简体繁体 English

关于Android语音识别

[英]About Android Speech recognition

原文 2015-10-18 08:28:09 0 1 android/ speech-recognition/ speech-to-text

I use RecognizerIntent and implement the RecognitionListener and implement all of its call back methodsas to do voice commands. 我使用RecognizerIntent并实现了RecognitionListener并实现了其所有回调方法来执行语音命令。 And I try to adjust the parameters EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS,EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS and EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS to decrease the listen time but it seems not work. 我尝试调整参数EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS，EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS和EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS以减少侦听时间，但似乎不起作用。 How can I do ? 我能怎么做？

Another question is about the recognition speed. 另一个问题是关于识别速度。 I just have five voice commands in my system. 我的系统中只有五个语音命令。 But I need to pass and wait for the recognition result every time. 但是我每次都需要通过并等待识别结果。 Can I preprocess something or other methods to accelerate the recognition speed? 我可以预处理某些东西或其他方法来加快识别速度吗？

1 个解决方案

For the task you described it make sense to use closed-dictionary ASR system, such as pocketsphinx-android . 对于您描述的任务，使用封闭字典式ASR系统是有意义的，例如pocketsphinx-android 。 You will be able to fine-tune pre- and post-speech wait intervals as well as speed-up the decoding as the recognition happens on-board rather than going back and forth to the cloud. 您将能够微调语音前后的等待时间间隔，并加快识别速度，因为识别是在板上进行的，而不是往返于云端。