CN114925705A - Speech translation error correction method - Google Patents
Speech translation error correction method Download PDFInfo
- Publication number
- CN114925705A CN114925705A CN202210404042.6A CN202210404042A CN114925705A CN 114925705 A CN114925705 A CN 114925705A CN 202210404042 A CN202210404042 A CN 202210404042A CN 114925705 A CN114925705 A CN 114925705A
- Authority
- CN
- China
- Prior art keywords
- display area
- touch display
- user
- word
- dictation content
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/40—Processing or translation of natural language
- G06F40/42—Data-driven translation
- G06F40/47—Machine-assisted translation, e.g. using translation memory
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/048—Interaction techniques based on graphical user interfaces [GUI]
- G06F3/0484—Interaction techniques based on graphical user interfaces [GUI] for the control of specific functions or operations, e.g. selecting or manipulating an object, an image or a displayed text element, setting a parameter value or selecting a range
- G06F3/04842—Selection of displayed objects or displayed text elements
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
- G06F40/35—Discourse or dialogue representation
-
- G—PHYSICS
- G06—COMPUTING OR CALCULATING; COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F9/00—Arrangements for program control, e.g. control units
- G06F9/06—Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
- G06F9/44—Arrangements for executing specific programs
- G06F9/451—Execution arrangements for user interfaces
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Software Systems (AREA)
- Human Computer Interaction (AREA)
- Health & Medical Sciences (AREA)
- Artificial Intelligence (AREA)
- Audiology, Speech & Language Pathology (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Machine Translation (AREA)
Abstract
本发明公开了一种语音翻译错误修正方法，语音翻译错误修正方法，包括以下步骤：（1）在翻译设备的第一触控显示区域展示文字听写内容，在翻译设备的第二触控显示区域展示根据所述文字听写内容翻译识别的翻译内容；（2）根据用户选中文字听写内容中错误的字或词，在用户选择确定修正之后切换到第三触控显示区域；（3）在第三触控显示区域展示根据用户就错误的字或词重新进行造词或造句之后说话时的语音所识别出的二次听写内容；（4）根据用户选中二次听写内容中正确的字或词，在用户确定修正之后切换回到第一触控显示区域和第二触控显示区域，并同时将错误的字或词替换为正确的字或词。本发明能够方便的对语音翻译环节中出错的内容进行修正，准确率高。The invention discloses a voice translation error correction method, comprising the following steps: (1) displaying text dictation content in a first touch display area of a translation device, and displaying text dictation content in a second touch display area of the translation device Display the translated content translated and recognized according to the text dictation content; (2) According to the wrong word or word in the text dictation content selected by the user, switch to the third touch display area after the user selects and confirms the correction; (3) In the third touch display area The touch display area displays the secondary dictation content recognized by the user's speech after re-creating words or sentences for the wrong words or words; (4) According to the user's selection of the correct word or word in the secondary dictation content, After the user confirms the correction, it switches back to the first touch display area and the second touch display area, and at the same time replaces the wrong word or word with the correct word or word. The present invention can conveniently correct the content erroneous in the speech translation link, and has high accuracy.
Description
技术领域technical field
本发明涉及一种语音翻译错误修正方法。The present invention relates to a method for correcting errors in speech translation.
背景技术Background technique
随着语音识别以及翻译技术的发展，目前市面上具有很多移动式的翻译软件和设备，例如讯飞、百度或搜狗出品的翻译机，以及搭载运行在例如手机、平板等移动终端上的翻译软件等。这些翻译软件或设备上通常都具有语音翻译功能，能够将用户说话时的语音直接的转化为相应的文字，而后再将这些文字相应的转化翻译为其他语种的文字。实际使用时由于用户声音大小、使用时的环境噪音、用户口音不同、以及同音不同字等因素的影响，极容易导致语音听写的内容出错，进而导致翻译的内容也相应的出错。现有方式是需要用户通过选择这些错误的内容进行删除，然后通过虚拟键盘重新编辑输入，操作比较麻烦。With the development of speech recognition and translation technology, there are many mobile translation software and devices on the market, such as translation machines produced by iFLYTEK, Baidu or Sogou, as well as translation software running on mobile terminals such as mobile phones and tablets. Wait. These translation software or devices usually have a voice translation function, which can directly convert the voice of the user into corresponding text, and then convert the text into text in other languages accordingly. In actual use, due to factors such as the volume of the user's voice, ambient noise during use, different user accents, and different words with homophones, it is very easy to cause errors in the content of the voice dictation, which in turn leads to corresponding errors in the translated content. The existing method requires the user to delete the wrong contents by selecting them, and then re-edit the input through the virtual keyboard, which is troublesome to operate.
发明内容SUMMARY OF THE INVENTION
针对现有技术的不足，本发明提供了一种操作更为方便、能够提高翻译准确性的语音翻译错误修正方法。In view of the deficiencies of the prior art, the present invention provides a voice translation error correction method that is more convenient to operate and can improve translation accuracy.
为实现上述目的，本发明提供了一种语音翻译错误修正方法，包括以下步骤：To achieve the above object, the present invention provides a method for correcting errors in speech translation, comprising the following steps:
（1）在翻译设备的第一触控显示区域展示根据用户说话时的语音所识别出的文字听写内容，在翻译设备的第二触控显示区域展示根据所述文字听写内容翻译识别的翻译内容；(1) Display the text dictation content recognized according to the voice of the user in the first touch display area of the translation device, and display the translation content recognized according to the translation and recognition of the text dictation content in the second touch display area of the translation device ;
（2）根据用户在所述第一触控显示区域的选中文字听写内容中错误的字或词，弹出是否确定修正的第一提示窗口，在用户选择确定修正之后切换到第三触控显示区域；(2) According to the wrong word or word in the dictation content selected by the user in the first touch display area, a first prompt window will pop up whether to confirm the correction, and switch to the third touch display area after the user chooses to confirm the correction ;
（3）在第三触控显示区域展示根据用户就错误的字或词重新进行造词或造句之后说话时的语音所识别出的二次听写内容；(3) In the third touch display area, display the secondary dictation content recognized by the user's speech after re-creating words or sentences about the wrong word or word;
（4）根据用户在所述第三触控显示区域的选中二次听写内容中正确的字或词，弹出是否确定修正的第二提示窗口，在用户选择确定修正之后切换回到第一触控显示区域和第二触控显示区域，并同时将错误的字或词替换为正确的字或词；(4) According to the correct word or word in the second dictation content selected by the user in the third touch display area, a second prompt window pops up whether to confirm the correction, and switches back to the first touch after the user chooses to confirm the correction The display area and the second touch display area, and at the same time replace the wrong word or word with the correct word or word;
（5）重新的对第一触控显示区域的文字听写内容进行识别翻译并展示在第二触控显示区域。(5) Re-identify and translate the text dictation content in the first touch display area and display it in the second touch display area.
进一步地，所述步骤（2）中，用户在选中文字听写内容中错误的字或词之后通过长按若干秒弹出所述第一提示窗口。Further, in the step (2), after the user selects the wrong word or word in the text dictation content, the first prompt window pops up by pressing and holding for several seconds.
进一步地，所述步骤（3）中，用户在选中二次听写内容中正确的字或词之后通过长按若干秒弹出所述第二提示窗口。Further, in the step (3), after the user selects the correct word or word in the secondary dictation content, the second prompt window pops up by pressing and holding for several seconds.
进一步地，所述步骤（3）中，在第三触控显示区域设置有虚拟按钮，通过点击或长按该虚拟按钮监听用户说话时的声音，并将其识别转化为所述二次听写内容。Further, in the step (3), a virtual button is set in the third touch display area, and the voice of the user when the user speaks is monitored by clicking or long-pressing the virtual button, and its recognition is converted into the secondary dictation content. .
本发明的有益效果是：在翻译环节中，用户通过选择听写内容中错误识别的字或词，并就错误的字或词重新进行造词或造句之后进行语音听写，选中二次听写内容中的正确的字或词对原有听写内容中错误识别的字或词进行替换，能够方便的对其进行修正，不需要麻烦的对听写内容中错误的字或词进行重新编辑，能够克服语音识别率不高的缺陷，提高翻译的效率。The beneficial effects of the present invention are as follows: in the translation link, the user selects the wrongly recognized word or word in the dictation content, and re-creates a word or sentence for the wrong word or word, and then performs voice dictation, and selects the word or word in the second dictation content. The correct word or word replaces the wrongly recognized word or word in the original dictation content, which can be easily corrected without the trouble of re-editing the wrong word or word in the dictation content, which can overcome the speech recognition rate. Not high defects, improve the efficiency of translation.
具体实施方式Detailed ways
本发明一种语音翻译错误修正方法的实施例，包括以下步骤：An embodiment of a speech translation error correction method of the present invention includes the following steps:
（1）在翻译设备的第一触控显示区域展示根据用户说话时的语音所识别出的文字听写内容，在翻译设备的第二触控显示区域展示根据所述文字听写内容翻译识别的翻译内容；(1) Display the text dictation content recognized according to the voice of the user in the first touch display area of the translation device, and display the translation content recognized according to the translation and recognition of the text dictation content in the second touch display area of the translation device ;
翻译设备是指至少具有触控显示屏、麦克风的便携式智能设备，其可以是专业的翻译机，也可以是具有语音翻译功能的平板、手机等智能移动终端。A translation device refers to a portable smart device with at least a touch-screen display and a microphone, which can be a professional translator, or an intelligent mobile terminal such as a tablet or mobile phone with a voice translation function.
用户通过翻译设备自带的虚拟或实体语音输入按钮，能够进行语音输入，利用配置在云端或本地的语音识别库对输入的语音进行识别并转化为具有对应语言的文字听写内容，该文字听写内容展现在所述第一触控显示区域，供用户查看。同时，利用配置在云端或本地的语言翻译库能够将所述文字听写内容同步的为被识别转化为其他语种的翻译内容，展现在所述第二触控显示区域，方便用户进行对照。用户语音至文字听写内容的识别转换以及文字听写内容至翻译内容的识别转换均为现有翻译软件或设备上常见的技术，详细原理本发明中不再赘述。The user can perform voice input through the virtual or physical voice input button that comes with the translation device, and use the voice recognition library configured in the cloud or local to recognize the input voice and convert it into text dictation content in the corresponding language. The text dictation content It is displayed in the first touch display area for the user to view. At the same time, using the language translation library configured in the cloud or locally, the text dictation content can be synchronized with the translation content that has been recognized and converted into other languages, and displayed in the second touch display area, which is convenient for users to compare. The recognition and conversion of user voice to text dictation content and the recognition and conversion of text dictation content to translation content are common technologies in existing translation software or devices, and detailed principles are not repeated in the present invention.
（2）根据用户在所述第一触控显示区域的选中文字听写内容中错误的字或词，弹出是否确定修正的第一提示窗口，在用户选择确定修正之后切换到第三触控显示区域；(2) According to the wrong word or word in the dictation content selected by the user in the first touch display area, a first prompt window will pop up whether to confirm the correction, and switch to the third touch display area after the user chooses to confirm the correction ;
用户可直观的从第一触控显示区域中展现的文字听写内容中找出语音识别错误的字或词，通过翻译设备的触控屏能够对文字听写内容中错误的字或词进行选择。在对字或词进行触控选择的方式中，可由用户自主触摸滑动并框选这些字或词，也可以由翻译设备根据用户点触的字符自动的联想并框选与之相关联的整个词语。例如在第一触控显示区域中显示的文字听写内容是“今天天气晴朗”，当用户选择晴时，可以自动的通过联想框选“晴朗”一词。The user can intuitively find words or words with incorrect speech recognition from the text dictation content displayed in the first touch display area, and can select the wrong words or words in the text dictation content through the touch screen of the translation device. In the way of selecting words or words by touch, the user can touch and slide and select these words or words independently, or the translation device can automatically associate and select the whole word associated with it according to the characters touched by the user. . For example, the text dictation content displayed in the first touch display area is "it's sunny today", when the user selects sunny, the word "sunny" can be automatically selected through the association box.
在选择错误的字或词之后，直接弹出或通过长按若干秒弹出是否确定修正的第一提示窗口，用户选择确定修正之后切换到第三触控显示区域。第一提示窗口的设置能够防止用户误操作，用户也可选择取消修正返回第一触控显示区域和第二触控显示区域的界面。After selecting the wrong word or word, the first prompt window for confirming the correction will pop up directly or by long-pressing for several seconds, and the user switches to the third touch display area after choosing to confirm the correction. The setting of the first prompt window can prevent the user from misoperation, and the user can also choose to cancel the correction and return to the interface of the first touch display area and the second touch display area.
第三触控显示区域可以是弹出的新的窗口，有可以是将第一触控显示区域和第二触控显示区域的界面整体跳转切换为一个新的界面。The third touch display area may be a pop-up new window, or may be a whole jump switching of the interfaces of the first touch display area and the second touch display area to a new interface.
（3）在第三触控显示区域展示根据用户就错误的字或词重新进行造词或造句之后说话时的语音所识别出的二次听写内容；(3) In the third touch display area, display the secondary dictation content recognized by the user's speech after re-creating words or sentences about the wrong word or word;
例如当用户初始输入的语音“今天天气晴朗”，因为用户口音或环境噪音等影响被错误的识别为“今天天津晴朗”，那么通过在第一触控显示区域选择“天津”一词之后，可在第三触控显示区域处就被识别错误的词“天气”重新进行造词或造句。例如，用户可通过语音输入“天气很好”，二次听写内容“天气很好”则会展示在第三触控显示区域。由于现有语音识别技术多采用联想的方式，在重新造词或造句之后的二次语音输入过程中容易识别出正确的内容。For example, when the user's initial input voice "the weather is sunny today" is incorrectly identified as "it is sunny today in Tianjin" due to the user's accent or environmental noise, then by selecting the word "Tianjin" in the first touch display area, you can At the third touch display area, the word "weather" that has been identified incorrectly is re-formed or sentenced. For example, the user can input "the weather is fine" by voice, and the secondary dictation content "the weather is fine" will be displayed in the third touch display area. Since the existing speech recognition technology mostly adopts the method of association, it is easy to identify the correct content during the secondary speech input process after re-creating words or sentences.
（4）根据用户在所述第三触控显示区域的选中二次听写内容中正确的字或词，弹出是否确定修正的第二提示窗口，在用户选择确定修正之后切换回到第一触控显示区域和第二触控显示区域，并同时将错误的字或词替换为正确的字或词。(4) According to the correct word or word in the second dictation content selected by the user in the third touch display area, a second prompt window pops up whether to confirm the correction, and switches back to the first touch after the user chooses to confirm the correction Display area and second touch display area, and replace the wrong word or word with the correct word or word at the same time.
例如，用户在第三触控显示区域展示的二次听写内容“天气很好”中，选择识别正确的词语“天气”，选择的方式同上，用户可以自主触摸框选，也可以智能的联想。在选择之后，直接弹出或通过长按若干秒弹出是否确定修正的第二提示窗口，用户选择确定修正之后切换回到初始界面。第二提示窗口的设置也能够防止用户误操作，用户也可选择取消修正以便于在第三触控显示区域重新进行选择或者重新识别输入语音。在回到第一触控显示区域和第二触控显示区域界面的同时将第一触控显示区域中错误的字或词替换为正确的字或词，即将所述的“天津”替换为“天气”。For example, in the secondary dictation content "weather is good" displayed in the third touch display area, the user selects and recognizes the correct word "weather". The selection method is the same as above. The user can independently touch the frame to select, or can make an intelligent association. After the selection, a second prompt window pops up directly or by pressing and holding for a few seconds whether to confirm the correction. After the user selects to confirm the correction, the user switches back to the initial interface. The setting of the second prompt window can also prevent the user from misoperation, and the user can also choose to cancel the correction so as to re-select or re-recognize the input voice in the third touch display area. When returning to the interface of the first touch display area and the second touch display area, replace the wrong word or word in the first touch display area with the correct word or word, that is, replace the "Tianjin" with " weather".
当二次语音识别内容仍然不是“天气”时，用于可通过虚拟的重置按钮重新进行造词或造句进行语音输入，多次重试直到语音识别出正确内容为止。When the content of the secondary speech recognition is still not "weather", the virtual reset button can be used to re-create words or sentences for speech input, and retry several times until the speech recognizes the correct content.
（5）重新的对第一触控显示区域的文字听写内容进行识别翻译并展示在第二触控显示区域。(5) Re-identify and translate the text dictation content in the first touch display area and display it in the second touch display area.
在重新修正好第一触控显示区域的文字听写内容之后，重新的对其进行识别翻译并展示在第二触控显示区域，即此时展现的内容就是翻译好的“What a nice day today”。After re-correcting the text dictation content in the first touch display area, re-identify and translate it and display it in the second touch display area, that is, the content displayed at this time is the translated "What a nice day today" .
本发明在翻译出错时可快速、方便的进行修正，采用语音方式修正错误的内容，不需要手部通过操作虚拟键盘进行更正，更加高效。通过更正语音识别的内容，可以提高最终翻译的其他语种的内容的准确性。The present invention can quickly and conveniently correct translation errors, correct the wrong content by voice, and does not require hands to correct by operating the virtual keyboard, and is more efficient. By correcting the content of the speech recognition, the accuracy of the final translation of the content in other languages can be improved.
以上实施例，只是本发明优选地具体实施例的一种，本领域技术人员在本发明技术方案范围内进行的通常变化和替换都包含在本发明的保护范围内。The above embodiment is only one of the preferred specific embodiments of the present invention, and the usual changes and substitutions made by those skilled in the art within the scope of the technical solution of the present invention are included in the protection scope of the present invention.
Claims (4)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210404042.6A CN114925705A (en) | 2022-04-18 | 2022-04-18 | Speech translation error correction method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202210404042.6A CN114925705A (en) | 2022-04-18 | 2022-04-18 | Speech translation error correction method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN114925705A true CN114925705A (en) | 2022-08-19 |
Family
ID=82806196
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202210404042.6A Pending CN114925705A (en) | 2022-04-18 | 2022-04-18 | Speech translation error correction method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN114925705A (en) |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1183606A (en) * | 1996-10-31 | 1998-06-03 | 微软公司 | Method and system for selecting alternative words during speech recognition |
| CN102170553A (en) * | 2010-02-26 | 2011-08-31 | 夏普株式会社 | Conference system, information processor, conference supporting method and information processing method |
| KR20140025619A (en) * | 2012-08-08 | 2014-03-05 | (주)아이티씨교육 | Method for providing learning foreign language service based on interpretation test and writing test using speech recognition and speech to text technology |
| CN112684913A (en) * | 2020-12-30 | 2021-04-20 | 维沃移动通信有限公司 | Information correction method and device and electronic equipment |
-
2022
- 2022-04-18 CN CN202210404042.6A patent/CN114925705A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1183606A (en) * | 1996-10-31 | 1998-06-03 | 微软公司 | Method and system for selecting alternative words during speech recognition |
| CN102170553A (en) * | 2010-02-26 | 2011-08-31 | 夏普株式会社 | Conference system, information processor, conference supporting method and information processing method |
| KR20140025619A (en) * | 2012-08-08 | 2014-03-05 | (주)아이티씨교육 | Method for providing learning foreign language service based on interpretation test and writing test using speech recognition and speech to text technology |
| CN112684913A (en) * | 2020-12-30 | 2021-04-20 | 维沃移动通信有限公司 | Information correction method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| JP5064404B2 (en) | Combination of voice and alternative input methods on mobile devices | |
| US6401065B1 (en) | Intelligent keyboard interface with use of human language processing | |
| US8275603B2 (en) | Apparatus performing translation process from inputted speech | |
| CN106251869B (en) | Voice processing method and device | |
| TWI296793B (en) | Speech recognition assisted autocompletion of composite characters | |
| KR101586890B1 (en) | Input processing method and apparatus | |
| US20160328205A1 (en) | Method and Apparatus for Voice Operation of Mobile Applications Having Unnamed View Elements | |
| US20090326938A1 (en) | Multiword text correction | |
| US8213995B2 (en) | Input processing method of mobile terminal and device for performing the same | |
| CN103869931B (en) | Method and device for controlling user interface through voice | |
| JP2002116796A (en) | Voice processor and method for voice processing and storage medium | |
| JP2015525933A (en) | Terminal voice auxiliary editing method and apparatus | |
| US20100198578A1 (en) | Translation apparatus, method, and computer program product | |
| US20150193410A1 (en) | System for editing a text of a portable terminal and method thereof | |
| KR20080083290A (en) | Method and apparatus for accessing digital files in a collection of digital files | |
| CN111326158A (en) | Voice control method based on intelligent terminal | |
| CN113743102A (en) | Method and device for recognizing characters and electronic equipment | |
| CN102999639B (en) | A kind of lookup method based on speech recognition character index and system | |
| CN109036409A (en) | A kind of method and device thereof of intelligent sound control operating software | |
| CN102467908A (en) | Multi-language voice control system and method thereof | |
| KR20160080711A (en) | Apparatus, Method and System for Translation based on Communication | |
| CN114925705A (en) | Speech translation error correction method | |
| CN108920470A (en) | A kind of language of automatic detection audio and the method translated | |
| CN107766826B (en) | Method for searching word paraphrase and electronic equipment | |
| JP3411198B2 (en) | Interpreting apparatus and method, and medium storing interpreting apparatus control program |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination |