CN101008942A - Machine translation device and method thereof - Google Patents

Machine translation device and method thereof Download PDF

Info

Publication number
CN101008942A
CN101008942A CN 200610002940 CN200610002940A CN101008942A CN 101008942 A CN101008942 A CN 101008942A CN 200610002940 CN200610002940 CN 200610002940 CN 200610002940 A CN200610002940 A CN 200610002940A CN 101008942 A CN101008942 A CN 101008942A
Authority
CN
China
Prior art keywords
language
text information
information
text
converted
Prior art date
Application number
CN 200610002940
Other languages
Chinese (zh)
Inventor
王亚军
李大冀
Original Assignee
北京金远见电脑技术有限公司
Priority date (The priority date 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 date listed.)
Filing date
Publication date
Application filed by 北京金远见电脑技术有限公司 filed Critical 北京金远见电脑技术有限公司
Priority to CN 200610002940 priority Critical patent/CN101008942A/en
Publication of CN101008942A publication Critical patent/CN101008942A/en

Links

Abstract

This invention discloses one machine translation device, which comprises the following parts: sound information input unit to input first sound information; sound identification unit to identify first sound information and to convert it into text information; translation unit to translate text information into second one. This invention translation method comprises the following steps: sound information input unit to input first sound information; sound identification unit to identify first sound information and to convert it into text information; translation unit to translate text information into second one.

Description

机器翻译装置和机器翻译方法 Machine translation apparatus and machine translation method

技术领域 FIELD

本发明涉及一种机器翻译装置和机器翻译方法。 The present invention relates to a machine translation apparatus and machine translation method.

背景技术 Background technique

一直以来,人们在与说外语的人进行会话交流时,希望能够有一种便携装置,能够随时将听到的外语翻译成自己的母语,又能够将自己的话翻译成外语说给对方听。 All along, people in the conversation with people speaking a foreign language, and hope to have a portable device that can at any time to hear the translation of foreign language into their mother tongue, but also can be translated into a foreign language in their own words to say to each other to listen.

在相关技术中,当前有三种技术:一是语音识别技术,利用该技术,计算机能够识别输入的语音,将语音转换成便于处理的文本;二是文本转换成语音技术,即文本语音转换TTS(Text To Speech)技术,利用该技术,计算机能够将翻译后的文本转换成人们能够听懂的语音进行输出;三是机器翻译技术,即利用计算装置将一种语言翻译成另外一种语言。 In the related art, there are currently three techniques: First, speech recognition, using this technique, the computer can recognize voice input, converting the voice to text to facilitate processing; second text into voice technology, i.e. the TTS Text to Speech ( text to speech) technique, using this technique, the computer can be converted into a translated text that people can understand speech output; third machine translation technique, i.e. using a computing device to translate one language into another language.

1.语音识别技术计算机语音识别过程与人对语音识别处理过程基本上是一致的。 1. The speech recognition technology and computer speech recognition process of human speech recognition process is basically the same. 目前主流的语音识别技术是基于统计模式识别的基本理论。 Mainstream speech recognition technology is based on the basic theory of statistical pattern recognition. 一个典型语音识别系统100的实现过程如图1所示,可大致分为三部分:(1)语音特征提取单元110:其目的是从语音波形中提取出随时间变化的语音特征序列。 A typical speech recognition system 100 of the process shown in Figure 1, can be roughly divided into three parts: (1) speech feature extraction unit 110: an object thereof is to extract the speech features from the sequence of time-varying speech waveform. (2)声学模型(模型库120)与模式匹配130(识别算法):声学模型通常将获取的语音特征通过学习算法产生。 (2) acoustic model (library model 120) 130 matches the pattern (recognition algorithm): a speech characteristic acoustic model is typically acquired through the learning algorithm generated. 在识别时将输入的语音特征同声学模型(模式)进行匹配与比较,得到最佳的识别结果。 Wherein when the speech recognition model learning simultaneous input (pattern) matching and comparison, the best recognition result. (3)语言模型与语言处理:语言模型包括由识别语音命令构成的语法网络或由统计方法构成的语言模型,语言处理可以进行语法、语义分析。 (3) language model and language processing: language model comprises grammar network including language models recognizing a voice command or constituted by statistical methods, language processing may be performed syntax, semantic analysis. 对小词表语音识别系统,往往不需要语言处理部分。 Small vocabulary speech recognition systems often do not require language processing section.

声学模型是识别系统的底层模型,并且是语音识别系统中最关键的一部分。 The acoustic model is a model of the underlying recognition system, and is the most critical part of the speech recognition system. 声学模型的目的是提供一种有效的方法计算语音的特征矢量序列和每个发音模板之间的距离。 Acoustic model object is to provide an efficient method for calculating a speech feature vector sequence and the distance between each speaker template. 声学模型的设计和语言发音特点密切相关。 Acoustic model is closely related to the design and features of language pronunciation. 声学模型单元大小(字发音模型、半音节模型或音素模型)对语音训练数据量大小、系统识别率,以及灵活性有较大的影响。 The acoustic model unit size (word pronunciation model, semi-syllable or phoneme models model) the amount of speech training data size, recognition rate, and flexibility have a greater impact. 必须根据不同语言的特点、识别系统词汇量的大小决定识别单元的大小。 Must be based on the characteristics of different languages, the size of the vocabulary of the recognition system determines the size of the identification unit.

关于语音识别应用系统的研究开发,已有一些实用的语音识别系统投入商业运营。 Research and development on speech recognition application system, there are some practical speech recognition system put into commercial operation. 在市场上已经出现了一些语音识别的软件,帮助人们利用语音识别技术实现文本录入,以及简单的计算机操作等。 On the market there have been some speech recognition software to help people use speech recognition technology to achieve text entry, and a simple computer operations. 例如,在某些移动电话里,人们实现了语音拨号功能;某些软件可以帮助人们使用PC机时,用对PC机上所连接的话筒说话的方式来录入文本。 For example, in some mobile phones, people realized the voice dialing function; some software can help people when using a PC, a PC with a microphone connected way of talking to input text.

2.TTS技术TTS技术,又称文本语音转换技术,它将计算机自己产生的、或外部输入的文字信息转变为可以听得懂的、流利的汉语口语输出的技术,隶属于语音合成。 2.TTS technology TTS technology, also known as text-to-speech technology that will own computer generated, or text information externally input into can understand the technical fluent Chinese spoken language output, part of speech synthesis. 语音合成为通过机械的、电子的方法产生人造语音的技术。 Speech synthesis to produce synthetic speech techniques, electronic mechanically. 下面以图2为例,说明TTS技术的原理。 2 as an example below, explain the principles of the TTS technology. 语言学处理(S210),在文语转换系统中起着重要的作用,主要模拟人对自然语言的理解过程——文本规整、词的切分、语法分析和语义分析,使计算机对输入的文本能完全理解,并给出后两部分所需要的各种发音提示。 Linguistic processing (S210), plays an important role in text to speech system, the main analog people understand the process of natural language - structured text, word segmentation, parsing and semantic analysis, text on the computer input I can fully understand, and given the variety of pronunciation two parts needed for tips. 韵律处理(S220),为合成语音规划出音段特征,如音高、音长和音强等,使合成语音能正确表达语意,听起来更加自然。 Rhythm processing (S220), as synthesized speech planning a segmental features, such as pitch, duration or amplitude, so that the synthesized speech can express semantic correctly, it sounds more natural. 声学处理(S230),根据前两部分处理结果的要求输出语音,即合成语音。 Acoustic processing (S230), the required output voice according to the first two parts of the processing result, i.e., synthesized speech.

当前市场上已经出现了很多TTS的软件,并且已经有了各种语言的TTS软件,通过这些软件可以将汉语、英语、日语等各种语言的文本转换成该语言的语音进行输出。 Already on the market is currently a lot of TTS software, and have a variety of languages ​​TTS software, the software can convert text in Chinese, English, Japanese, and other languages ​​of the language into speech output. 例如我们在各种热线电话、游戏软件、仪器仪表等的应用里都可以听到利用TTS技术输出的语音提示。 For example, we can hear the output using the TTS technology of voice prompts in a variety of applications hotline, game software, instruments and other's.

3.机器翻译技术当前已经出现了大量的机器翻译软件,可以安装在PC机、PDA等各种装置上,进行各种语别的翻译。 3. The current machine translation technology have been a lot of machine translation software can be installed on a variety of devices a PC, PDA, etc., and various other language translation. 例如金远见公司的文曲星TMV5100,可以实现英语日常用语的翻译。 For example, the vision of the company's Wenquxing TMV5100, can achieve everyday language translation. 该装置可以对日常用语进行英汉、汉英双向整句翻译。 The device can be everyday language between English and Chinese, Chinese-English bi-sentence translation. 在进行英语交流时,向文曲星TMV5100输入中文或者英文,就可以得到翻译结果。 During communicate in English, TMV5100 Wenquxing to input Chinese or English, you can get the translation. 日常用语翻译是涉及计算语言学、人工智能、自然语言处理等多种学科和技术的交叉学科。 Everyday language translation is involved in computational linguistics, artificial intelligence, natural language processing technology and other disciplines and interdisciplinary. 日常用语翻译主要包括日常用语解析和翻译。 Everyday language translation including everyday language parsing and translation. 日常用语解析主要分析日常用语句型、自动切分长句和改写语句。 Everyday language parsing analyzes the everyday language sentences, long sentences and automatic segmentation rewrite the statement. 日常用语翻译针对语义分析得出的结果,利用预先建立的数据库,确定可懂的,日常用语化的第二语言。 Everyday language translation for semantic analysis of the results obtained, the use of pre-built database to determine the intelligibility of everyday language of the second language. 目前开发的计算机自动日常用语翻译系统已经有了很多,其中作为嵌入式系统设备的文曲星TMV5100上引入了日常用语翻译。 Many already have the computer automatically everyday language translation system currently in development, which as Wenquxing TMV5100 devices in embedded systems introduced everyday language translation.

然而,人们在实际的翻译应用中,希望出现一种机器翻译装置,能够随身携带,能够听懂人们说的话,并且将听到的话翻译出来后能够开口说出来。 However, people in the actual translation applications it is desirable a machine translation device appears, can carry, can understand what people say, and hear the words come out post-translational able to speak out.

在现有的机器翻译装置中,利用了相关技术中的机器翻译技术,能够将一种语言的文本翻译成另一种语言的文本,或者是结合了相关技术中的TTS技术,能够将翻译结果说出来;但是这些机器翻译装置存在以下的问题,即,这些机器翻译装置不能够听人们说的话,更不能听懂人们说的话,然后将听到的话翻译出来后能够开口说出来。 In a conventional machine translation apparatus, using a machine translation technology in the related art, the text can be translated into text in one language to another language, or a combination of a TTS technology of the related art, the translation can be They say it; but these machine translation means there is a problem, that is, the machine translation apparatus can not listen to what people say, but can not understand what people say, and then be able to speak out after hearing the words translated.

另外,上述的相关技术都存在一个问题,即,由于语言的大词汇量和灵活多变的语法所带来的语义分析的问题。 In addition, the above-mentioned technologies have a problem, namely, the problem of semantic analysis of large vocabulary language grammar and flexible brought about due. 而这个问题在机器翻译整句的话当中显得尤为突出。 And this problem in machine translation sentence the words which is particularly prominent.

发明内容 SUMMARY

因此,本发明涉及一种机器翻译装置以及机器翻译方法,其能够很好地解决由于相关技术的限制和不足而导致的一个或多个问题。 Accordingly, the present invention relates to a machine translation apparatus and machine translation method, which can solve one or more problems due to limitations and disadvantages of the related art caused.

本发明的一个优点在于提供了一种机器翻译装置以及机器翻译方法,具体而言,涉及一种用于翻译通过语音输入的语言,然后将翻译结果用语音输出的机器翻译装置。 One advantage of the present invention is to provide a machine translation apparatus and machine translation method, particularly, to a language for translation by speech input, and then outputs the result with the speech translation machine translation apparatus.

本发明的另一个优点在于根据本发明的机器翻译装置可以通过嵌入式系统设备来实现,所以便于携带并且成本很低。 Another advantage of the invention is that the embedded system may be achieved by the machine translation apparatus according to the present invention, the portable and low cost.

本发明的其它特征和优点将在随后的说明书中阐述,并且,部分地从说明书中变得显而易见,或者通过实施本发明而了解。 Other features and advantages of the invention will be set forth in the description which follows, and in part will be obvious from the description, or learned by practice of the present invention. 本发明的目的和其他优点可通过在所写的说明书、权利要求书、以及附图中所特别指出的结构来实现和获得。 The objectives and other advantages of the invention may be realized and attained by the written description, claims, and drawings structure particularly pointed out.

为了实现根据本发明的这些目的和其它优点,如文中所具体和概括描述的,提供了一种机器翻译装置,其特征在于,包括:语音信息输入单元,用于输入第一语言的语音信息;语音识别单元,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译单元,用于将所转换的文本信息翻译成第二语言的文本信息。 To achieve these objects and other advantages of the present invention, as described as embodied and broadly described, there is provided a machine translation apparatus comprising: a voice information input unit for inputting speech information of the first language; voice recognition unit, a speech information identifying a first language input, and converts it to text information; and a translation unit for translating the text information converted into the second language text information.

根据本发明的机器翻译装置,还可包括:文本语音转换单元,用于将所翻译的第二语言的文本信息转换成语音信息;以及语音信息输出单元,用于将所转换的语音信息输出。 The machine translation apparatus according to the present invention, further comprising: a text to speech conversion means for converting the translated text message into voice information of the second language; and a voice information output means for outputting the converted voice information.

根据本发明的机器翻译装置,还可包括:判断单元,用于判断所转换的文本信息是单词还是句子;以及词典单元,用于翻译单词;其中,当所述判断单元判断所转换的文本是单词时,通过所述词典单元将所述单词翻译成第二语言的文本信息;以及当所述判断单元判断所转换的文本是句子时,通过所述翻译单元将所述句子翻译成第二语言的文本信息。 The machine translation apparatus according to the present invention, further comprising: determining means for determining the converted text information is a word or a sentence; and dictionary means for translating a word; wherein, when said determination means determines whether the text is converted when a word, the dictionary means by the word translated into the second language text information; and when the determination unit determines whether the converted text is a sentence, the translation unit by the translated sentence into the second language the text information.

根据本发明的机器翻译装置,还可包括:文本信息输出单元,用于输出所转换的文本信息和所翻译的第二语言的文本信息;以及文本信息输入单元,用于输入第一语言的文本信息和修改所转换的第二语言的文本信息。 The machine translation apparatus according to the present invention, further comprising: text information output means for outputting the converted text information to text information and the translated second language; the text, and the text information input means for inputting a first language, text information and modify the converted second language.

根据本发明的机器翻译装置,可用计算机来实现。 The machine translation apparatus according to the invention, can be used to implement the computer.

根据本发明的机器翻译装置,可用嵌入式系统设备来实现。 The machine translation apparatus according to the invention, the device can be used to implement an embedded system.

所述预定语言可限定为一种现有语言中的日常用语,或者一种现有语言中的行业用语。 The language may be defined as a predetermined current language everyday language, or an industry term conventional language.

根据本发明另一方面,提供了一种机器翻译方法,其特征在于包括以下步骤:语音信息输入步骤,用于输入第一语言的语音信息;语音识别步骤,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译步骤,用于将所转换的文本翻译成第二语言的文本信息。 According to another aspect of the present invention, there is provided a method of machine translation, comprising the steps of: voice information inputting step of inputting speech information of the first language; speech recognition step of identifying a first language input the voice information, and convert it to text information; and a translation step for translating the translated text to a second language text information.

根据本发明的机器翻译方法,还可包括以下步骤:文本语音转换步骤,用于将所翻译的第二语言的文本信息转换成语音信息;以及语音信息输出步骤,用于将所转换的语音信息输出。 The machine translation method of the present invention, further comprising the steps of: text to speech conversion step for converting the translated text message into speech information of the second language; and voice information output step, for converting the voice information output.

根据本发明的机器翻译方法,还可包括以下步骤:判断步骤,用于判断所转换的文本信息是单词还是句子;以及单词翻译步骤,用于翻译单词,其中当判断所转换的文本信息是单词时,通过所述单词翻译步骤将所述单词翻译成第二语言的文本信息;以及当判断所转换的文本信息是句子时,通过所述翻译步骤将所述句子翻译成第二语言的文本信息。 The machine translation method of the present invention, further comprising the steps of: determining step for determining whether the converted text information is a word or a sentence; and word translation step for translating a word, wherein when determining the converted text information is the word when, by said step of translating the word translated into the second language word text information; and when determining the converted text information is a sentence, by the step of translating the sentence into the translated second language text information .

根据本发明的机器翻译方法,还可包括以下步骤:文本信息输出步骤,用于输出所转换的文本信息和所翻译的第二语言的文本信息;以及文本信息输入步骤,用于输入第一语言的文本信息和修改所转换的文本信息。 The machine translation method of the present invention, further comprising the steps of: text information output step of outputting text information for the converted text information and the translated second language; and a text information input step for inputting a first language text messages and edit the converted text information.

所述预定语言可限定为一种现有语言中的日常用语,或者一种现有语言中的行业用语。 The language may be defined as a predetermined current language everyday language, or an industry term conventional language.

通过下面对本发明的具体实施例的说明,并结合附图,本发明其他方面和特征对本技术领域的人员来说将变得明显。 The following Examples illustrate specific embodiments of the present invention, in conjunction with the accompanying drawings, the present invention Other aspects and features of the person skilled in the art will become apparent.

附图说明 BRIEF DESCRIPTION

下面将结合附图,对本发明的实施例进行说明,应该理解,这些实施例是用于说明本发明,而不是对本发明进行限定,其中:图1是示出语音识别的实现的示意图; Below with the accompanying drawings, embodiments of the present invention will be described, it should be understood that these examples are for illustration of the present invention, rather than limit the invention, wherein: FIG. 1 is a diagram showing a voice recognition implementation;

图2是示出TTS的实现的示意图;图3是示出根据本发明的机器翻译装置的原理图;图4是示出根据本发明的一个实施例的机器翻译装置的方框图;图5是示出根据本发明的一个实施例的机器翻译方法的流程图;图6是示出根据本发明的另一个实施例的机器翻译装置的方框图;以及图7是示出根据本发明的另一个实施例的机器翻译方法的流程图。 FIG 2 is a schematic diagram illustrating an implementation of TTS; Figure 3 shows a schematic diagram of the translation apparatus machine according to the present invention; FIG. 4 is a block diagram showing a machine translation apparatus according to embodiments of the present invention; FIG. 5 is a diagram the machine translation method flowchart illustrating an embodiment of the present invention; FIG. 6 is a block diagram showing a machine translation apparatus according to another embodiment of the present invention according to; and FIG. 7 is a diagram illustrating another embodiment of the present invention. a flowchart of a method of machine translation.

具体实施方式 Detailed ways

以下将详细参照本发明的优选实施例,其实例在附图中示出。 In detail below with reference to a preferred embodiment of the present invention, examples of which are illustrated in the accompanying drawings.

人们在实际的外语会话中,希望出现一种机器翻译装置,能够随身携带,能够听懂人们说的话,并且将听到的话翻译出来后能够开口说出来。 People in the actual conversation in a foreign language, want a machine translation device appears, can carry, can understand what people say, and hear the words come out post-translational able to speak out.

为了实现这个目的,需要解决三方面的问题。 To achieve this goal, the need to address three issues. 一是听懂人们说的话,二是将听到的话翻译出来,三是将翻译结果开口说出来。 First, understand what people say, the second is the translated hear, the third is to translate the results speak out.

图3是示出根据本发明的机器翻译装置的原理图。 FIG 3 is a schematic diagram of a machine translation apparatus according to the present invention is shown. 如图3所示,根据本发明的原理,将相关技术的语音识别技术、TTS技术、和机器翻译技术结合起来,即利用语音识别技术将输入的语音转换成文本(听懂人们说的话)(S410),然后利用机器翻译技术,即将一种语言翻译成另外一种语言(将听到的话翻译出来)(S420),最后利用TTS技术,翻译出来的语言转换成语音输出(将翻译结果开口说出来)(S430)。 As shown, the principles of the present invention, the speech recognition technology of the related art, the TTS technology, machine translation and 3 combined together, i.e., using a speech input voice recognition technology into text (say people understand) ( S410), and then using machine translation technology will soon translate one language into another language (to hear the words translated) (S420), and finally the use of TTS technology, language translated into speech output (translating the results speak out) (S430).

然而,在相关技术的语音识别技术、TTS技术、和机器翻译技术中存在一个问题,即由于语言的大词汇量和灵活多变的语法所带来的语义分析的问题。 However, there is a problem in speech recognition technology-related technology, TTS technology, and machine translation technology, namely the problem of semantic analysis of large vocabulary language grammar and flexible brought about due. 而这个问题在机器翻译整句的话当中显得尤为突出。 And this problem in machine translation sentence the words which is particularly prominent.

由于语言语义巨大的复杂性,使得语义分析特别重要,一方面要采用优化的算法,另一方面,通过减少将要翻译的语言限定为语言中的特定领域,可以显著地降低语义分析的计算量,使得以上相关技术的结合变得容易实现。 Due to the great complexity of the semantics of the language, a semantic analysis is particularly important that, on the one hand the optimization algorithm to be used, on the other hand, by reducing the language to be translated is defined as the domain-specific language, a semantic analysis of the amount of calculation can be significantly reduced, such that the combination of the above related art can be easily achieved.

因此,根据本发明的原理,为了解决上述语义分析的问题,将所要翻译的语言限定于特定的领域。 Thus, according to the principles of the present invention, in order to solve the above problems semantic analysis, language translation to be limited to a specific field.

优选地,例如,针对于会话交流,可以将所要翻译的语言限定于日常用语翻译,即日用语翻译。 Preferably, for example, for the exchange of the session, the language can be translated to be limited to the everyday language translation, language translation today.

可选地,如果针对于某些行业应用,例如通信领域,也可以将所要翻译的语言限定于通信用语。 Alternatively, if the application is directed to certain industries such as the field of communications, the language may be defined to be translated in terms of communication.

通过以上方式,可以显著地降低语义分析的计算量,并且显著地加快翻译速度,以及由于降低了对机器翻译装置运算能力和储存能力的要求,所以显著地加强了跨硬件平台性能,例如不但可以应用于PC,而且可以应用于单片机等各种嵌入式系统。 In the above manner, can significantly reduce the amount of calculation semantic analysis, and significantly speed up translation, as well as due to the reduced requirements for machine translation means computing power and storage capacity, it is significantly enhanced cross hardware platform, for example, not only can It applied to the PC, and can be applied to a variety of microcontrollers and other embedded systems.

可选地,为了改善便携性,更好地实现随时随地的会话交流,根据本发明的机器翻译装置可以用FLASH存储器的32位单片机来实现。 Alternatively, in order to improve portability, better realize the exchange of session anytime, anywhere, can be 32-bit microcontroller FLASH memory to store the machine translation apparatus according to the invention.

下面将结合附图来详细描述根据本发明的实施例的机器翻译装置以及机器翻译方法。 The machine translation apparatus according to an embodiment of the present invention and a machine translation method described in detail below in conjunction with the accompanying drawings.

图4是示出根据本发明的一个实施例的机器翻译装置500的方框图。 FIG 4 is a diagram illustrating the machine in accordance with one embodiment of the present invention, a block diagram of the translation apparatus 500.

机器翻译装置500,包括:语音信息输入单元510,用于输入第一语言的语音信息;语音识别单元520,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译单元530,用于将所转换的文本信息翻译成第二语言的文本信息。 Machine translation means 500, comprising: a voice information input unit 510, for voice information inputted in a first language; voice recognition unit 520, speech information for identifying a first language input, and converts it to text information; translation unit 530 for translating the text information converted into the second language text information.

图5是示出根据本发明的一个实施例的机器翻译方法的流程图。 FIG 5 is a flowchart showing a machine translation method according to one embodiment of the present invention.

该机器翻译方法包括以下步骤:语音信息输入步骤S610,用于输入第一语言的语音信息;语音识别步骤S620,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译步骤S630,用于将所转换的文本翻译成第二语言的文本信息。 The machine translation method comprising the steps of: voice information inputting step S610, the input speech information of the first language; speech recognition step S620, the speech information for identifying a first language input, and convert it to text information; and a translation step S630, the translation for the translated text to a second language text information.

图6是示出根据本发明的一个实施例的机器翻译装置700的方框图。 FIG 6 is a diagram illustrating the machine in accordance with one embodiment of the present invention, a block diagram of the translation apparatus 700.

如图6所示,根据本发明的机器翻译装置700包括:话筒710,用于输入用户的语音;语音识别单元720,利用语音识别技术来识别所输入的语音,并将其转换成文本;判断单元730,用于判断所转换的文本是一个单词还是一句日常用语;词典单元740,用于翻译单词;日常用语翻译单元750,用于翻译日常用语;显示屏760,用于显示翻译结果;TTS单元770,用于将翻译结果转换成语音信息;扬声器780,用于输出语音信息;以及键盘790,用于输入第一语言的文本信息和修改所转换的第二语言的文本信息。 6, the present invention according to the machine translation apparatus 700 comprises: a microphone 710 for inputting a user's voice; voice recognition unit 720, using voice recognition technology to recognize the voice input and convert it into text; Analyzing unit 730 for determining a converted text is an everyday language or word; dictionary unit 740, to translate a word; everyday language translation unit 750 for translating everyday language; display 760 for displaying a translation result; the TTS unit 770, for converting the translation result to speech information; a speaker 780 for outputting voice information; and a keyboard 790, the text information input in the first language for second language text information converted and modifications.

可选地,该机器翻译装置可以用PC来实现,也可以用嵌入式系统来实现。 Alternatively, the machine translation device can be realized with a PC, it can also be used to implement an embedded system. 值得注意的是,根据本发明的机器翻译装置并不限定于特定的硬件平台。 Notably, a machine translation apparatus according to the present invention is not limited to a specific hardware platform.

可选地,该机器翻译装置可用于中英日常用语对译、中日日常用语对译等。 Alternatively, the machine translation means may be used in everyday language to English translation, the Japanese translation of everyday language and the like. 值得注意的是,根据本发明的机器翻译装置并不限定于一种或几种语言。 Notably, a machine translation apparatus according to the invention is not limited to one or more languages.

可选地,该机器翻译装置可用于日常用语翻译、行业用语翻译等。 Alternatively, the machine translation means may be used for everyday language translation, language translation industry. 值得注意的是,根据本发明的机器翻译装置并不限定于特定领域的用语。 Notably, a machine translation apparatus according to the present invention is not limited to the specific terms of the art.

下面将根据图7来说明根据本发明的另一个实施例的机器翻译装置700的操作流程。 7 will now be described in accordance with FIG machine according to another embodiment of the present invention, the operational flow 700 of the translation apparatus.

图7是示出根据本发明的一个实施例的机器翻译装置700的流程图。 7 is a diagram illustrating an embodiment of the machine according to the present invention, a flowchart 700 of the translation apparatus.

在S810中,用户用预定的一种语言对机器翻译装置的话筒说话,即输入需要翻译的语音信息;在S820中,利用语音识别技术来识别所输入的语音,并将其转换成文本;在S830中,判断所转换的文本是一个单词还是一句日常用语;如果是单词,则转到S840,在S840中,翻译单词;如果是日常用语,则转到S850,在S850中,翻译日常用语;在S860中,显示翻译结果;在S870中,将翻译结果转换成语音信息;在S880中,向用户输出语音信息;以及在S880中,直接输入文本信息,可用于输入第一语言的文本信息和修改所转换的第二语言的文本信息。 In S810, the microphone on the user machine translation apparatus with a predetermined speak the language, i.e., the input voice information to be translated; in S820, using voice recognition technology to recognize the voice input and convert it into text; in S830, it is determined that the translated text is a word or an everyday language; if it is a word, go to S840, in S840, the translation of the word; if it is everyday language, go to S850, in S850, the translation of everyday language; in S860, the display translation result; in S870, the translation results converted into voice information; in S880, the voice output to the user information; and S880, the text information entered directly, can be used to input text information in a first language and modify the second language of the converted text information.

通过本发明的机器翻译装置,其一个优点在于不但能够进行机器翻译,而且能够直接听懂人们说的话,不再需要手工地文本输入。 By a machine translation apparatus according to the present invention is advantageous in that not only can be a machine translation, but also to directly understand what people say, no longer need to manually enter text.

根据本发明的机器翻译装置,其另一个优点在于能够用嵌入式系统设备实现,从而便于携带并且成本低廉。 The machine translation apparatus according to the invention, which is another advantage that the apparatus can be realized by an embedded system, so that portable and inexpensive.

通过本发明的机器翻译装置,其另一个优点在于还能够将机器翻译的结果直接说出来。 By a machine translation apparatus according to the present invention, which is another advantage that the result of machine translation is also possible to directly say.

通过本发明的机器翻译装置,其又一个优点在于不但能够翻译单词,还能够翻译特定领域整句的话,例如日常用语或者行业用语。 By a machine translation apparatus according to the present invention, not only a further advantage that the translation word, specific areas can also be translated sentence, then, for example, everyday language or industry terminology.

通过本发明的机器翻译装置,实现了人们在实际的外语会话中,能够听懂人们说的话,并且将听到的话翻译出来后能够开口说出来。 By a machine translation apparatus according to the present invention, realized in the actual Western people session, he says people can understand and be able to speak it will hear the translated words. 总而言之,携带这样的机器翻译装置就像随身配备了一名翻译人员。 All in all, carrying such as portable machine translation device is equipped with a translator.

以上所述仅为本发明的优选实施例而已,并不用于限制本发明,对于本领域的技术人员来说,本发明可以有各种更改和变化。 The above are only preferred embodiments of the present invention, it is not intended to limit the invention to those skilled in the art, the present invention may have various changes and variations. 凡在本发明的精神和原则之内,所作的任何修改、等同替换、改进等,均应包含在本发明的保护范围之内。 Any modification within the spirit and principle of the present invention, made, equivalent substitutions, improvements, etc., should be included within the scope of the present invention.

Claims (14)

1.一种机器翻译装置,其特征在于,包括:语音信息输入单元,用于输入第一语言的语音信息;语音识别单元,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译单元,用于将所转换的文本信息翻译成第二语言的文本信息。 A machine translation apparatus, comprising: voice information inputting means for inputting voice information of the first language; voice recognition unit configured to recognize speech information of the first language input, and converts into text information; and a translation unit for translating the text information converted into the second language text information.
2.根据权利要求1所述的机器翻译装置,其特征在于,还包括:文本语音转换单元,用于将所翻译的第二语言的文本信息转换成语音信息;以及语音信息输出单元,用于将所转换的语音信息输出。 2. The machine translation apparatus according to claim 1, characterized in that, further comprising: a text to speech conversion means for converting the translated text message into voice information of the second language; and a voice information output unit for the output of the converted voice messages.
3.根据权利要求1所述的机器翻译装置,其特征在于,还包括:判断单元,用于判断所转换的文本信息是单词还是句子;以及词典单元,用于翻译单词;其中,当所述判断单元判断所转换的文本是单词时,通过所述词典单元将所述单词翻译成第二语言的文本信息;以及当所述判断单元判断所转换的文本是句子时,通过所述翻译单元将所述句子翻译成第二语言的文本信息。 3. The machine translation apparatus according to claim 1, characterized in that, further comprising: determining means for determining whether the converted text information is a word or a sentence; and dictionary means for translating a word; wherein, when the determination means determines whether the converted text word is, by means of the dictionary word translated into the second language text information; and when the determination unit determines whether the converted text is a sentence, the translation unit by the the translation of the sentence into the second language text information.
4.根据权利要求1至3中任一项所述的机器翻译装置,其特征在于,还包括:文本信息输出单元,用于输出所转换的文本信息和所翻译的第二语言的文本信息;以及文本信息输入单元,用于输入第一语言的文本信息和修改所转换的第二语言的文本信息。 Machine translation apparatus according to claim any one of claims 1 to 3, characterized in that, further comprising: text information output means for outputting the converted text information and text information in the translated second language; and a text information input unit for input of a first language, the second language text information and modifications of the converted text information.
5.根据权利要求1至4中任一项所述的机器翻译装置,其特征在于,用计算机来实现。 The machine translation apparatus according to claim 4, characterized in that, with the computer.
6.根据权利要求1至4中任一项所述的机器翻译装置,其特征在于,用嵌入式系统设备来实现。 The machine translation apparatus according to claim 4, characterized in that the device is achieved by the embedded system.
7.根据权利要求1至4中任一项所述的机器翻译装置,其特征在于,所述第一语言限定为一种现有语言中的日常用语。 7. The machine translation apparatus 1 in any 4-1 claim, characterized in that the first language is defined as a conventional language in everyday language.
8.根据权利要求1至4中任一项所述的机器翻译装置,其特征在于,所述第一语言限定为一种现有语言中的行业用语。 A machine translation apparatus according to any 4-1 claim, characterized in that the first language is defined as the industry in terms of a conventional language.
9.一种机器翻译方法,其特征在于,包括以下步骤:语音信息输入步骤,用于输入第一语言的语音信息;语音识别步骤,用于识别所输入的第一语言的语音信息,并将其转换成文本信息;以及翻译步骤,用于将所转换的文本翻译成第二语言的文本信息。 A machine translation method, characterized by comprising the steps of: voice information inputting step for inputting a first language speech information; speech recognition step of identifying a first language speech information inputted, and which is converted into text information; and a translation step for translating the translated text to a second language text information.
10.根据权利要求9所述的方法,其特征在于,还包括以下步骤:文本语音转换步骤,用于将所翻译的第二语言的文本信息转换成语音信息;以及语音信息输出步骤,用于将所转换的语音信息输出。 10. The method according to claim 9, characterized in that, further comprising the step of: text to speech conversion step for converting the translated text message into voice information of the second language; and voice information outputting step of the output of the converted voice messages.
11.根据权利要求9所述的方法,其特征在于,还包括以下步骤:判断步骤,用于判断所转换的文本信息是单词还是句子;以及单词翻译步骤,用于翻译单词,其中当判断所转换的文本信息是单词时,通过所述单词翻译步骤将所述单词翻译成第二语言的文本信息;以及当判断所转换的文本信息是句子时,通过所述翻译步骤将所述句子翻译成第二语言的文本信息。 11. The method according to claim 9, characterized in that, further comprising: determining step for determining whether the converted text information is a word or a sentence; and word translation step for translating a word, wherein when it is judged that converted text information is a word, a word by word translation step of translating the second language into text information; and when determining the converted text information is a sentence, by the step of translating the sentence into the translated text messages a second language.
12.根据权利要求9至11中任一项所述的方法,其特征在于,还包括以下步骤:文本信息输出步骤,用于输出所转换的文本信息和所翻译的第二语言的文本信息;以及文本信息输入步骤,用于输入第一语言的文本信息和修改所转换的文本信息。 12. The method according to any one of claims 9 to 11, characterized in that, further comprising the step of: text information output step of outputting the converted text information and text information in the translated second language; and a text information input step for inputting a first language, text information and text information converted modification.
13.根据权利要求9至12中任一项所述的方法,其特征在于,所述预定语言限定为一种现有语言中的日常用语。 9 to 12 13. A method according to any one of the preceding claims, wherein said predetermined language is defined as a conventional language in everyday language.
14.根据权利要求9至12中任一项所述的方法,其特征在于,所述预定语言限定为一种现有语言中的行业用语。 9 to 12 14. A method according to any one of the preceding claims, wherein said predetermined language is defined as the industry in terms of a conventional language.
CN 200610002940 2006-01-25 2006-01-25 Machine translation device and method thereof CN101008942A (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN 200610002940 CN101008942A (en) 2006-01-25 2006-01-25 Machine translation device and method thereof

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN 200610002940 CN101008942A (en) 2006-01-25 2006-01-25 Machine translation device and method thereof

Publications (1)

Publication Number Publication Date
CN101008942A true CN101008942A (en) 2007-08-01

Family

ID=38697376

Family Applications (1)

Application Number Title Priority Date Filing Date
CN 200610002940 CN101008942A (en) 2006-01-25 2006-01-25 Machine translation device and method thereof

Country Status (1)

Country Link
CN (1) CN101008942A (en)

Cited By (46)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN102237083A (en) * 2010-04-23 2011-11-09 姚敏锋 Portable interpretation system based on WinCE platform and language recognition method thereof
CN102239517A (en) * 2009-01-28 2011-11-09 三菱电机株式会社 Speech recognition device
CN102467908A (en) * 2010-11-17 2012-05-23 英业达股份有限公司 Multilingual voice control system and method thereof
CN102650960A (en) * 2012-03-31 2012-08-29 奇智软件(北京)有限公司 Method and device for eliminating faults of terminal equipment
CN101923858B (en) 2009-06-17 2012-11-21 劳英杰 Real-time and synchronous mutual translation voice terminal
CN103514153A (en) * 2012-06-29 2014-01-15 株式会社 东芝 Speech translation apparatus, method and program
CN103838714A (en) * 2012-11-22 2014-06-04 北大方正集团有限公司 Method and device for converting voice information
CN104049960A (en) * 2013-03-16 2014-09-17 上海能感物联网有限公司 Method for remotely controlling computer program operation through foreign-language voice
CN104380284A (en) * 2012-03-06 2015-02-25 苹果公司 Handling speech synthesis of content for multiple languages
CN104679733A (en) * 2013-11-26 2015-06-03 中国移动通信集团公司 Voice conversation translation method, device and system
CN104899192A (en) * 2014-03-07 2015-09-09 韩国电子通信研究院 Apparatus and method for automatic interpretation
CN106156012A (en) * 2016-06-28 2016-11-23 乐视控股(北京)有限公司 A kind of method for generating captions and device
CN106649295A (en) * 2017-01-04 2017-05-10 携程旅游网络技术(上海)有限公司 Text translation method for mobile terminal
US9668024B2 (en) 2014-06-30 2017-05-30 Apple Inc. Intelligent automated assistant for TV user interactions
US9865248B2 (en) 2008-04-05 2018-01-09 Apple Inc. Intelligent text-to-speech conversion
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9966060B2 (en) 2013-06-07 2018-05-08 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US9986419B2 (en) 2014-09-30 2018-05-29 Apple Inc. Social reminders
US10043516B2 (en) 2016-09-23 2018-08-07 Apple Inc. Intelligent automated assistant
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
US10083690B2 (en) 2014-05-30 2018-09-25 Apple Inc. Better resolution when referencing to concepts
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control
US10169329B2 (en) 2014-05-30 2019-01-01 Apple Inc. Exemplar-based natural language processing
US10192552B2 (en) 2016-06-10 2019-01-29 Apple Inc. Digital assistant providing whispered speech
US10223066B2 (en) 2015-12-23 2019-03-05 Apple Inc. Proactive assistance based on dialog communication between devices
US10249300B2 (en) 2016-06-06 2019-04-02 Apple Inc. Intelligent list reading
US10269345B2 (en) 2016-06-11 2019-04-23 Apple Inc. Intelligent task discovery
US10283110B2 (en) 2009-07-02 2019-05-07 Apple Inc. Methods and apparatuses for automatic speech recognition
US10297253B2 (en) 2016-06-11 2019-05-21 Apple Inc. Application integration with a digital assistant
US10318871B2 (en) 2005-09-08 2019-06-11 Apple Inc. Method and apparatus for building an intelligent automated assistant
US10332518B2 (en) 2017-05-09 2019-06-25 Apple Inc. User interface for correcting recognition errors
US10354011B2 (en) 2016-06-09 2019-07-16 Apple Inc. Intelligent automated assistant in a home environment
US10356243B2 (en) 2015-06-05 2019-07-16 Apple Inc. Virtual assistant aided communication with 3rd party service in a communication session
US10366158B2 (en) 2015-09-29 2019-07-30 Apple Inc. Efficient word encoding for recurrent neural network language models
US10410637B2 (en) 2017-05-12 2019-09-10 Apple Inc. User-specific acoustic models
CN110309289A (en) * 2019-08-23 2019-10-08 深圳市优必选科技股份有限公司 A kind of sentence generation method, sentence generation device and smart machine
US10446143B2 (en) 2016-03-14 2019-10-15 Apple Inc. Identification of voice inputs providing credentials
US10482874B2 (en) 2017-05-15 2019-11-19 Apple Inc. Hierarchical belief states for digital assistants
US10490187B2 (en) 2016-06-10 2019-11-26 Apple Inc. Digital assistant providing automated status report
US10509862B2 (en) 2016-06-10 2019-12-17 Apple Inc. Dynamic phrase expansion of language input
US10521466B2 (en) 2016-09-19 2019-12-31 Apple Inc. Data driven natural language event detection and classification

Cited By (53)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US10318871B2 (en) 2005-09-08 2019-06-11 Apple Inc. Method and apparatus for building an intelligent automated assistant
US9865248B2 (en) 2008-04-05 2018-01-09 Apple Inc. Intelligent text-to-speech conversion
CN102239517A (en) * 2009-01-28 2011-11-09 三菱电机株式会社 Speech recognition device
CN102239517B (en) 2009-01-28 2013-05-08 三菱电机株式会社 Speech recognition device
CN101923858B (en) 2009-06-17 2012-11-21 劳英杰 Real-time and synchronous mutual translation voice terminal
US10283110B2 (en) 2009-07-02 2019-05-07 Apple Inc. Methods and apparatuses for automatic speech recognition
CN102237083A (en) * 2010-04-23 2011-11-09 姚敏锋 Portable interpretation system based on WinCE platform and language recognition method thereof
CN102467908B (en) * 2010-11-17 2016-01-06 英业达股份有限公司 Multilingual voice control system and method thereof
CN102467908A (en) * 2010-11-17 2012-05-23 英业达股份有限公司 Multilingual voice control system and method thereof
CN104380284A (en) * 2012-03-06 2015-02-25 苹果公司 Handling speech synthesis of content for multiple languages
CN104380284B (en) * 2012-03-06 2018-01-30 苹果公司 For the phonetic synthesis of multilingual process content
CN102650960A (en) * 2012-03-31 2012-08-29 奇智软件(北京)有限公司 Method and device for eliminating faults of terminal equipment
CN102650960B (en) * 2012-03-31 2015-04-15 北京奇虎科技有限公司 Method and device for eliminating faults of terminal equipment
US10079014B2 (en) 2012-06-08 2018-09-18 Apple Inc. Name recognition system
CN103514153A (en) * 2012-06-29 2014-01-15 株式会社 东芝 Speech translation apparatus, method and program
US9971774B2 (en) 2012-09-19 2018-05-15 Apple Inc. Voice-based media searching
CN103838714A (en) * 2012-11-22 2014-06-04 北大方正集团有限公司 Method and device for converting voice information
CN104049960A (en) * 2013-03-16 2014-09-17 上海能感物联网有限公司 Method for remotely controlling computer program operation through foreign-language voice
US9966060B2 (en) 2013-06-07 2018-05-08 Apple Inc. System and method for user-specified pronunciation of words for speech synthesis and recognition
CN104679733B (en) * 2013-11-26 2018-02-23 中国移动通信集团公司 A kind of voice dialogue interpretation method, apparatus and system
CN104679733A (en) * 2013-11-26 2015-06-03 中国移动通信集团公司 Voice conversation translation method, device and system
CN104899192A (en) * 2014-03-07 2015-09-09 韩国电子通信研究院 Apparatus and method for automatic interpretation
CN104899192B (en) * 2014-03-07 2018-03-27 韩国电子通信研究院 For the apparatus and method interpreted automatically
US10169329B2 (en) 2014-05-30 2019-01-01 Apple Inc. Exemplar-based natural language processing
US10083690B2 (en) 2014-05-30 2018-09-25 Apple Inc. Better resolution when referencing to concepts
US9668024B2 (en) 2014-06-30 2017-05-30 Apple Inc. Intelligent automated assistant for TV user interactions
US9986419B2 (en) 2014-09-30 2018-05-29 Apple Inc. Social reminders
US10356243B2 (en) 2015-06-05 2019-07-16 Apple Inc. Virtual assistant aided communication with 3rd party service in a communication session
US10366158B2 (en) 2015-09-29 2019-07-30 Apple Inc. Efficient word encoding for recurrent neural network language models
US10049668B2 (en) 2015-12-02 2018-08-14 Apple Inc. Applying neural network language models to weighted finite state transducers for automatic speech recognition
US10223066B2 (en) 2015-12-23 2019-03-05 Apple Inc. Proactive assistance based on dialog communication between devices
US10446143B2 (en) 2016-03-14 2019-10-15 Apple Inc. Identification of voice inputs providing credentials
US9934775B2 (en) 2016-05-26 2018-04-03 Apple Inc. Unit-selection text-to-speech synthesis based on predicted concatenation parameters
US9972304B2 (en) 2016-06-03 2018-05-15 Apple Inc. Privacy preserving distributed evaluation framework for embedded personalized systems
US10249300B2 (en) 2016-06-06 2019-04-02 Apple Inc. Intelligent list reading
US10049663B2 (en) 2016-06-08 2018-08-14 Apple, Inc. Intelligent automated assistant for media exploration
US10354011B2 (en) 2016-06-09 2019-07-16 Apple Inc. Intelligent automated assistant in a home environment
US10490187B2 (en) 2016-06-10 2019-11-26 Apple Inc. Digital assistant providing automated status report
US10509862B2 (en) 2016-06-10 2019-12-17 Apple Inc. Dynamic phrase expansion of language input
US10067938B2 (en) 2016-06-10 2018-09-04 Apple Inc. Multilingual word prediction
US10192552B2 (en) 2016-06-10 2019-01-29 Apple Inc. Digital assistant providing whispered speech
US10297253B2 (en) 2016-06-11 2019-05-21 Apple Inc. Application integration with a digital assistant
US10269345B2 (en) 2016-06-11 2019-04-23 Apple Inc. Intelligent task discovery
US10089072B2 (en) 2016-06-11 2018-10-02 Apple Inc. Intelligent device arbitration and control
CN106156012A (en) * 2016-06-28 2016-11-23 乐视控股(北京)有限公司 A kind of method for generating captions and device
US10521466B2 (en) 2016-09-19 2019-12-31 Apple Inc. Data driven natural language event detection and classification
US10043516B2 (en) 2016-09-23 2018-08-07 Apple Inc. Intelligent automated assistant
CN106649295A (en) * 2017-01-04 2017-05-10 携程旅游网络技术(上海)有限公司 Text translation method for mobile terminal
US10332518B2 (en) 2017-05-09 2019-06-25 Apple Inc. User interface for correcting recognition errors
US10410637B2 (en) 2017-05-12 2019-09-10 Apple Inc. User-specific acoustic models
US10482874B2 (en) 2017-05-15 2019-11-19 Apple Inc. Hierarchical belief states for digital assistants
CN110309289B (en) * 2019-08-23 2019-12-06 深圳市优必选科技股份有限公司 Sentence generation method, sentence generation device and intelligent equipment
CN110309289A (en) * 2019-08-23 2019-10-08 深圳市优必选科技股份有限公司 A kind of sentence generation method, sentence generation device and smart machine

Similar Documents

Publication Publication Date Title
Besacier et al. Automatic speech recognition for under-resourced languages: A survey
Rabiner et al. Theory and applications of digital speech processing
Moberg Contributions to Multilingual Low-Footprint TTS System for Hand-Held Devices
US7280968B2 (en) Synthetically generated speech responses including prosodic characteristics of speech inputs
CN1667700B (en) Method for adding voice or acoustic description, pronunciation in voice recognition dictionary
US8290775B2 (en) Pronunciation correction of text-to-speech systems between different spoken languages
US8498857B2 (en) System and method for rapid prototyping of existing speech recognition solutions in different languages
US6937983B2 (en) Method and system for semantic speech recognition
US6910012B2 (en) Method and system for speech recognition using phonetically similar word alternatives
CN1277248C (en) Speech recognition system
JP5327054B2 (en) Pronunciation variation rule extraction device, pronunciation variation rule extraction method, and pronunciation variation rule extraction program
US6272464B1 (en) Method and apparatus for assembling a prediction list of name pronunciation variations for use during speech recognition
Wang et al. Complete recognition of continuous Mandarin speech for Chinese language with very large vocabulary using limited training data
US7496498B2 (en) Front-end architecture for a multi-lingual text-to-speech system
US6374224B1 (en) Method and apparatus for style control in natural language generation
US8949128B2 (en) Method and apparatus for providing speech output for speech-enabled applications
US6510410B1 (en) Method and apparatus for recognizing tone languages using pitch information
US8352260B2 (en) Multimodal unification of articulation for device interfacing
US7249019B2 (en) Method and apparatus for providing an integrated speech recognition and natural language understanding for a dialog system
US6067520A (en) System and method of recognizing continuous mandarin speech utilizing chinese hidden markou models
US6952665B1 (en) Translating apparatus and method, and recording medium used therewith
US20110238407A1 (en) Systems and methods for speech-to-speech translation
US20160379638A1 (en) Input speech quality matching
US7191132B2 (en) Speech synthesis apparatus and method
CN1591315A (en) Semantic object synchronous understanding for highly interactive interface

Legal Events

Date Code Title Description
C06 Publication
C10 Request of examination as to substance
C12 Rejection of an application for a patent