EP0327408A2
Expired / Lapsed
EP
⏱️ 0.0 years remaining
Voice language translator
Assignee: Advanced Products and Technologies Inc
•
Filing: 1989-02-06
•
Granted: —
•
Expires: 2009-02-06
Abstract
Abstract A voice language translator, suitable for implementation in hand-held size. The translator includes: a key pad (20); a display system (17); a language cartridge(s); a voice recognition module; a voice synthesizer; a speaker; a microphone; and a programmed CPU. Prior to use as a translator, the voice language translator is trained to the voice of a user. As the user speaks the words and phrases, the voice recognition circuit produces a digitally coded voice pattern that uniquely identifies the user. The voice patterns are analyzed and stored. Thereafter, during translation, when the user speaks a sentence, the voice pattern produced by the voice recognition circuit is compared with the stored voice patterns to determine the nature of the spoken sentence. The result of the comparison is used to locate equivalent translations stored in the cartridge. Strings of words and phrases that make up sentences are combinable only in a logical manner. Illogical combinations of words and phrases are ignored. If the translator does not understand a spoken word or phrase, a list of acceptable words and phrases is displayed. With a cursor a desired word or phrase can be selected. The logical string combinations of equivalent translations are converted to audible sounds. If desired, a visual display, or an audible emission, in the language of the user can be made to occur before the translated emission takes place.
Inventors
- 👤 Stephen A. Rondel
- 👤 Joel R. Carter
Bibliographic Details
Application Number
—
Jurisdiction
EP
Data Source
google_patents
Last Synchronized
2026-11-01 11:01
CPC Classifications
G; G06; G06F; G06F17/00; G06F3/00; G06F3/16; G06F40/00; G06F40/20; G06F40/279; G10; G10L; G10L15/00; G10L15/26
Claims Analysis
Total Claims: 23
Claim 1
Independent Claim
274 words
A voice language translator for translating words spoken by a user in one language into spoken words in another language, said voice language translator comprising: language storing means for storing, in digital form, words and phrases in at least two languages; voice recognition means for receiving audible words spoken by a user and creating corresponding digital voice patterns; voice producing means for receiving digital voice patterns and producing corresponding audible words; and programmable control means connected to said language storage means, said voice recognition means and said voice producing means for translating words spoken by a user in one language into spoken words in another language by controlling the operation of said language storage means, said voice recognition means and said voice producing means, said programmable control means including a training mode of operation and a translate mode of operation, said training mode of operation training said voice language translator to understand words spoken by a user in one language by instructing a user to speak a series of words stored in said language storage means and storing in said language storing means the digital voice patterns produced by said voice recognition means in response to said user speaking said series of words, said translate mode of operation translating words spoken by said user into another language by comparing the digital voice patterns, produced by said voice recognition means when said user speaks, with said digital voice patterns stored in said language storing means and using the results of said comparison to read corresponding words in another language stored in said language storing means and apply said corresponding words to said voice producing means.
Claim 2
Dependent Claim
274 words
A voice language translator for translating words spoken by a user in one language into spoken words in another language, said voice language translator comprising: language storing means for storing, in digital form, words and phrases in at least two languages; voice recognition means for receiving audible words spoken by a user and creating corresponding digital voice patterns; voice producing means for receiving digital voice patterns and producing corresponding audible words; and programmable control means connected to said language storage means, said voice recognition means and said voice producing means for translating words spoken by a user in one language into spoken words in another language by controlling the operation of said language storage means, said voice recognition means and said voice producing means, said programmable control means including a training mode of operation and a translate mode of operation, said training mode of operation training said voice language translator to understand words spoken by a user in one language by instructing a user to speak a series of words stored in said language storage means and storing in said language storing means the digital voice patterns produced by said voice recognition means in response to said user speaking said series of words, said translate mode of operation translating words spoken by said user into another language by comparing the digital voice patterns, produced by said voice recognition means when said user speaks, with said digital voice patterns stored in said language storing means and using the results of said comparison to read corresponding words in another language stored in said language storing means and apply said corresponding words to said voice producing means.
Claim 3
Dependent Claim
75 words
A voice language translator as claimed in Claim 1, wherein at least some of said digital voice patterns stored in said language storing means are stored in banks of related words or phrases, said programmable control means only accessing selected ones of said banks in a logical sequence when comparing the digital voice patterns produced by said voice recognition means when said user speaks with said digital voice patterns stored in said language store means.
Claim 4
Dependent Claim
48 words
A voice language translator as claimed in Claim 1 or 2, wherein said voice language translator includes a display means and wherein said programmable control means causes said display means to display said series of words when said programmable control means is in said training mode of operation.
Claim 5
Dependent Claim
68 words
A voice language translator as claimed in Claim 3, wherein said training mode of operation includes a TRAIN ALL words option during which a user speaks all of the series of words stored in said language storage means as they are displayed, and a TRAIN SELECTED words option during which a user can select which of said series of words stored in said language storage means to speak.
Claim 6
Dependent Claim
63 words
A voice language translator as claimed in Claim 4, wherein said training mode of operation tests the way in which a user speaks a word by having the word repeated and analyzing the digital voice pattern produced by said voice recognition means in response to said user repeating said word to determine if the user has respoken the word in the same way.
Claim 7
Dependent Claim
54 words
A voice language translator as claimed in Claim 4, wherein said training mode of operation determines the acceptability of digital voice pattern by instructing a user to respeak a spoken word and comparing the digital voice pattern created by said respoken word with the digital voice pattern produced when said word was first spoken.
Claim 8
Dependent Claim
77 words
A voice language translator as claimed in Claim 5 or 6, wherein said control means includes a talk key that enables said voice recognition means to receive audible words spoken by a user and create corresponding digital voice patterns when said talk key is depressed and wherein said voice language translator instructs a user to depress said talk key as well as speak a word when said programmable control means is in said training mode of operation.
Claim 9
Dependent Claim
50 words
A voice language translator as claimed in Claim 7, wherein said control means includes cursor keys and wherein said cursor keys are used to scroll through words displayed by said display means when said programmable control means is in said TRAIN SELECTED words option of said training mode of operation.
Claim 10
Dependent Claim
50 words
A voice language translator as claimed in Claim 1, wherein said programmable controller logically combines the words spoken by a user into a sentence and analyzes the sentence to determine if it is a sentence suitable for translation when said programmable control means is in said translate mode of operation.
Claim 11
Dependent Claim
53 words
A voice language translator as claimed in Claim 9, wherein said analysis requires that said sentence lie in a predetermined sequence of banks accessed by said program when comparing the digital patterns produced by said voice recognition means when said user speaks with said digital voice patterns stored in said language storage means.
Claim 12
Dependent Claim
33 words
A voice language translator as claimed in Claim 9 or 10, wherein said analysis requires that said combined sentence terminate with a specific word that is unrelated to the content of the sentence.
Claim 13
Dependent Claim
48 words
A voice language translator claimed in Claim 11, wherein said spoken words are used to read corresponding words in another language stored in said language storing means and apply said corresponding words to said voice producing means immediately after said sentence is determined to be suitable for translation.
Claim 14
Dependent Claim
59 words
A voice language translator as claimed in Claim 11, wherein said sentence is provided to said user in said user's language after said sentence is determined to be legitimate prior to said spoken words being used to read corresponding words in another language stored in said language storing means and apply said corresponding words to said voice producing means.
Claim 15
Dependent Claim
24 words
A voice language translator as claimed in Claim 12, wherein said sentence is provided to said user by being displayed on said display means.
Claim 16
Dependent Claim
25 words
A voice language translator as claimed in Claim 12, wherein said sentence is provided to said user by being uttered by said voice producing means.
Claim 17
Dependent Claim
71 words
A voice language translator as claimed in Claim 15, wherein said training mode of operation includes a TRAIN ALL words option during which a user is required to speak all of the series of words stored in said language storage means as they are displayed, and a TRAIN SELECTED words option during which a user can select which of said series of words stored in said language storage means to speak.
Claim 18
Dependent Claim
72 words
A voice language translator as claimed in Claim 16, wherein said training mode of operation also includes a TEST option during which a user speaks a word to be tested and the digital voice pattern produced by said voice recognition means in response to said user speaking is analyzed to determine if the word spoken by the user is part of a legitimate code string that includes a stored digital voice pattern.
Claim 19
Dependent Claim
75 words
A voice language translator as claimed in Claim 16, wherein at least some of said digital voice patterns stored in said language storing means are stored in banks of related words or phrases, said programmable control means only accessing selected ones of said banks in a logical sequence when comparing the digital voice patterns produced by said voice recognition means when said user speaks with said digital voice patterns stored in said language store means.
Claim 20
Dependent Claim
63 words
A voice language translator as claimed in Claims 1 through 18, wherein: (a) said voice language translator includes a hand-sized housing; (b) said display means, voice recognition means, voice producing means and said programmable control means are all mounted in said hand-sized housing; and (c) said language storing means includes at least two cartridges, said cartridges being removably mounted in said hand-held housing.
Claim 21
Dependent Claim
36 words
A voice language translator as claimed in Claims 1 through 19, wherein said programmable controller displays the words in the banks when the analysis of the words spoken by a user do not find a match.
Claim 22
Dependent Claim
38 words
A voice language translator as claimed in Claim 20, wherein words spoken by a user are analyzed twice and the words in a bank are displayed only if no match is found after both analyses have been completed.
Claim 23
Dependent Claim
26 words
A voice language translator as claimed in Claims 1 through 19, wherein said user can control during translation the display of words stored in said banks.
References Cited (Backward Citations)
No citation records indexed.
USPTO Annuity & Maintenance Windows
Maintenance schedule is calculated for granted US utility patents.