blocks|key|1210496|text|我认为你必须直接从手机的麦克风中捕获音频，并将其流式传输到你自己的识别服务。Google+recognition+API旨在启动自己的识别对话框，并向您返回结果。如果您希望在没有UI的情况下连续识别，则必须自己构建该功能。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1210497|entityMap^0|0^^$0|@$1|2|3|4|5|6|7|D|8|@]|9|@]|A|$]]|$1|B|3|-4|5|6|7|E|8|@]|9|@]|A|$]]]|C|$]]

I think you would have to capture audio directly from the phone's microphone and stream it to your own recognition service. The Google recognition APIs are built as an Intent that launches their own Recognition dialog and gives you back results. If you want continuous recognition without a UI, you'll have to build that functionality yourself.

blocks|key|1210573|text|CMUSphinx最近在安卓平台上实现了持续监听。您可以在wiki+page上找到演示|type|unstyled|depth|inlineStyleRanges|entityRanges|offset|length|data|1210574|您可以配置一个或多个关键字来收听，默认的关键字是“哦，强大的计算机”。您还可以配置检测阈值。目前支持的语言是美国英语和少数其他语言(法语、西班牙语、俄语等)。您可以针对您的语言训练自己的模型。|1210575|监听很简单，你创建一个识别器，然后添加关键字识别搜索：|1210576|++++recognizer+=+defaultSetup()
++++++++++++.setAcousticModel(new+File(modelsDir,+"hmm/en-us-semi"))
++++++++++++.setDictionary(new+File(modelsDir,+"lm/cmu07a.dic"))
++++++++++++.setKeywordThreshold(1e-5f)
++++++++++++.getRecognizer();

++++recognizer.addListener(this);
++++recognizer.addKeywordSearch(KWS_SEARCH_NAME,+KEYPHRASE);
++++switchSearch(KWS_SEARCH_NAME);|code-block|syntax|javascript|1210577|并定义监听程序：|1210578|@Override
public+void+onPartialResult(Hypothesis+hypothesis)+{
++++String+text+=+hypothesis.getHypstr();
++++if+(text.equals(KEYPHRASE))
++++++//++do+something
}|1210579|您可以在文件系统上指定命令文件路径，而不是单个关键短语：|1210580|++++recognizer.addKeywordSearch(KWS_SEARCH,+new+File(assetsDir,
++++++++++++"commands.lst").toString());|1210581|哪个命令文件commands.lst每行包含一个命令：|style|CODE|1210582|++oh+might+computer
++ok+google
++hello+dude|1210583|要将此文件放到文件系统中，您可以将其放入assets中，并在应用程序启动时运行syncAssets。|1210584|entityMap|0|LINK|mutability|MUTABLE|url|http://cmusphinx.sourceforge.net/wiki/tutorialandroid^0|T|9|0|0|0|0|0|0|0|0|0|6|C|0|0|0^^$0|@$1|2|3|4|5|6|7|1A|8|@]|9|@$A|1B|B|1C|1|1D]]|C|$]]|$1|D|3|E|5|6|7|1E|8|@]|9|@]|C|$]]|$1|F|3|G|5|6|7|1F|8|@]|9|@]|C|$]]|$1|H|3|I|5|J|7|1G|8|@]|9|@]|C|$K|L]]|$1|M|3|N|5|6|7|1H|8|@]|9|@]|C|$]]|$1|O|3|P|5|J|7|1I|8|@]|9|@]|C|$K|L]]|$1|Q|3|R|5|6|7|1J|8|@]|9|@]|C|$]]|$1|S|3|T|5|J|7|1K|8|@]|9|@]|C|$K|L]]|$1|U|3|V|5|6|7|1L|8|@$A|1M|B|1N|W|X]]|9|@]|C|$]]|$1|Y|3|Z|5|J|7|1O|8|@]|9|@]|C|$K|L]]|$1|10|3|11|5|6|7|1P|8|@]|9|@]|C|$]]|$1|12|3|-4|5|6|7|1Q|8|@]|9|@]|C|$]]]|13|$14|$5|15|16|17|C|$18|19]]]]

CMUSphinx has recently implemented continuous listening on Android platform. You can find the demo on the <a href="http://cmusphinx.sourceforge.net/wiki/tutorialandroid" rel="noreferrer">wiki page</a> 

You can configure one or multiple keywords to listen to, the default keyword is "oh mighty computer". You also can configure the detection threshold. Currently supported languages are US English and few others (French, Spanish, Russian, etc). You can train your own model for your language.

Listening is simple, you create a recognizer and just add keyword spotting search:

<pre><code> recognizer = defaultSetup()
 .setAcousticModel(new File(modelsDir, "hmm/en-us-semi"))
 .setDictionary(new File(modelsDir, "lm/cmu07a.dic"))
 .setKeywordThreshold(1e-5f)
 .getRecognizer();

 recognizer.addListener(this);
 recognizer.addKeywordSearch(KWS_SEARCH_NAME, KEYPHRASE);
 switchSearch(KWS_SEARCH_NAME);
</code></pre>

and define a listener:

<pre><code>@Override
public void onPartialResult(Hypothesis hypothesis) {
 String text = hypothesis.getHypstr();
 if (text.equals(KEYPHRASE))
 // do something
}
</code></pre>

Instead of single key phrase you can specify a commands file path on a filesystem:

<pre><code> recognizer.addKeywordSearch(KWS_SEARCH, new File(assetsDir,
 "commands.lst").toString());
</code></pre>

Which commands file <code>commands.lst</code> containing commands one per line:

<pre><code> oh might computer
 ok google
 hello dude
</code></pre>

To put this file on filesystem you can put it in assets and run syncAssets on application start.

blocks|key|1211225|text|这里有另一种方法(如果你计划使用Phonegap/Cordova)。|type|unstyled|depth|inlineStyleRanges|entityRanges|data|1211226|https://stackoverflow.com/a/39695412/3603128|offset|length|1211227|1)它不断地监听。|1211228|2)不在屏幕上显示(占用)。|1211229|entityMap|0|LINK|mutability|MUTABLE|url^0|0|0|18|0|0|0|0^^$0|@$1|2|3|4|5|6|7|Q|8|@]|9|@]|A|$]]|$1|B|3|C|5|6|7|R|8|@]|9|@$D|S|E|T|1|U]]|A|$]]|$1|F|3|G|5|6|7|V|8|@]|9|@]|A|$]]|$1|H|3|I|5|6|7|W|8|@]|9|@]|A|$]]|$1|J|3|-4|5|6|7|X|8|@]|9|@]|A|$]]]|K|$L|$5|M|N|O|A|$P|C]]]]

Here is another way (if you are planning to use Phonegap/Cordova).

<a href="https://stackoverflow.com/a/39695412/3603128">https://stackoverflow.com/a/39695412/3603128</a>

1) It listens continuously.

2) Does not display (occupy) on screen.

I am looking at doing speech recognition in android. The program needs to have continuous speech recognition. The library only needs to be about 10 words. I have considered using Googles api, but I don't think it will work. (I cannot have anything covering the screen). I have been looking into other ways but nothing seems like it will work. Is it possible to use java's speech recognition library, or is there any other way of going about this?

In summary 
1. Need continuous speech input 
2. 10 words at max 
3. can train if necessary 
4. overview of program - display screen, wait for voice input or touch input, update screen repeat 
5. cannot cover what is being displayed on the screen 

Any help would be appreciated. 
Thanks in advance

Continuous Speech Recognition Android

语音识别

文件系统

Cordova

我正在考虑在android上做语音识别。该程序需要有连续的语音识别。这个库只需要10个单词左右。我考虑过使用Googles api，但我认为它不会起作用。(我不能让任何东西覆盖屏幕)。我一直在寻找其他方法，但似乎没有什么能行得通。有没有可能使用java的语音识别库，或者有没有其他方法呢？总而言之需要连续的语音input...

问连续语音识别Android
EN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问连续语音识别AndroidEN

社区

活动

资源

关于

腾讯云开发者

热门产品

热门推荐

更多推荐

问连续语音识别Android
EN