I am trying to implement speech recognition. I keep getting the error:
ERROR_NO_MATCH - No recognition result matched - 7
I can't find anything that explain what does this means.
What does "No recognition result matched" mean?
you need to enable partial results first, and to call UNSTABLE_TEXT
// When creating the intent, set the partial flag to true
intent.putExtra(RecognizerIntent.EXTRA_PARTIAL_RESULTS,true);
use the partialResults returned in onPartialResults(). In the returned bundle "SpeechRecognizer.RESULTS_RECOGNITION" has all the terms minus the last term and "android.speech.extra.UNSTABLE_TEXT" has the last missing recognized term.
#Override
public void onPartialResults(Bundle partialResults) {
ArrayList<String> data =
partialResults.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
ArrayList<String> unstableData =
partialResults.getStringArrayList("android.speech.extra.UNSTABLE_TEXT");
mResult = data.get(0) + unstableData.get(0);
}
you can follow below link for better understanding -
speech recognition
No recognition result matched. Meaning superbox s3 cannot us voice command message no recognition result matched . Come up on screen
Related
I've been developing a demo for speech recognition and ran into an issue. Could anyone help me? I called startRecognizing interface and received an onError callback (Error 11203, subError 3005, errorMessage: service unavailable), see screenshot:
I followed the document , My code:
// Create an Intent to set parameters.
val mSpeechRecognizerIntent = Intent(MLAsrConstants.ACTION_HMS_ASR_SPEECH)
// Use Intent for recognition parameter settings.
mSpeechRecognizerIntent
// Set the language that can be recognized to English. If this parameter is not set, English is recognized by default. Example: "zh-CN": Chinese; "en-US": English; "fr-FR": French; "es-ES": Spanish; "de-DE": German; "it-IT": Italian; "ar": Arabic; "th_TH": Thai; "ms_MY": Malay; "fil_PH": Filipino.
.putExtra(MLAsrConstants.LANGUAGE, "en-US") // Set to return the recognition result along with the speech. If you ignore the setting, this mode is used by default. Options are as follows:
// MLAsrConstants.FEATURE_WORDFLUX: Recognizes and returns texts through onRecognizingResults.
// MLAsrConstants.FEATURE_ALLINONE: After the recognition is complete, texts are returned through onResults.
.putExtra(MLAsrConstants.FEATURE, MLAsrConstants.FEATURE_WORDFLUX) // Set the application scenario. MLAsrConstants.SCENES_SHOPPING indicates shopping, which is supported only for Chinese. Under this scenario, recognition for the name of Huawei products has been optimized.
.putExtra(MLAsrConstants.SCENES, MLAsrConstants.SCENES_SHOPPING)
// Start speech recognition.
mSpeechRecognizer.startRecognizing(mSpeechRecognizerIntent)
Do you have any idea why this could be happening? Please help, thanks!!
You need to change "en-US" to "zh-CN".
Or comment out ".putExtra(SCENES, SCENES_SHOPPING)":
I have a working application that I would like to add voice commands. The current application transmits data back and forth over bluetooth on a periodic (timer) basis. The user can press Buttons and NumberPickers to modify the data being sent over bluetooth. There is also data received from the bluetooth link, and displayed in textViews. This application is currently working correctly.
What I would like to do is add voice command capability, so that the user has either the choice of pressing the Buttons/NumberPickers, or can change the values with only voice commands.
I have tested some of the Speech-to-Text examples that can be found on various websites. I have succesfully tested an App that uses RecognizerIntent. Upon a button press, a dialog pops up and you can speak words or phrases, and it correctly displays the result on the screen.
So, I think that I am close, but I'm not really sure how I can combine the Speech-to-Text with my current Bluetooth App. I don't want the user to have to press a button, I just want the App to be constantly listening. Also, I don't want the pop-up Voice Dialog on the screen.
My hardware is a Samsung tablet running Android 4.1.
I am relatively new to Android programming, so any advice (no matter how basic) is appreciated. Thanks.
To prevent the pop-up Voice Dialog on the screen, you can use the ACTION_RECOGNIZE_SPEECH intent:
private static int SR_CODE = 123;
/**
* Initializes the speech recognizer and starts listening to the user input
*/
private void listen() {
Intent intent = new Intent(RecognizerIntent.ACTION_RECOGNIZE_SPEECH);
//Specify language
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE, Locale.ENGLISH)
// Specify language model
intent.putExtra(RecognizerIntent.EXTRA_LANGUAGE_MODEL, RecognizerIntent.LANGUAGE_MODEL_FREE_FORM);
// Specify how many results to receive
intent.putExtra(RecognizerIntent.EXTRA_MAX_RESULTS, 5);
// Start listening
startActivityForResult(intent, SR_CODE);
}
#Override
protected void onActivityResult(int requestCode, int resultCode, Intent data) {
if (requestCode == SR_CODE && resultCode == RESULT_OK) {
if(data!=null) {
//Retrieves the best list SR result
ArrayList<String> nBestList = data.getStringArrayListExtra(RecognizerIntent.EXTRA_RESULTS);
String bestResult = nBestList.get(0);
Toast.makeText(getApplicationContext(), bestResult, Toast.LENGTH_LONG).show;
}else {
//Reports error in recognition error in log
Log.e(LOGTAG, "Recognition was not successful");
}
}
Concerning the other issue, " I don't want the user to have to press a button, I just want the App to be constantly listening":
I'll recommend using CMUSphinx to recognize speech continuously. To achieve continuous speech recognition using google speech recognition api, you might have to resort to a loop in a background service which will take too much resources and drains the device battery.
On the other hand, Pocketsphinx works really great. It's fast enough to spot a key phrase and recognize voice commands behind the lock screen without users touching their device. And it does all this offline.
You can try the demo.
If you really want to use google's api as I've demonstrated above, see this
I have written a small app on Android using python (Qpython3) with voice synthesizer & voice recognition.
droid = sl4a.Android()
droid.ttsSpeak("hello")
v = str(droid.recognizeSpeech()
droid.ttsSpeak(v)
The synthesized voice is then saying a first "hello", and then once again it says "hello" as if it was auto-recording the first string - and I interpret this as ttsSpeak non blocking.
Is there a way to wait for the completion of the voice synthesizer before starting the voice recognizer ?
found in In Love with a Droid
need to wait via ttsIsSpeaking which returns a tuple, the boolean is the second element of the tuple is set false when the current speak has completed.
I'm starting my final year project. I will do an android application, which will take commands from the user, and then process the input in order to show results.
My question is, what ways can I use to process the input( what I mean by input here is the data or text after transferring speech to text)?
I have found some ways to do that like matching the input with data stored already(template matching), but Im looking for something more better and smarter that that (and if there are any suggested references).
Thanks
I would suggest you start with a very basic and clearly defined set of keyword rules of your own:
#Override
public void onResults(final Bundle results) {
final ArrayList<String> heardVoice = results.getStringArrayList(SpeechRecognizer.RESULTS_RECOGNITION);
if(heardVoice != null && !heardVoice.isEmpty()) {
for(String result: heardVoice){
if(result.contains("bluetooth")){
if(result.contains("on")){
// turn on bluetooth
break;
} else if(result.contains("off")){
// turn off bluetooth
break;
}
}
}
}
}
Once you've understood these basic keyword parameters, you can then look to using a Natural Language Processing (NLP) model and the performance of your code.
There are many examples out there, but the Apache OpenNLP is a good place to start, with comprehensive documentation.
I am trying to add a few commands to android default voicedialer app. It has commands like Open, dial, call, redial etc, I want to include lets say 'Find' to it. I have downloaded the source code from here and compiled it in Eclipse. the application sets up Grammar for arguments of these commands like it stores the names and phone numbers of the persons in contact list to generate intents when their names are recognized for CALL JOHN voice command. For CALL in this command it is just comparing the first word of resulting recognized string to "CALL".
I added "FIND" as an extra else if condition in the onRecognitionSuccess() function as shown below:
public class CommandRecognizerEngine extends RecognizerEngine
{
............
protected void onRecognitionSuccess(RecognizerClient recognizerClient) throws InterruptedException
{
.....................
if ("DIAL".equalsIgnoreCase(commands[0]))
{
Uri uri = Uri.fromParts("tel", commands[1], null);
String num = formatNumber(commands[1]);
if (num != null)
{
addCallIntent(intents, uri, literal.split(" ")[0].trim() + " " + num, "", 0);
}
}
................
else if ("FIND".equalsIgnoreCase(commands[0]))
{
if (Config.LOGD)
Log.d(TAG, "FIND detected...");
}
}//end onRecognitionSuccess
}//end CommandRecognizerEngine
but my app can't recognize it. Does anyone know how does recognizer detects commands like OPEN or CALL etc or refer me to appropriate documentation?
Thanks.
As it has been over a year, I doubt you need this answer anymore. However, some other people might find this through Google, as I did.
Right now, the best way to apply grammars to speech recognition on Android is to set the number of results higher, and then filter the results based on your grammar. It is not perfect, as the word recognized may not have passed a threshold to be included in the list, but it does greatly improve the accuracy of all speech recognition applications where the types of things you can say are somewhat limited.