Data processing: speech signal processing – linguistics – language – Speech signal processing – Synthesis
Reexamination Certificate
1998-08-17
2002-12-03
{haeck over (S)}mits, T{overscore (a)}livaldis Ivars (Department: 2654)
Data processing: speech signal processing, linguistics, language
Speech signal processing
Synthesis
C704S235000, C382S187000
Reexamination Certificate
active
06490563
ABSTRACT:
BACKGROUND OF THE INVENTION
The present invention relates to data processing systems. More particularly, the present invention relates to proofreading text in a text editing system.
A text editing system or module, for example, a word processing application, is well known and allows easy manipulation of stored text. Many text editing modules also provide some level of proofreading. In many word processing applications, proofreading consists of a spelling checker for identifying spelling errors. In more advanced word processing applications, proofreading includes detecting grammatical and punctuation errors as well.
When performing spell checking, the word processing application scans the text stored in memory on the computer system and identifies spelling errors. To identify the errors, the word processing application compares each word of the text with a spelling dictionary. Spelling errors are detected when a word contained in the text does not exist in the spelling dictionary. After detection of each error, or after detection of all errors in the text, the individual errors are displayed to the user using a visual display device such as a cathode ray tube (CRT) or a liquid crystal display (LCD). The individual errors are visually identified to the user by highlighting or underlining the error in the surrounding text, and/or providing a suitable user interface that allows the user to see the error and select a suitable correction.
Although the word processing application is well suited for detecting textual errors such as spelling and grammar, current systems require the user to interact with the proofreading functions using the visual display device. This requires the user to remain in front of the visual display during the proofreading process.
Another text editing module in common use foremost Asian languages is a converter system that converts phonetic symbols to a selected language. Such a text editing module is often referred as IME (Input Method Editor) in “WINDOWS-95” or “WINDOWS NT” operating systems sold by Microsoft Corporation of Redmond, Wash. The phonetic symbols can be provided to a computer using a standard keyboard. The computer includes a converter module that converts the phonetic symbols to the selected language. For example, it is common to form Japanese text in a computer system by entering phonetic characters from an English or Latin keyboard. Inputting Japanese phonetic characters using the letters of the Latin alphabet is called “Romaji”. The computer system compares each of the Romaji characters with a stored dictionary and produces a “Kana” sequence (“Kanas”). Kanas are Japanese syllabic symbols which represent the sound of Japanese. The IME converter then converts the Kana form into “Kanji” form, which is a formal Japanese writing language, through sophisticated linguistic analysis. (The formal Japanese writing system actually consists of a mixture of Kanjis and Kanas, where the Kanjis represent most of the content information and bear no direct information about pronunciation.)
However, in a conventional text processing system used in a Japanese word processor, the appropriate Kanji equivalent for the Kana sequence often must be selected using a so-called candidate display-and-choice method. Specifically, a number of Kanji candidates are displayed for a sequence of Kana so that the user can choose the appropriate one. This display-and-choice method is necessary since the Japanese language includes a number of homonyms and no explicit word boundaries, which cause inevitable Kana to Kanji conversion errors. By displaying the Kanji candidates, the user can view the possible candidates and select the appropriate Kanji representation. As can be appreciated by those skilled in the art, detection of the incorrect Kanji representation is cumbersome and time-consuming. Since the user must constantly switch attention from the text that is being inputted to the Kanji candidates displayed on the screen, user fatigue is a problem and high typewriting speed cannot be achieved.
Similarly, the text editing module used in a Chinese word processor also requires IME conversions which converts either from phonetic symbols (Pinyin) or stroke symbols (Wu-Bi) to the written Hanzi representations. Pinyin IME is the most popular phonetic Chinese IME and operates similar to the Japanese Kana IME discussed above. Users type phonetic spelling of Chinese Hanzi characters and the IME will convert the phonetic Pinyin string to the corresponding Hanzi string through the use of Pinyin dictionary and language models. Wu-Bi IME is the most popular stroke-based Chinese IME which converts the input stroke sequence into the correspondent Hanzi sequence according to a special Chinese stroke dictionary. In addition to the user fatigue problem mentioned above, it is in general very difficult to spot errors because neither explicit word boundaries nor semantic separators (like Kana) are present in Chinese. Particularly, the lack of tone marks in Pinyin IME causes far more homonyms to occur than with Japanese Kana IME. Often the list of homonyms for some pinyin sequences can be too long to fit on the entire screen of the visual display.
Accordingly, there is an ongoing need to more effectively and efficiently proofread text in many types of data processing systems employing text editing modules.
SUMMARY OF THE INVENTION
In general an embodiment of the present invention is to use audio feedback to help users detect errors (typing, spelling, grammar, speech recognition, or IME conversion) when executing a text editing system. This type of audio feedback will not only enable a user to perform eyes-free (therefore less intrusive) proofreading, but also allow the user to detect errors much more effectively when compared with other proofreading tools, particularly for Asian languages.
Another aspect of the present invention is a computer implemented system and method of proofreading text in a computer system that includes receiving text from a user into a text editing module. At least a portion of the text is converted to an audio signal. The audio signal is played through a speaker to the user to provide feedback, so the user can detect errors (e.g. typing, spelling, grammar, speech recognition and IME conversion) without looking at the screen.
Another aspect of the present invention is a dictation system operable on a computer for processing text. The computer includes a microphone and a speaker. The dictation system includes a speech recognition module receiving an input signal from the microphone and converting the input signal to text, and a text-to-speech module receiving the text and converting the selected text to an output signal providable to the speaker. Through the audio feedback, the users can detect recognition errors without looking at the screen.
Another aspect of the present invention is a proofreading system operable on a computer for inputting text via IME's. The computer includes an input device and a speaker. The proofreading system includes a text converter adapted to receive phonetic (or stroke) symbols from the input device and to convert the phonetic symbols to text. A text-to-speech module receives the text and converts the text to an output signal providable to the speaker, so users can easily detect conversion errors.
REFERENCES:
patent: 4531119 (1985-07-01), Nakayama et al.
patent: 4707858 (1987-11-01), Fette
patent: 4717911 (1988-01-01), Matsuura et al.
patent: 4777600 (1988-10-01), Saito et al.
patent: 4783807 (1988-11-01), Marley
patent: 4914704 (1990-04-01), Cole et al.
patent: 4975957 (1990-12-01), Ichikawa et al.
patent: 5278943 (1994-01-01), Gasper et al.
patent: 5282267 (1994-01-01), Woo, Jr. et al.
patent: 5384893 (1995-01-01), Hutchins
patent: 5576955 (1996-11-01), Newbold et al.
patent: 5649060 (1997-07-01), Ellozy et al.
patent: 5652828 (1997-07-01), Silverman
patent: 5729629 (1998-03-01), Dai
patent: 0 200 389 (1986-11-01), None
Protalk “Protalk for Windows” Biolink, 1993.*
“Word-Processing Station With Audio Text Synthesis”, IBM Technical Discl
Hon Hsiao-Wuen
Huang Xuedong
Ju Yun-Chen
Li Dong
Zhang Xianghui Sean
Koehler S.
Microsoft Corporation
Westman Champlin & Kelly P.A.
{haeck over (S)}mits T{overscore (a)}livaldis Ivars
LandOfFree
Proofreading with text to speech feedback does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Proofreading with text to speech feedback, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Proofreading with text to speech feedback will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-2966677