演讲中的关键词发现 [英] Keyword Spotting in Speech

问题描述

是否有人知道免费提供的关键字发现系统，并且可能提供 API ??

Is anyone aware of a Keyword Spotting System that is freely available, and possibly providing APIs ??

CMU Sphinx 4 和 MS Speech API 是语音识别引擎，不能用于 KWS.

CMU Sphinx 4 and MS Speech API are speech recognition engines, and cannot be used for KWS.

SRI 有一个关键字识别系统，但没有下载链接，甚至没有用于评估的链接.(我什至在任何地方都找不到联系他们的软件的链接)

SRI has a keyword spotting system, but no download links, not even for evaluation. (I even couldn't find anywhere a link to contact them for their software)

我在这里找到了一个，但它是一个演示版且有限.

I found one here but it's a demo and limited.

推荐答案

CMUSphinx 在 Pocketsphinx 引擎中实现了关键字定位，详见常见问题解答.

CMUSphinx implements keyword spotting in pocketsphinx engine, see for details the FAQ entry.

要识别单个关键短语，您可以在关键短语搜索"模式下运行解码器.

To recognize a single keyphrase you can run decoder in "keyphrase search" mode.

从命令行尝试:

pocketsphinx_continuous -infile file.wav -keyphrase "oh mighty computer" -kws_threshold 1e-20

来自代码:

 ps_set_keyphrase(ps, "keyphrase_search", "oh mighty computer");
 ps_set_search(ps, "keyphrase_search);
 ps_start_utt();
 /* process data */

您还可以在我们的资源中找到 Python 和 Android/Java 的示例.Python 代码如下所示，完整示例 此处:

You can also find examples for Python and Android/Java in our sources. Python code looks like this, full example here:

# Process audio chunk by chunk. On keyphrase detected perform action and restart search
decoder = Decoder(config)
decoder.start_utt()
while True:
    buf = stream.read(1024)
    if buf:
         decoder.process_raw(buf, False, False)
    else:
         break
    if decoder.hyp() != None:
        print ([(seg.word, seg.prob, seg.start_frame, seg.end_frame) for seg in decoder.seg()])
        print ("Detected keyphrase, restarting search")
        decoder.end_utt()
        decoder.start_utt()

必须针对测试数据上的每个关键短语调整阈值，以正确平衡漏检和误报.您可以尝试使用 1e-5 到 1e-50 之类的值.

Threshold must be tuned for every keyphrase on a test data to get the right balance missed detections and false alarms. You can try values like 1e-5 to 1e-50.

为了获得最佳准确性，最好使用 3-4 个音节的关键短语.太短的短语很容易混淆.

For the best accuracy it is better to have keyphrase with 3-4 syllables. Too short phrases are easily confused.

您也可以搜索多个关键短语，创建一个文件keyphrase.list，如下所示:

You can also search for multiple keyphrase, create a file keyphrase.list like this:

  oh mighty computer /1e-40/
  hello world /1e-30/
  other_phrase /other_phrase_threshold/

并在带有 -kws 配置选项的解码器中使用它.

And use it in decoder with -kws configuration option.

  pocketsphinx_continuous -inmic yes -kws keyphrase_list

此功能尚未在 sphinx4 解码器中实现.

This feature is not yet implemented in sphinx4 decoder.

这篇关于演讲中的关键词发现的文章就介绍到这了，希望我们推荐的答案对大家有所帮助，也希望大家多多支持IT屋！