US5963892A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Translation apparatus and method for facilitating speech input operation and obtaining correct translation thereof
Assignee: Sony Corp
•
Filing: 1996-06-26
•
Granted: 1999-10-05
•
Expires: 2016-06-26
Abstract
Abstract A translation apparatus and a translation method arranged to facilitate the operation of inputting a speech and to obtain a correct translation. When a speech in Japanese is input to a microphone by a user, it is recognized in a speech recognition section and one or more words constituting the speech are output to a system control section. The system control section searches Japanese sentences stored in a first language sentence storage section to find one of them most similar to a combination of one or more words output from the speech recognition section. The Japanese sentence thereby found is output through an output section. If this Japanese sentence is correct, the user operates one of control keys. The system control section then searches English sentences stored in a second language sentence storage section to find one of them corresponding to a translation of the Japanese sentence output as a search result, and outputs the English sentence thereby found through the output section.
Inventors
- 👤 Miyuki Tanaka
- 👤 Hiroaki Ogawa
- 👤 Yasuhiko Kato
- 👤 Tetsuya Kagami
- 👤 Masao Watari
- 👤 Makoto Akabane
- 👤 Kazuo Ishii
- 👤 Yasuharu Asano
- 👤 Hiroshi Kakuda
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-11-09 17:22
CPC Classifications
G; G06; G06F; G06F17/00; G06F40/00; G06F40/40; G06F40/42; G06F40/45; G06F40/47; G10; G10L; G10L15/00; G10L15/08; G10L15/18; G10L15/1815
Claims Analysis
Total Claims: 37
Claim 1
Independent Claim
147 words
A translation apparatus for translating a speech input in a first language into a sentence in a second language, comprising: speech recognition means for recognizing an input speech and outputting at least one of word constituting the speech; first sentence storage means for storing sentences in the first language; second sentence storage means for storing sentences in the second language; first search means for searching the sentences stored in said first sentence storage means to find one of the sentences similar to a combination including at least one word output from said speech recognition means; second search means for searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said first search means; and output means for outputting search results obtained by said first and second search means.
Claim 2
Dependent Claim
147 words
A translation apparatus for translating a speech input in a first language into a sentence in a second language, comprising: speech recognition means for recognizing an input speech and outputting at least one of word constituting the speech; first sentence storage means for storing sentences in the first language; second sentence storage means for storing sentences in the second language; first search means for searching the sentences stored in said first sentence storage means to find one of the sentences similar to a combination including at least one word output from said speech recognition means; second search means for searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said first search means; and output means for outputting search results obtained by said first and second search means.
Claim 3
Dependent Claim
69 words
The translation apparatus of claim 1, wherein the sentences stored in said first sentence storage means and the sentences stored in said second storage means correspond to each other in a one-to-one relationship, and wherein said second search means searches the sentences stored in said second sentence storage means to find one of the sentences corresponding to the sentence in the first language found by said first search means.
Claim 4
Dependent Claim
69 words
The translation apparatus of claim 1, further comprising operation means operated when a predetermined input is given, wherein said second search means searches the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said first search means after the predetermined input has been given through the operation of said operation means.
Claim 5
Dependent Claim
45 words
The translation apparatus of claim 2, wherein said first sentence storage means stores the sentences in the first language and addresses in said second sentence storage means with which the sentences in the second language corresponding to the sentences in the first language are stored.
Claim 6
Dependent Claim
35 words
The translation apparatus of claim 3, wherein said second search means starts the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is accurate.
Claim 7
Dependent Claim
36 words
The translation apparatus of claim 3, wherein said first search means again performs the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is inaccurate.
Claim 8
Dependent Claim
48 words
The translation apparatus of claim 1, wherein said output means first outputs the sentence in the first language obtained by said first search means and outputs the sentence in the second language obtained by said second search means after the sentence in the first language has been confirmed.
Claim 9
Dependent Claim
27 words
The translation apparatus of claim 1, wherein the input speech in the first language is a speech input in the form of a series of independent words.
Claim 10
Dependent Claim
139 words
A translation method using first sentence storage means for storing sentences in a first language and second sentence storage means for storing sentences in a second language, in which a speech input in the first language is translated into a sentence in the second language, said method comprising the steps of: recognizing an input speech and outputting at least one of word constituting the speech; searching the sentences stored in said first sentence storage means to find and output one of the sentences similar to a combination including at least one word output as a speech recognition result; and searching the sentences stored in said second sentence storage means to find and output one of the sentences corresponding to a translation of the sentence in the first language output as a search result when a predetermined input is given.
Claim 11
Dependent Claim
139 words
A translation method using first sentence storage means for storing sentences in a first language and second sentence storage means for storing sentences in a second language, in which a speech input in the first language is translated into a sentence in the second language, said method comprising the steps of: recognizing an input speech and outputting at least one of word constituting the speech; searching the sentences stored in said first sentence storage means to find and output one of the sentences similar to a combination including at least one word output as a speech recognition result; and searching the sentences stored in said second sentence storage means to find and output one of the sentences corresponding to a translation of the sentence in the first language output as a search result when a predetermined input is given.
Claim 12
Dependent Claim
80 words
The translation apparatus of claim 1 wherein said speech recognition section includes: an analog-to-digital converter for quantizing the input speech and for generating a corresponding digital speech signal; an acoustic analyzer for analyzing the acoustic form of the digital speech signal and for extracting feature parameters of the speech signal; a dictionary for storing standard word patterns; and a recognition processor for performing speech recognition on the basis of the feature parameters and in accordance with the standard word patterns.
Claim 13
Dependent Claim
41 words
The translation apparatus of claim 10 further including a clock configured to provide a clock signal, and further, wherein said analog-to-digital converter is configured to sample the input speech in accordance with the clock signal to generate the digital speech signal.
Claim 14
Dependent Claim
30 words
The translation apparatus of claim 10 wherein the feature parameters of the speech signal includes the power of the speech signal in each of a predetermined ranges of speech signal.
Claim 15
Dependent Claim
48 words
The translation apparatus of claim 12 wherein the acoustic analyzer is configured to filter the speech signal with respect to each of the predetermined ranges to generate an filtered speech signal, and further, wherein the acoustic analyzer is further configured to rectify and smooth the filtered speech signal.
Claim 16
Dependent Claim
21 words
The translation apparatus of claim 10 wherein said output means includes a voice synthesizer and a speaker, or a visual monitor.
Claim 17
Dependent Claim
68 words
The method of claim 9 wherein the sentences stored in said first sentence storage means and the sentences stored in said second storage means correspond to each other in a one-to-one relationship, and further including the step of searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to the sentence in the first language found by said first search means.
Claim 18
Dependent Claim
88 words
The method of claim 9 further including the step of operating an operating means when a predetermined input is given, wherein said step of searching said second sentence storage means further includes the step of searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said step of searching said first sentence storage means after the predetermined input has been given through the step of operating said operation means.
Claim 19
Dependent Claim
43 words
The method of claim 15 further including the step of storing the sentences in the first language and addresses in said second sentence storage means with which the sentences in the second language corresponding to the sentences in the first language are stored.
Claim 20
Dependent Claim
34 words
The method of claim 16 further including the step of performing the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is accurate.
Claim 21
Dependent Claim
34 words
The method of claim 16 further including the step of re-performing the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is inaccurate.
Claim 22
Dependent Claim
46 words
The method of claim 9 further including the steps of outputting the sentence in the first language obtained by said first search means and outputting the sentence in the second language obtained by said second search means after the sentence in the first language is confirmed.
Claim 23
Dependent Claim
26 words
The method of claim 9 wherein the input speech in the first language is a speech input in the form of a series of independent words.
Claim 24
Dependent Claim
68 words
The method of claim 9 wherein said step of recognizing the input speech includes the steps of: quantizing the input speech and generating a corresponding digital speech signal; analyzing the acoustic form of the digital speech signal and extracting feature parameters of the speech signal; storing standard word patterns; and performing speech recognition on the basis of the feature parameters and in accordance with the standard word patterns.
Claim 25
Dependent Claim
40 words
The method of claim 22 further including the step of providing a clock signal, wherein said step of quantizing further includes the step of sampling the input speech in accordance with the clock signal to generate the digital speech signal.
Claim 26
Dependent Claim
29 words
The method of claim 22 wherein the feature parameters of the speech signal includes the power of the speech signal in each of a predetermined ranges of speech signal.
Claim 27
Dependent Claim
40 words
The method of claim 24 wherein the step of analyzing includes the steps of filtering the speech signal with respect to each of the predetermined ranges to generate an filtered speech signal, and rectifying and smoothing the filtered speech signal.
Claim 28
Dependent Claim
211 words
A translation apparatus for translating a speech input in a first language into a sentence in a second language, comprising: speech recognition means for recognizing an input speech and outputting at least one of word constituting the speech; first sentence storage means for storing sentences in the first language; second sentence storage means for storing sentences in the second language; first search means for searching the sentences stored in said first sentence storage means to find one of the sentences similar to a combination including at least one word output from said speech recognition means; operation means operated when a predetermined input is given; second search means for searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said first search means after the predetermined input has been given through the operation of said operation means; and output means for outputting search results obtained by said first and second search means; wherein said output means first outputs the sentence in the first language obtained by said first search means and outputs the sentence in the second language obtained by said second search means when the sentence in the first language is confirmed.
Claim 29
Dependent Claim
211 words
A translation apparatus for translating a speech input in a first language into a sentence in a second language, comprising: speech recognition means for recognizing an input speech and outputting at least one of word constituting the speech; first sentence storage means for storing sentences in the first language; second sentence storage means for storing sentences in the second language; first search means for searching the sentences stored in said first sentence storage means to find one of the sentences similar to a combination including at least one word output from said speech recognition means; operation means operated when a predetermined input is given; second search means for searching the sentences stored in said second sentence storage means to find one of the sentences corresponding to a translation of the sentence in the first language found by said first search means after the predetermined input has been given through the operation of said operation means; and output means for outputting search results obtained by said first and second search means; wherein said output means first outputs the sentence in the first language obtained by said first search means and outputs the sentence in the second language obtained by said second search means when the sentence in the first language is confirmed.
Claim 30
Dependent Claim
74 words
The translation apparatus of claim 26, wherein the sentences stored in said first sentence storage means and the sentences stored in said second storage means correspond to each other in a one-to-one relationship, and further, wherein said first sentence storage means stores the sentences in the first language and addresses in said second sentence storage means with which the sentences in the second language corresponding to the sentences in the first language are stored.
Claim 31
Dependent Claim
35 words
The translation apparatus of claim 26, wherein said second search means starts the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is accurate.
Claim 32
Dependent Claim
36 words
The translation apparatus of claim 28, wherein said first search means again performs the searching operation if the predetermined input signifies that the sentence in the first language found by said first search means is inaccurate.
Claim 33
Dependent Claim
27 words
The translation apparatus of claim 26, wherein the input speech in the first language is a speech input in the form of a series of independent words.
Claim 34
Dependent Claim
80 words
The translation apparatus of claim 26 wherein said speech recognition means includes: an analog-to-digital converter for quantizing the input speech and for generating a corresponding digital speech signal; an acoustic analyzer for analyzing the acoustic form of the digital speech signal and for extracting feature parameters of the speech signal; a dictionary for storing standard word patterns; and a recognition processor for performing speech recognition on the basis of the feature parameters and in accordance with the standard word patterns.
Claim 35
Dependent Claim
41 words
The translation apparatus of claim 31 further including a clock configured to provide a clock signal, and further, wherein said analog-to-digital converter is configured to sample the input speech in accordance with the clock signal to generate the digital speech signal.
Claim 36
Dependent Claim
48 words
The translation apparatus of claim 31 wherein the acoustic analyzer is configured to filter the speech signal with respect to each of the predetermined ranges to generate an filtered speech signal, and further, wherein the acoustic analyzer is further configured to rectify and smooth the filtered speech signal.
Claim 37
Dependent Claim
21 words
The translation apparatus of claim 26 wherein said output means includes a voice synthesizer and a speaker, or a visual monitor.
References Cited (Backward Citations)
US5220503A
Cited
US4800522A
Cited
JPS62229473A
Cited
US5384701A
Cited
US5010486A
Cited
EP0327408A2
Cited
US4984177A
Cited
EP0449230A2
Cited
EP0472193A2
Cited
US5457768A
Cited
US5371674A
Cited
US5293584A
Cited
US5704013A
Cited
US5615301A
Cited
US5764853A
Cited
US5796921A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 2002-10-04 | 2003-04-05 | 2003-10-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 2006-10-04 | 2007-04-05 | 2007-10-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2010-10-04 | 2011-04-05 | 2011-10-05 | $7700.00 | Window Closed / Lapsed |