZED BY output means (16, 46, 42, 12) for reading and outputting the output signal which corresponds to the indication outputted from said voice recognition means (14), from said storage medium (36) where the output signal is stored in correspondence to the indication.
Claim 29
Dependent Claim
75 words
A device in accordance with claim 28, CHARACTERIZED IN THAT said device further comprises connection means (229, 226, 56, 222) for connecting removably said recognition dictionary means (22a) and said storage medium (36) to said voice recognition means (14) and said output means (16, 46, 42, 12), respectively; said recognition dictionary means (22a) itself forming a discrete storage device, as said storage medium (36) does, and being removably connected to said voice recognition means (14).
Claim 30
Dependent Claim
30 words
A device in accordance with claim 28, CHARACTERIZED IN THAT said output means (16, 46, 42, 12) comprises conversion means (16) for converting the output signal to the voice signal.
Claim 31
Dependent Claim
60 words
A device in accordance with claim 30, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36), in correspondence to the indication; said output means (16, 46, 42, 12), which includes a loud speaker (12), comprising reproduction means for reproduce the voice signal outputted from said conversion means (16), in the vocal form.
Claim 32
Dependent Claim
54 words
A device in accordance with claim 31, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36) in the compression-encoded form; said conversion means (16) comprising supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42, 12) with the resulting signal.
Claim 33
Dependent Claim
37 words
A device in accordance with claim 30, CHARACTERIZED IN THAT the output signal representing the voice signal in a language from the language recognized by said voice recognition means (14) is stored in said storage medium (36).
Claim 34
Dependent Claim
205 words
A voice processing device comprising: input means for receiving a voice signal representing a word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and outputting the indication representing the recognized word; output means for reading and outputting the output signal, which corresponds to the indication, from the storage medium where the output signal is stored in correspondence to the indication; and control means interconnected to said voice recognition means and output means for controlling said voice recognition means and output means to output the output signal which corresponds to the voice signal, CHARACTERIZED IN THAT said input means (10, 18) further comprises: voice input means (10, 18) including microphone (10) for receiving the voice and converting it to the voice signal under the control of said control means (26, 34, 28, 30, 24); and command means (44) interconnected to said control means (26, 34, 28, 30, 24) for entering a command enabling the voice to be inputted to said voice input; said control means (26, 34, 28, 30, 24) making it possible for the voice to be inputted to said voice input means (10, 18) only when the command from said command means (44) is present.
Claim 35
Dependent Claim
30 words
A device in accordance with claim 34, CHARACTERIZED IN THAT said output means (16, 46, 42, 12) comprises conversion means (16) for converting the output signal to the voice signal.
Claim 36
Dependent Claim
63 words
A device in accordance with claim 35, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said memory means (36) in correspondence to the indication; and said output means (16, 40, 42, 12) including a loud speaker (12) comprises reproduction means (42, 12) for reproducing the voice signal outputted from said conversion means (16, 40) in the vocal form.
Claim 37
Dependent Claim
56 words
A device in accordance with claim 36, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36) in the compression-encoded form; and said conversion means (16, 40) comprises supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42, 12) with the resulting signal.
Claim 38
Dependent Claim
45 words
A device in accordance with claim 35, CHARACTERIZED IN THAT the output signal representing the voice signal in a language different from the language recognized by said voice recognition means (20, 14, 22) is stored in said storage medium (36) in correspondence to the indication.
Claim 39
Dependent Claim
230 words
A voice processing means comprising: input means for receiving a voice signal representing a word; voice recognition means interconnected to said input means for recognizing the word represented by the voice signal and outputting the indication representing the recognized word; output means for reading out the output signal, which corresponds to the indication, from the storage medium containing the memory locations where the output signal is stored in correspondence to the indication; and control means interconnected to said voice recognition means and output means for controlling said voice recognition means and output means to output the output signal which corresponds to the voice signal; CHARACTERIZED IN THAT said storage medium (366) contains additional memory locations (139) where a prescribed output signal is stored; said device further comprising command means (44) interconnected to said control means (26, 34, 28, 30, 24) for entering the command to interrupt the output of the output signal from said output means (16, 40, 42, 12); said control means (26, 34, 28, 30, 24) controlling said output means (16, 40, 42, 12) in response to the command so that the output of the output signal from said output means (16, 40, 42, 12) is interrupted, and then, the prescribed output signal is read from said storage medium (36) by said output means (16, 40, 42, 12) and outputted by said output means (16, 40, 42, 12).
Claim 40
Dependent Claim
30 words
A device in accordance with claim 39, CHARACTERIZED IN THAT said output means (16, 40, 42, 12) comprises conversion means (16, 40) for converting the output signal to voice signal.
Claim 41
Dependent Claim
62 words
A device in accordance with claim 40, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (37) in correspondence to the indication; said output means (16, 40, 42, 12) including a loud speaker (12) comprising reproduction means (42, 12) for reproducing the voice signal outputted from said conversion means (16, 40) in the vocal form.
Claim 42
Dependent Claim
56 words
A device in accordance with claim 41, CHARACTERIZED IN THAT the output signal representing the voice signal is stored in said storage medium (36) in the compression-encoded form; and said conversion means (16, 40) comprises supply means (16) for decoding and decompressing the output signal and supplying said reproduction means (42. 12) with the resulting signal.
Claim 43
Dependent Claim
45 words
A device in accordance with claim 40, CHARACTERIZED IN THAT the output signal representing the voice signal in a language different from the language recognized by said voice recognition means (20, 14, 22) is stored in said storage medium (36) in correspondence to the indication.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.