CN105827878B - Voice messaging conversion method and voice transfer gateway - Google Patents
Voice messaging conversion method and voice transfer gateway Download PDFInfo
- Publication number
- CN105827878B CN105827878B CN201510002321.XA CN201510002321A CN105827878B CN 105827878 B CN105827878 B CN 105827878B CN 201510002321 A CN201510002321 A CN 201510002321A CN 105827878 B CN105827878 B CN 105827878B
- Authority
- CN
- China
- Prior art keywords
- voice
- voice conversion
- gateway
- server
- unit
- 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.)
- Active
Links
- 238000006243 chemical reaction Methods 0.000 title claims abstract description 234
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000004044 response Effects 0.000 claims description 18
- 238000005538 encapsulation Methods 0.000 claims description 3
- 230000001960 triggered effect Effects 0.000 claims description 2
- 230000006870 function Effects 0.000 description 8
- 238000010586 diagram Methods 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000004891 communication Methods 0.000 description 3
- 230000008878 coupling Effects 0.000 description 3
- 238000010168 coupling process Methods 0.000 description 3
- 238000005859 coupling reaction Methods 0.000 description 3
- 239000000203 mixture Substances 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 241001672694 Citrus reticulata Species 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004883 computer application Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Landscapes
- Data Exchanges In Wide-Area Networks (AREA)
- Information Transfer Between Computers (AREA)
Abstract
本发明实施例公开了一种语音信息转换方法及语音转换网关，所述方法包括：所述语音转换网关接收所述接入网侧转发的Web消息，确定所述Web消息包含语音内容时，获取所述语音内容中语音的类别；根据所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器，并将所述语音内容向所选取的语音转换服务器发送；接收语音转换服务器反馈的语音转换结果，将所述语音转换结果封装为Web消息，将封装后的Web消息向所述互联网侧发送。
The embodiment of the present invention discloses a voice information conversion method and a voice conversion gateway. The method includes: the voice conversion gateway receives a Web message forwarded by the access network side, and when it is determined that the Web message contains voice content, obtaining The category of the voice in the voice content; according to the category of the voice, a voice conversion server capable of recognizing the voice of the category is selected from the one or more voice conversion servers, and the voice content is sent to the selected voice conversion server. Send; receive the voice conversion result fed back by the voice conversion server, encapsulate the voice conversion result into a Web message, and send the encapsulated Web message to the Internet side.
Description
技术领域technical field
本发明涉及语音转换技术，尤其涉及一种基于Web应用的语音信息转换方法及语音转换网关。The invention relates to a voice conversion technology, in particular to a voice information conversion method and a voice conversion gateway based on a Web application.
背景技术Background technique
目前，语音识别技术发展非常迅猛，已应用于各技术领域，如用于个人电脑或手机终端中作身份识别用。更多的语音识别应用，是识别用户输入的语音，将其转换为字符作为文字信息输出，或作为指令发送给处理器。目前，语音识别技术多用于单电子终端中，而随着互联网技术的不断成熟，为进一步方便用户对互联网进行访问，语音识别应用于Web网页将会有相当广阔的前景。目前，如果在用户终端侧对语音进行识别，鉴于用户终端的处理能力有限，很难达到较高的识别精度，而设置于互联网网络侧时，鉴于用户终端与互联网通信的不稳定性，识别效果也不会特别好，并且，语音文件一般比较大，在用户终端与互联网之间传输的稳定性也不佳。At present, speech recognition technology is developing very rapidly, and has been applied to various technical fields, such as being used for identity recognition in personal computers or mobile phone terminals. More speech recognition applications are to recognize the speech input by the user, convert it into characters and output it as text information, or send it as an instruction to the processor. At present, speech recognition technology is mostly used in single electronic terminals, and with the continuous maturity of Internet technology, in order to further facilitate users to access the Internet, speech recognition applied to Web pages will have quite broad prospects. At present, if the voice recognition is performed on the user terminal side, it is difficult to achieve a high recognition accuracy due to the limited processing capability of the user terminal. However, when it is set on the Internet network side, due to the instability of the communication between the user terminal and the Internet, the recognition effect will be reduced. It is not particularly good, and the voice files are generally relatively large, and the stability of transmission between the user terminal and the Internet is not good.
发明内容SUMMARY OF THE INVENTION
本发明实施例为解决上述技术问题，提供一种语音信息转换方法及语音转换网关，能快捷准确地识别出语音信息，识别准确度及稳定性较高。In order to solve the above technical problems, the embodiments of the present invention provide a voice information conversion method and a voice conversion gateway, which can quickly and accurately identify voice information, and have high recognition accuracy and stability.
本发明实施例的技术方案是这样实现的：The technical solution of the embodiment of the present invention is realized as follows:
一种语音信息转换方法，在接入网与互联网之间设置语音转换网关，所述语音转换网关与一个以上的语音转换服务器连接；所述方法包括：A voice information conversion method, wherein a voice conversion gateway is set between an access network and the Internet, and the voice conversion gateway is connected with more than one voice conversion server; the method includes:
所述语音转换网关接收所述接入网侧转发的Web消息，确定所述Web消息包含语音内容时，获取所述语音内容中语音的类别；The voice conversion gateway receives the Web message forwarded by the access network side, and when it is determined that the Web message contains voice content, obtains the voice category in the voice content;
根据所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器，并将所述语音内容向所选取的语音转换服务器发送；According to the category of the voice, a voice conversion server capable of recognizing the voice of the category is selected from the one or more voice conversion servers, and the voice content is sent to the selected voice conversion server;
接收语音转换服务器反馈的语音转换结果，将所述语音转换结果封装为Web消息，将封装后的Web消息向所述互联网侧发送。Receive the voice conversion result fed back by the voice conversion server, encapsulate the voice conversion result into a Web message, and send the encapsulated Web message to the Internet side.
优选地，所述方法还包括：Preferably, the method further includes:
所述语音转换网关向所述一个以上的语音转换服务器发送状态查询消息，The voice conversion gateway sends a status query message to the one or more voice conversion servers,
在设定时长内接收到语音转换服务器的响应消息时，确定语音转换服务器正常运行；When receiving a response message from the voice conversion server within the set time period, determine that the voice conversion server is running normally;
在设定时长内未接收到语音转换服务器的响应消息或在设定时长内未接收到语音转换服务器的响应消息超过设定次数时，确定语音转换服务器非正常运行。When no response message from the voice conversion server is received within the set period of time or no response message from the voice conversion server is received within the set period of time for more than a set number of times, it is determined that the voice conversion server is operating abnormally.
优选地，所述方法还包括：Preferably, the method further includes:
所述语音转换网关根据语音转换服务器的当前状态及所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。The voice conversion gateway selects a voice conversion server capable of recognizing the voice of the category from among the one or more voice conversion servers according to the current state of the voice conversion server and the type of the voice.
优选地，所述方法还包括：Preferably, the method further includes:
所述语音转换网关未接收到语音转换服务器反馈的语音转换结果，而确定语音转换网关故障时，根据所述语音的类别重新在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。The voice conversion gateway does not receive the voice conversion result fed back by the voice conversion server, and when it is determined that the voice conversion gateway is faulty, it re-selects a voice conversion server that can recognize the voice of the category according to the voice category. Voice conversion server.
优选地，为所述语音转换网关设置至少一个冗余语音转换网关；所述方法还包括：Preferably, at least one redundant voice conversion gateway is set for the voice conversion gateway; the method further includes:
所述接入网确定当前工作的语音转换网关故障时，在所述至少一个冗余语音转换网关中选取一个代替当前的语音转换网关。When the access network determines that the currently working voice conversion gateway is faulty, it selects one of the at least one redundant voice conversion gateway to replace the current voice conversion gateway.
优选地，所述语音转换结果为字符信息。Preferably, the voice conversion result is character information.
一种语音转换网关，所述语音转换网关设置于接入网与互联网之间，所述语音转换网关与一个以上的语音转换服务器连接；所述语音转换网关包括：第一接收单元、第一确定单元、获取单元、选取单元、第一发送单元、第二接收单元、封装单元和第二发送单元，其中：A voice conversion gateway, the voice conversion gateway is arranged between an access network and the Internet, and the voice conversion gateway is connected with more than one voice conversion server; the voice conversion gateway comprises: a first receiving unit, a first determining unit, acquiring unit, selecting unit, first sending unit, second receiving unit, encapsulating unit and second sending unit, wherein:
第一接收单元，用于接收所述接入网侧转发的Web消息；a first receiving unit, configured to receive the Web message forwarded by the access network side;
第一确定单元，用于确定所述Web消息是否包含语音内容，包含语音内容时触发所述获取单元；a first determining unit for determining whether the Web message contains voice content, and triggering the acquiring unit when the web message contains voice content;
获取单元，用于获取所述语音内容中语音的类别；an obtaining unit for obtaining the category of the voice in the voice content;
选取单元，用于根据所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器；a selecting unit, configured to select a voice conversion server capable of recognizing the voice of the category from among the one or more voice conversion servers according to the category of the voice;
第一发送单元，用于将所述语音内容向所选取的语音转换服务器发送；a first sending unit, for sending the voice content to the selected voice conversion server;
第二接收单元，用于接收语音转换服务器反馈的语音转换结果；a second receiving unit, configured to receive the voice conversion result fed back by the voice conversion server;
封装单元，用于将所述语音转换结果封装为Web消息；an encapsulation unit for encapsulating the speech conversion result into a Web message;
第二发送单元，用于将封装后的Web消息向所述互联网侧发送。The second sending unit is configured to send the encapsulated Web message to the Internet side.
优选地，所述语音转换网关还包括：第三发送单元、第三接收单元、第二确定单元和第三确定单元，其中：Preferably, the voice conversion gateway further comprises: a third sending unit, a third receiving unit, a second determining unit and a third determining unit, wherein:
第三发送单元，用于向所述一个以上的语音转换服务器发送状态查询消息；a third sending unit, configured to send a status query message to the one or more voice conversion servers;
第三接收单元，用于接收语音转换服务器的响应消息；The third receiving unit is used for receiving the response message of the voice conversion server;
第二确定单元，用于在所述第三接收单元在设定时长内接收到语音转换服务器的响应消息时，确定语音转换服务器正常运行；a second determining unit, configured to determine that the voice conversion server is running normally when the third receiving unit receives a response message from the voice conversion server within a set time period;
第三确定单元，用于在所述第三接收单元在设定时长内未接收到语音转换服务器的响应消息或在设定时长内未接收到语音转换服务器的响应消息超过设定次数时，确定语音转换服务器非正常运行。a third determining unit, configured to determine when the third receiving unit does not receive a response message from the voice conversion server within the set time period or does not receive a response message from the voice conversion server within the set time period for more than a set number of times The voice conversion server is not functioning properly.
优选地，所述选取单元，还用于根据语音转换服务器的当前状态及所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。Preferably, the selecting unit is further configured to select a voice conversion server capable of recognizing the voice of the category among the one or more voice conversion servers according to the current state of the voice conversion server and the category of the voice.
优选地，所述语音转换网关还包括：第四确定单元，用于在所述第二接收单元未接收到语音转换服务器反馈的语音转换结果时，确定语音转换网关故障，触发所述选取单元根据所述语音的类别重新在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。Preferably, the voice conversion gateway further includes: a fourth determining unit, configured to determine that the voice conversion gateway is faulty when the second receiving unit does not receive the voice conversion result fed back by the voice conversion server, and trigger the selection unit to be based on The category of the voice is to select a voice conversion server capable of recognizing the voice of the category from among the one or more voice conversion servers.
优选地，所述语音转换结果为字符信息。Preferably, the voice conversion result is character information.
本发明实施例中，通过在接入网与互联网之间设置语音转换网关，对用户终端发往互联网的Web消息进行识别，确认Web消息中承载的信息为语音信息时，将其发送至语音转换服务器，经语音转换服务器识别为字符信息后，再由语音转换网关将转换后的字符信息重新封装为Web消息而发送至互联网侧。本发明实施例中，通过设置不同类型的语音转换服务器，能识别不同类型的语音，识别准确度高；由于语音转换网关与语音转换服务器之间的连接稳定度高而识别可靠，而语音转换服务器对用户不可见，提升了用户体验。In the embodiment of the present invention, by setting a voice conversion gateway between the access network and the Internet, the Web message sent by the user terminal to the Internet is identified, and when it is confirmed that the information carried in the Web message is voice information, it is sent to the voice conversion After the server is recognized as character information by the speech conversion server, the speech conversion gateway repackages the converted character information into a Web message and sends it to the Internet side. In the embodiment of the present invention, by setting different types of voice conversion servers, different types of voices can be recognized, and the recognition accuracy is high; It is invisible to the user and improves the user experience.
附图说明Description of drawings
图1为本发明实施例的网络结构示意图；1 is a schematic diagram of a network structure according to an embodiment of the present invention;
图2为本发明实施例一的语音信息转换方法的流程图；2 is a flowchart of a method for converting voice information according to Embodiment 1 of the present invention;
图3为本发明实施例二的语音信息转换方法的流程图；3 is a flowchart of a method for converting voice information according to Embodiment 2 of the present invention;
图4为本发明实施例的语音转换网关的组成结构示意图。FIG. 4 is a schematic diagram of the composition and structure of a voice conversion gateway according to an embodiment of the present invention.
具体实施方式Detailed ways
为使本发明的目的、技术方案和优点更加清楚明白，以下举实施例并参照附图，对本发明进一步详细说明。In order to make the objectives, technical solutions and advantages of the present invention more clearly understood, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments.
图1为本发明实施例的网络结构示意图，如图1所示，本发明实施例中，FIG. 1 is a schematic diagram of a network structure according to an embodiment of the present invention. As shown in FIG. 1 , in the embodiment of the present invention,
在接入网的网络侧如移动网络侧部署Web应用网关；由该Web应用网关维护语言种类与Web语音转换服务器之间的对应关系；该Web应用网关截获包括语音内容的Web消息，将根据Web消息中语音内容的语言种类将语音内容转发到对应的Web语音转换服务器，Web语音转换服务器将其转换成字符，然后该Web应用网关将Web语音转换服务器的返回字符重新封装为新的Web消息，并将重新封装的Web消息发送至互联网侧。A web application gateway is deployed on the network side of the access network, such as the mobile network side; the web application gateway maintains the correspondence between language types and the web voice conversion server; the web application gateway intercepts web messages including The language type of the voice content in the message forwards the voice content to the corresponding web-to-speech server, the web-to-speech server converts it into characters, and then the web application gateway re-encapsulates the returned characters from the web-to-speech server into a new web message, And send the repackaged Web message to the Internet side.
本发明实施例中，当Web应用网关探测各Web语音转换服务器的可用性，必要时，为语音Web消息选取可用的Web语音转换服务器。In the embodiment of the present invention, when the web application gateway detects the availability of each web speech conversion server, if necessary, selects an available web speech conversion server for the voice web message.
本发明实施例的技术方案，对于Web应用开发者而言，无需了解Web应用网关的地址信息；也无需了解Web语音转换服务器支持的语言种类，降低了开发者使用语音转换功能的门槛；同时有助于汇聚、动态组合业界优秀的语音转换资源。The technical solution of the embodiment of the present invention, for the web application developer, does not need to know the address information of the web application gateway; also does not need to know the language types supported by the web speech conversion server, which lowers the threshold for developers to use the speech conversion function; It helps to aggregate and dynamically combine the industry's excellent voice conversion resources.
图2为本发明实施例一的语音信息转换方法的流程图，结合图1，本发明实施例中，在接入网如移动网络与互联网之间设置语音转换网关，所述语音转换网关与一个以上的语音转换服务器连接；如图2所示，本示例的语音信息转换方法包括以下步骤：2 is a flowchart of a method for converting voice information according to Embodiment 1 of the present invention. With reference to FIG. 1 , in this embodiment of the present invention, a voice conversion gateway is set between an access network such as a mobile network and the Internet, and the voice conversion gateway is connected to a The above voice conversion server is connected; as shown in Figure 2, the voice information conversion method of this example includes the following steps:
步骤201，语音转换网关接收所述接入网侧转发的Web消息，确定所述Web消息包含语音内容时，获取所述语音内容中语音的类别。Step 201: The voice conversion gateway receives the Web message forwarded by the access network side, and when it is determined that the Web message contains voice content, obtains the voice category in the voice content.
作为一种实现方式，本发明实施例中，语音转换网关可以通过Web消息中的特定标签，来识别Web消息为语音Web消息还是字符Web消息。例如，可通过Web应用识别出待Web封装的内容为语音内容还是字符内容，从而在所封装后的Web消息中插入不同的标签，由语音转换网关对所接收的Web消息进行识别。As an implementation manner, in this embodiment of the present invention, the voice conversion gateway can identify whether the Web message is a voice Web message or a character Web message through a specific tag in the Web message. For example, the Web application can identify whether the content to be Web encapsulated is voice content or character content, so that different tags are inserted into the encapsulated Web message, and the received Web message is recognized by the speech conversion gateway.
需要说明的是，本发明实施例中，由用户终端侧发送的Web消息，需要经语音转换网关处理，再发送至互联网侧。It should be noted that, in this embodiment of the present invention, the Web message sent by the user terminal side needs to be processed by the voice conversion gateway, and then sent to the Internet side.
步骤202，根据所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器，并将所述语音内容向所选取的语音转换服务器发送。Step 202, according to the type of the voice, select a voice conversion server capable of recognizing the voice of the category from among the one or more voice conversion servers, and send the voice content to the selected voice conversion server.
本发明实施例中，当语音转换网关确定当前的Web消息中承载的内容为语音内容时，将会识别该语音内容的语言类别，如识别出语音内容为英文、日文、还是中文等，或者，当识别出语音内容为中文时，再进一步识别其为普通话还是方言，识别出后，为该语音内容选取能识别该语音内容的语音转换服务器，以便将语音内容准确识别为字符内容。In this embodiment of the present invention, when the voice conversion gateway determines that the content carried in the current Web message is voice content, it will recognize the language category of the voice content, such as identifying whether the voice content is English, Japanese, or Chinese, etc., or, When it is recognized that the voice content is Chinese, it is further identified whether it is Mandarin or a dialect, and after identification, a voice conversion server capable of recognizing the voice content is selected for the voice content, so as to accurately recognize the voice content as character content.
选取出语音转换服务器后，将所述语音内容向所选取的语音转换服务器发送。After the voice conversion server is selected, the voice content is sent to the selected voice conversion server.
步骤203，接收语音转换服务器反馈的语音转换结果，将所述语音转换结果封装为Web消息，将封装后的Web消息向所述互联网侧发送。Step 203: Receive the voice conversion result fed back by the voice conversion server, encapsulate the voice conversion result into a Web message, and send the encapsulated Web message to the Internet side.
本发明实施例中，当语音转换服务器将语音内容识别为字符信息后，将该字符信息发送给语音转换网关，语音转换网关将转换后的字符信息重新封装为Web消息，将封装后的Web消息向所述互联网侧发送。In the embodiment of the present invention, after the voice conversion server recognizes the voice content as character information, the character information is sent to the voice conversion gateway, and the voice conversion gateway re-encapsulates the converted character information into a Web message, and then re-encapsulates the encapsulated Web message. Send to the Internet side.
以下通过具体示例，进一步阐明本发明实施例的技术方案的实质。The following will further illustrate the essence of the technical solutions of the embodiments of the present invention through specific examples.
图3为本发明实施例二的语音信息转换方法的流程图，如图3所示，本示例的语音信息转换方法包括以下步骤：3 is a flowchart of a method for converting voice information according to Embodiment 2 of the present invention. As shown in FIG. 3 , the method for converting voice information in this example includes the following steps:
步骤301，Web应用录制语音，并将录制的语音内容封装为Web消息。Step 301, the web application records voice, and encapsulates the recorded voice content into a web message.
Web应用可以为安装于用户终端中的浏览器。语音内容可以通过设置于用户终端上的麦克输入。例如用户可以通过麦克输入语音信息，由Web应用采集该语音内容并封装。The web application may be a browser installed in the user terminal. The voice content can be input through the microphone provided on the user terminal. For example, a user can input voice information through a microphone, and the web application collects and encapsulates the voice content.
步骤302，Web应用将封装好的语音Web消息向Web应用网关(语音转换网关)发送。Step 302, the web application sends the encapsulated voice web message to the web application gateway (voice conversion gateway).
步骤303，Web应用网关对多接收的所有Web消息进行处理，分拣出语音Web消息，并提取Web消息中的语音内容，对该语音内容进行识别，识别出语音内容的语言类型，确定其是中文，还是其他种类的外语，或者是中文中的哪种方言。Step 303, the Web application gateway processes all the received Web messages, sorts out the voice Web messages, and extracts the voice content in the Web message, identifies the voice content, identifies the language type of the voice content, and determines whether it is Chinese, or other kinds of foreign languages, or which dialect in Chinese.
步骤304，Web应用网关将识别出语言类别的语音内容发送至对应的语音转换Web服务器(语音转换服务器)，对该语音内容进行识别，将其转换为字符内容。本发明实施例中，与Web应用网关连接的语音转换Web服务器有多个，且每个语音转换Web服务器由不同的运营商维护，能识别出不同语言类型的语音，本发明实施例通过对语音内容进行分类，提升了语音内容识别的准确性。Step 304, the web application gateway sends the speech content of the recognized language category to the corresponding speech conversion web server (voice conversion server), recognizes the speech content, and converts it into character content. In the embodiment of the present invention, there are multiple voice conversion web servers connected to the web application gateway, and each voice conversion web server is maintained by a different operator and can recognize voices of different language types. The content is classified to improve the accuracy of speech content recognition.
步骤305，语音转换Web服务器将语音内容转换为字符信息。Step 305, the speech conversion Web server converts the speech content into character information.
步骤306，语音转换Web服务器将识别出的字符信息发送给Web应用网关。Step 306, the speech conversion web server sends the recognized character information to the web application gateway.
步骤307，Web应用网关对所接收的字符信息重新封装，并根据之前语音Web消息的目的地址及源地址，重新封装给识别的字符信息为Web字符消息。Step 307, the Web application gateway re-encapsulates the received character information, and re-encapsulates the recognized character information into a Web character message according to the destination address and source address of the previous voice Web message.
步骤308，Web应用网关将该重新封装后的Web字符消息发送至对应的Web应用服务器(互联网侧)。Step 308, the web application gateway sends the repackaged web character message to the corresponding web application server (Internet side).
本发明实施例中，通过在接入网与互联网之间设置语音转换网关，对用户终端发往互联网的Web消息进行识别，确认Web消息中承载的信息为语音信息时，将其发送至语音转换服务器，经语音转换服务器识别为字符信息后，再由语音转换网关将转换后的字符信息重新封装为Web消息而发送至互联网侧。本发明实施例中，通过设置不同类型的语音转换服务器，能识别不同类型的语音，识别准确度高；由于语音转换网关与语音转换服务器之间的连接稳定度高而识别可靠，而语音转换服务器对用户不可见，这样，对于Web应用开发者而言，无需了解Web应用网关的地址信息；也无需了解Web语音转换服务器支持的语言种类，降低了开发者使用语音转换功能的门槛；同时有助于汇聚、动态组合业界优秀的语音转换资源。In the embodiment of the present invention, by setting a voice conversion gateway between the access network and the Internet, the Web message sent by the user terminal to the Internet is identified, and when it is confirmed that the information carried in the Web message is voice information, it is sent to the voice conversion After the server is recognized as character information by the speech conversion server, the speech conversion gateway repackages the converted character information into a Web message and sends it to the Internet side. In the embodiment of the present invention, by setting different types of voice conversion servers, different types of voices can be recognized, and the recognition accuracy is high; It is invisible to users, so that web application developers do not need to know the address information of the web application gateway, nor do they need to know the languages supported by the web speech conversion server, which lowers the threshold for developers to use the speech conversion function; It is used to aggregate and dynamically combine the industry's excellent voice conversion resources.
如图1所示，本发明实施例的语音转换网关设置于接入网与互联网之间，所述语音转换网关与一个以上的语音转换服务器连接；接入网可以为移动网络；图4为本发明实施例的语音转换网关的组成结构示意图，如图4所示，所述语音转换网关包括：第一接收单元40、第一确定单元41、获取单元42、选取单元43、第一发送单元44、第二接收单元45、封装单元46和第二发送单元47，其中：As shown in FIG. 1, the voice conversion gateway of the embodiment of the present invention is arranged between the access network and the Internet, and the voice conversion gateway is connected with more than one voice conversion server; the access network can be a mobile network; A schematic diagram of the composition and structure of the voice conversion gateway according to the embodiment of the invention, as shown in FIG. 4 , the voice conversion gateway includes: a first receiving unit 40 , a first determining unit 41 , an obtaining unit 42 , a selecting unit 43 , and a first sending unit 44 , the second receiving unit 45, the encapsulating unit 46 and the second sending unit 47, wherein:
第一接收单元40，用于接收所述接入网侧转发的Web消息；a first receiving unit 40, configured to receive the Web message forwarded by the access network side;
第一确定单元41，用于确定所述Web消息是否包含语音内容，包含语音内容时触发所述获取单元42；The first determination unit 41 is used to determine whether the Web message contains voice content, and triggers the acquisition unit 42 when the web message contains voice content;
获取单元42，用于获取所述语音内容中语音的类别；an acquiring unit 42, configured to acquire the category of the voice in the voice content;
选取单元43，用于根据所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器；A selection unit 43, configured to select a voice conversion server that can recognize the voice of the category from among the one or more voice conversion servers according to the category of the voice;
第一发送单元44，用于将所述语音内容向所选取的语音转换服务器发送；The first sending unit 44 is used to send the voice content to the selected voice conversion server;
第二接收单元45，用于接收语音转换服务器反馈的语音转换结果；The second receiving unit 45 is used for receiving the voice conversion result fed back by the voice conversion server;
封装单元46，用于将所述语音转换结果封装为Web消息；an encapsulation unit 46, for encapsulating the voice conversion result into a Web message;
第一发送单元47，用于将封装后的Web消息向所述互联网侧发送。The first sending unit 47 is configured to send the encapsulated Web message to the Internet side.
在图4所示的语音转换网关的基础上，本发明实施例的语音转换网关还包括：第三发送单元(图4中未示出)、第三接收单元(图4中未示出)、第二确定单元(图4中未示出)和第三确定单元(图4中未示出)，其中：On the basis of the voice conversion gateway shown in FIG. 4 , the voice conversion gateway of the embodiment of the present invention further includes: a third sending unit (not shown in FIG. 4 ), a third receiving unit (not shown in FIG. 4 ), The second determination unit (not shown in FIG. 4 ) and the third determination unit (not shown in FIG. 4 ), wherein:
第三发送单元，用于向所述一个以上的语音转换服务器发送状态查询消息；a third sending unit, configured to send a status query message to the one or more voice conversion servers;
第三接收单元，用于接收语音转换服务器的响应消息；The third receiving unit is used for receiving the response message of the voice conversion server;
第二确定单元，用于在所述第三接收单元在设定时长内接收到语音转换服务器的响应消息时，确定语音转换服务器正常运行；a second determining unit, configured to determine that the voice conversion server is running normally when the third receiving unit receives a response message from the voice conversion server within a set time period;
第三确定单元，用于在所述第三接收单元在设定时长内未接收到语音转换服务器的响应消息或在设定时长内未接收到语音转换服务器的响应消息超过设定次数时，确定语音转换服务器非正常运行。a third determining unit, configured to determine when the third receiving unit does not receive a response message from the voice conversion server within the set time period or does not receive a response message from the voice conversion server within the set time period for more than a set number of times The voice conversion server is not functioning properly.
本发明实施例，所述选取单元42，还用于根据语音转换服务器的当前状态及所述语音的类别在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。In this embodiment of the present invention, the selecting unit 42 is further configured to select a voice conversion server capable of recognizing the voice of the category from among the one or more voice conversion servers according to the current state of the voice conversion server and the type of the voice.
在图4所示的语音转换网关的基础上，本发明实施例的语音转换网关还包括：第四确定单元(图4中未示出)，用于在所述第二接收单元未接收到语音转换服务器反馈的语音转换结果时，确定语音转换网关故障，触发所述选取单元根据所述语音的类别重新在所述一个以上的语音转换服务器中选取能识别所述类别语音的语音转换服务器。On the basis of the voice conversion gateway shown in FIG. 4 , the voice conversion gateway according to the embodiment of the present invention further includes: a fourth determining unit (not shown in FIG. 4 ), configured to not receive voice at the second receiving unit When converting the voice conversion result fed back by the server, it is determined that the voice conversion gateway is faulty, and the selecting unit is triggered to re-select a voice conversion server that can recognize the voice of the category from among the one or more voice conversion servers according to the voice category.
本发明实施例中，所述语音转换结果为字符信息。In the embodiment of the present invention, the voice conversion result is character information.
本领域技术人员应当理解，图4中所示的语音转换网关中的各处理单元的实现功能可参照前述语音信息转换方法及其实施例的相关描述而理解。本领域技术人员应当理解，图4示的语音转换网关中各处理单元的功能可通过运行于处理器上的程序而实现，也可通过具体的逻辑电路而实现。Those skilled in the art should understand that the implementation function of each processing unit in the voice conversion gateway shown in FIG. 4 can be understood with reference to the foregoing description of the voice information conversion method and its embodiments. Those skilled in the art should understand that the functions of each processing unit in the voice conversion gateway shown in FIG. 4 can be implemented by a program running on the processor or by a specific logic circuit.
本发明实施例中，通过在接入网与互联网之间设置语音转换网关，对用户终端发往互联网的Web消息进行识别，确认Web消息中承载的信息为语音信息时，将其发送至语音转换服务器，经语音转换服务器识别为字符信息后，再由语音转换网关将转换后的字符信息重新封装为Web消息而发送至互联网侧。本发明实施例中，通过设置不同类型的语音转换服务器，能识别不同类型的语音，识别准确度高；由于语音转换网关与语音转换服务器之间的连接稳定度高而识别可靠，而语音转换服务器对用户不可见，这样，对于Web应用开发者而言，无需了解Web应用网关的地址信息；也无需了解Web语音转换服务器支持的语言种类，降低了开发者使用语音转换功能的门槛；同时有助于汇聚、动态组合业界优秀的语音转换资源。In the embodiment of the present invention, by setting a voice conversion gateway between the access network and the Internet, the Web message sent by the user terminal to the Internet is identified, and when it is confirmed that the information carried in the Web message is voice information, it is sent to the voice conversion After the server is recognized as character information by the speech conversion server, the speech conversion gateway repackages the converted character information into a Web message and sends it to the Internet side. In the embodiment of the present invention, by setting different types of voice conversion servers, different types of voices can be recognized, and the recognition accuracy is high; It is invisible to users, so that web application developers do not need to know the address information of the web application gateway, nor do they need to know the languages supported by the web speech conversion server, which lowers the threshold for developers to use the speech conversion function; It is used to aggregate and dynamically combine the industry's excellent voice conversion resources.
本发明实施例所记载的技术方案之间，在不冲突的情况下，可以任意组合。The technical solutions described in the embodiments of the present invention may be combined arbitrarily if there is no conflict.
在本发明所提供的几个实施例中，应该理解到，所揭露的方法、装置和电子设备，可以通过其它的方式实现。以上所描述的设备实施例仅仅是示意性的，例如，所述单元的划分，仅仅为一种逻辑功能划分，实际实现时可以有另外的划分方式，如：多个单元或组件可以结合，或可以集成到另一个系统，或一些特征可以忽略，或不执行。另外，所显示或讨论的各组成部分相互之间的耦合、或直接耦合、或通信连接可以是通过一些接口，设备或单元的间接耦合或通信连接，可以是电性的、机械的或其它形式的。In the several embodiments provided by the present invention, it should be understood that the disclosed method, apparatus and electronic device may be implemented in other manners. The device embodiments described above are only illustrative. For example, the division of the units is only a logical function division. In actual implementation, there may be other division methods. For example, multiple units or components may be combined, or Can be integrated into another system, or some features can be ignored, or not implemented. In addition, the coupling, or direct coupling, or communication connection between the components shown or discussed may be through some interfaces, and the indirect coupling or communication connection of devices or units may be electrical, mechanical or other forms. of.
上述作为分离部件说明的单元可以是、或也可以不是物理上分开的，作为单元显示的部件可以是、或也可以不是物理单元，即可以位于一个地方，也可以分布到多个网络单元上；可以根据实际的需要选择其中的部分或全部单元来实现本实施例方案的目的。The unit described above as a separate component may or may not be physically separated, and the component displayed as a unit may or may not be a physical unit, that is, it may be located in one place or distributed to multiple network units; Some or all of the units may be selected according to actual needs to achieve the purpose of the solution in this embodiment.
另外，在本发明各实施例中的各功能单元可以全部集成在一个处理单元中，也可以是各单元分别单独作为一个单元，也可以两个或两个以上单元集成在一个单元中；上述集成的单元既可以采用硬件的形式实现，也可以采用硬件加应用功能单元的形式实现。In addition, each functional unit in each embodiment of the present invention may all be integrated into one processing unit, or each unit may be separately used as a unit, or two or more units may be integrated into one unit; the above-mentioned integration The unit can be realized in the form of hardware, or can be realized in the form of hardware plus application function unit.
本领域普通技术人员可以理解：实现上述方法实施例的全部或部分步骤可以通过程序指令相关的硬件来完成，前述的程序可以存储于一计算机可读取存储介质中，该程序在执行时，执行包括上述方法实施例的步骤；而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。Those of ordinary skill in the art can understand that all or part of the steps of implementing the above method embodiments can be completed by program instructions related to hardware, the aforementioned program can be stored in a computer-readable storage medium, and when the program is executed, execute Including the steps of the above-mentioned method embodiment; and the aforementioned storage medium includes: a mobile storage device, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and other various A medium on which program code can be stored.
或者，本发明实施例上述集成的单元如果以应用功能模块的形式实现并作为独立的产品销售或使用时，也可以存储在一个计算机可读取存储介质中。基于这样的理解，本发明实施例的技术方案本质上或者说对现有技术做出贡献的部分可以以应用产品的形式体现出来，该计算机应用产品存储在一个存储介质中，包括若干指令用以使得一台计算机设备(可以是个人计算机、服务器、或者网络设备等)执行本发明各个实施例所述方法的全部或部分。而前述的存储介质包括：移动存储设备、只读存储器(ROM，Read-Only Memory)、随机存取存储器(RAM，Random Access Memory)、磁碟或者光盘等各种可以存储程序代码的介质。Alternatively, if the above-mentioned integrated unit in the embodiment of the present invention is implemented in the form of an application function module and sold or used as an independent product, it may also be stored in a computer-readable storage medium. Based on this understanding, the technical solutions of the embodiments of the present invention essentially or the parts that make contributions to the prior art can be embodied in the form of application products, and the computer application products are stored in a storage medium and include several instructions for A computer device (which may be a personal computer, a server, or a network device, etc.) is caused to execute all or part of the methods described in the various embodiments of the present invention. The aforementioned storage medium includes: a removable storage device, a read-only memory (ROM, Read-Only Memory), a random access memory (RAM, Random Access Memory), a magnetic disk or an optical disk and other media that can store program codes.
本发明的保护范围并不局限于此，熟悉本技术领域的技术人员在本发明揭露的技术范围内，可轻易想到变化或替换，都应涵盖在本发明的保护范围之内。The protection scope of the present invention is not limited to this, and those skilled in the art can easily think of changes or substitutions within the technical scope disclosed in the present invention, which should all be included within the protection scope of the present invention.
Claims (11)
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510002321.XA CN105827878B (en) | 2015-01-04 | 2015-01-04 | Voice messaging conversion method and voice transfer gateway |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510002321.XA CN105827878B (en) | 2015-01-04 | 2015-01-04 | Voice messaging conversion method and voice transfer gateway |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105827878A CN105827878A (en) | 2016-08-03 |
| CN105827878B true CN105827878B (en) | 2019-06-25 |
Family
ID=56513320
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510002321.XA Active CN105827878B (en) | 2015-01-04 | 2015-01-04 | Voice messaging conversion method and voice transfer gateway |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105827878B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1311469A (en) * | 2000-03-03 | 2001-09-05 | 松下电器产业株式会社 | Interface system, interface connection method and information terminal |
| KR20030037514A (en) * | 2001-11-06 | 2003-05-14 | 최중인 | Operating system for life information using voice-web and operating method thereof |
| EP1643739A1 (en) * | 2004-10-04 | 2006-04-05 | Alcatel | Method for exchanging messages between end-user and textmessage server |
| CN101339725A (en) * | 2008-08-07 | 2009-01-07 | 北京中星微电子有限公司 | Introduction system, device and method of exhibit |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN103839549A (en) * | 2012-11-22 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Voice instruction control method and system |
Family Cites Families (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7738833B2 (en) * | 2004-06-30 | 2010-06-15 | Glenayre Electronics, Inc. | Provision of messaging services from a video messaging system for video compatible and non-video compatible equipment |
| EP3091535B1 (en) * | 2009-12-23 | 2023-10-11 | Google LLC | Multi-modal input on an electronic device |
-
2015
- 2015-01-04 CN CN201510002321.XA patent/CN105827878B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1311469A (en) * | 2000-03-03 | 2001-09-05 | 松下电器产业株式会社 | Interface system, interface connection method and information terminal |
| KR20030037514A (en) * | 2001-11-06 | 2003-05-14 | 최중인 | Operating system for life information using voice-web and operating method thereof |
| EP1643739A1 (en) * | 2004-10-04 | 2006-04-05 | Alcatel | Method for exchanging messages between end-user and textmessage server |
| CN101339725A (en) * | 2008-08-07 | 2009-01-07 | 北京中星微电子有限公司 | Introduction system, device and method of exhibit |
| CN103188408A (en) * | 2011-12-29 | 2013-07-03 | 上海博泰悦臻电子设备制造有限公司 | Voice auto-answer cloud server, voice auto-answer system and voice auto-answer method |
| CN103839549A (en) * | 2012-11-22 | 2014-06-04 | 腾讯科技（深圳）有限公司 | Voice instruction control method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105827878A (en) | 2016-08-03 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| TW202034185A (en) | Computing service implementation scheme based on structured query language statements | |
| WO2019019645A1 (en) | Method and apparatus for executing information pushing task, and computer device and storage medium | |
| CN112291423B (en) | Communication call intelligent response processing method and device, electronic equipment and storage medium | |
| WO2020124724A1 (en) | Resource description file processing, and page resource obtaining method and device | |
| CN101257461A (en) | Category-based content filtering method and device | |
| CN111382051B (en) | API automatic test method and test device | |
| CN106412296A (en) | Terminal device control method and apparatus | |
| CN108509059B (en) | Information processing method, electronic equipment and computer storage medium | |
| CN112422414B (en) | Session message processing method, device and computer readable storage medium | |
| CN110321129A (en) | Business based on developing instrument executes method, apparatus and computer equipment | |
| CN114330280A (en) | Sensitive data identification method and device | |
| CN107623620B (en) | Processing method of random interaction data, network server and intelligent dialogue system | |
| CN105827878B (en) | Voice messaging conversion method and voice transfer gateway | |
| KR102713221B1 (en) | Customized call center operation system through voice analysis-based consultation type classification | |
| US20220294874A1 (en) | Method for reporting asynchronous data, electronic device and storage medium | |
| CN114911753B (en) | A method, device, electronic device and storage medium for generating a presentation document | |
| CN113656731B (en) | Advertisement page processing method and device, electronic equipment and storage medium | |
| CN116150415A (en) | User portrait construction method, device and electronic equipment | |
| CN107577396A (en) | A rendering method and device for an information dialog box in a session window | |
| CN114168652A (en) | A smart contract interaction method, device, device and storage medium | |
| CN113852835A (en) | Live audio processing method, device, electronic device and storage medium | |
| CN112965707A (en) | Web multi-application single page generation method, system, computer device and medium | |
| CN111985186A (en) | Dictionary entry conversion method, API gateway system, equipment and storage medium | |
| CN110995940A (en) | Harassment visitor identification method and device, electronic equipment and medium | |
| CN119690367B (en) | Object sharing method, object display method, device, electronic device and medium |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |