Home | History | Annotate | Download | only in speech
      1 /*
      2  * Copyright (C) 2008 The Android Open Source Project
      3  *
      4  * Licensed under the Apache License, Version 2.0 (the "License");
      5  * you may not use this file except in compliance with the License.
      6  * You may obtain a copy of the License at
      7  *
      8  *      http://www.apache.org/licenses/LICENSE-2.0
      9  *
     10  * Unless required by applicable law or agreed to in writing, software
     11  * distributed under the License is distributed on an "AS IS" BASIS,
     12  * WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
     13  * See the License for the specific language governing permissions and
     14  * limitations under the License.
     15  */
     16 
     17 package android.speech;
     18 
     19 import java.util.ArrayList;
     20 
     21 import android.app.Activity;
     22 import android.content.ActivityNotFoundException;
     23 import android.content.BroadcastReceiver;
     24 import android.content.ComponentName;
     25 import android.content.Context;
     26 import android.content.Intent;
     27 import android.content.pm.PackageManager;
     28 import android.content.pm.ResolveInfo;
     29 import android.os.Bundle;
     30 
     31 /**
     32  * Constants for supporting speech recognition through starting an {@link Intent}
     33  */
     34 public class RecognizerIntent {
     35     /**
     36      * The extra key used in an intent to the speech recognizer for voice search. Not
     37      * generally to be used by developers. The system search dialog uses this, for example,
     38      * to set a calling package for identification by a voice search API. If this extra
     39      * is set by anyone but the system process, it should be overridden by the voice search
     40      * implementation.
     41      */
     42     public final static String EXTRA_CALLING_PACKAGE = "calling_package";
     43 
     44     private RecognizerIntent() {
     45         // Not for instantiating.
     46     }
     47 
     48     /**
     49      * Starts an activity that will prompt the user for speech and send it through a
     50      * speech recognizer.  The results will be returned via activity results (in
     51      * {@link Activity#onActivityResult}, if you start the intent using
     52      * {@link Activity#startActivityForResult(Intent, int)}), or forwarded via a PendingIntent
     53      * if one is provided.
     54      *
     55      * <p>Starting this intent with just {@link Activity#startActivity(Intent)} is not supported.
     56      * You must either use {@link Activity#startActivityForResult(Intent, int)}, or provide a
     57      * PendingIntent, to receive recognition results.
     58      *
     59      * <p>Required extras:
     60      * <ul>
     61      *   <li>{@link #EXTRA_LANGUAGE_MODEL}
     62      * </ul>
     63      *
     64      * <p>Optional extras:
     65      * <ul>
     66      *   <li>{@link #EXTRA_PROMPT}
     67      *   <li>{@link #EXTRA_LANGUAGE}
     68      *   <li>{@link #EXTRA_MAX_RESULTS}
     69      *   <li>{@link #EXTRA_RESULTS_PENDINGINTENT}
     70      *   <li>{@link #EXTRA_RESULTS_PENDINGINTENT_BUNDLE}
     71      * </ul>
     72      *
     73      * <p> Result extras (returned in the result, not to be specified in the request):
     74      * <ul>
     75      *   <li>{@link #EXTRA_RESULTS}
     76      * </ul>
     77      *
     78      * <p>NOTE: There may not be any applications installed to handle this action, so you should
     79      * make sure to catch {@link ActivityNotFoundException}.
     80      */
     81     public static final String ACTION_RECOGNIZE_SPEECH = "android.speech.action.RECOGNIZE_SPEECH";
     82 
     83     /**
     84      * Starts an activity that will prompt the user for speech, send it through a
     85      * speech recognizer, and either display a web search result or trigger
     86      * another type of action based on the user's speech.
     87      *
     88      * <p>If you want to avoid triggering any type of action besides web search, you can use
     89      * the {@link #EXTRA_WEB_SEARCH_ONLY} extra.
     90      *
     91      * <p>Required extras:
     92      * <ul>
     93      *   <li>{@link #EXTRA_LANGUAGE_MODEL}
     94      * </ul>
     95      *
     96      * <p>Optional extras:
     97      * <ul>
     98      *   <li>{@link #EXTRA_PROMPT}
     99      *   <li>{@link #EXTRA_LANGUAGE}
    100      *   <li>{@link #EXTRA_MAX_RESULTS}
    101      *   <li>{@link #EXTRA_PARTIAL_RESULTS}
    102      *   <li>{@link #EXTRA_WEB_SEARCH_ONLY}
    103      *   <li>{@link #EXTRA_ORIGIN}
    104      * </ul>
    105      *
    106      * <p> Result extras (returned in the result, not to be specified in the request):
    107      * <ul>
    108      *   <li>{@link #EXTRA_RESULTS}
    109      *   <li>{@link #EXTRA_CONFIDENCE_SCORES} (optional)
    110      * </ul>
    111      *
    112      * <p>NOTE: There may not be any applications installed to handle this action, so you should
    113      * make sure to catch {@link ActivityNotFoundException}.
    114      */
    115     public static final String ACTION_WEB_SEARCH = "android.speech.action.WEB_SEARCH";
    116 
    117     /**
    118      * The minimum length of an utterance. We will not stop recording before this amount of time.
    119      *
    120      * Note that it is extremely rare you'd want to specify this value in an intent. If you don't
    121      * have a very good reason to change these, you should leave them as they are. Note also that
    122      * certain values may cause undesired or unexpected results - use judiciously! Additionally,
    123      * depending on the recognizer implementation, these values may have no effect.
    124      */
    125     public static final String EXTRA_SPEECH_INPUT_MINIMUM_LENGTH_MILLIS =
    126             "android.speech.extras.SPEECH_INPUT_MINIMUM_LENGTH_MILLIS";
    127 
    128     /**
    129      * The amount of time that it should take after we stop hearing speech to consider the input
    130      * complete.
    131      *
    132      * Note that it is extremely rare you'd want to specify this value in an intent. If
    133      * you don't have a very good reason to change these, you should leave them as they are. Note
    134      * also that certain values may cause undesired or unexpected results - use judiciously!
    135      * Additionally, depending on the recognizer implementation, these values may have no effect.
    136      */
    137     public static final String EXTRA_SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS =
    138             "android.speech.extras.SPEECH_INPUT_COMPLETE_SILENCE_LENGTH_MILLIS";
    139 
    140     /**
    141      * The amount of time that it should take after we stop hearing speech to consider the input
    142      * possibly complete. This is used to prevent the endpointer cutting off during very short
    143      * mid-speech pauses.
    144      *
    145      * Note that it is extremely rare you'd want to specify this value in an intent. If
    146      * you don't have a very good reason to change these, you should leave them as they are. Note
    147      * also that certain values may cause undesired or unexpected results - use judiciously!
    148      * Additionally, depending on the recognizer implementation, these values may have no effect.
    149      */
    150     public static final String EXTRA_SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS =
    151             "android.speech.extras.SPEECH_INPUT_POSSIBLY_COMPLETE_SILENCE_LENGTH_MILLIS";
    152 
    153     /**
    154      * Informs the recognizer which speech model to prefer when performing
    155      * {@link #ACTION_RECOGNIZE_SPEECH}. The recognizer uses this
    156      * information to fine tune the results. This extra is required. Activities implementing
    157      * {@link #ACTION_RECOGNIZE_SPEECH} may interpret the values as they see fit.
    158      *
    159      *  @see #LANGUAGE_MODEL_FREE_FORM
    160      *  @see #LANGUAGE_MODEL_WEB_SEARCH
    161      */
    162     public static final String EXTRA_LANGUAGE_MODEL = "android.speech.extra.LANGUAGE_MODEL";
    163 
    164     /**
    165      * Use a language model based on free-form speech recognition.  This is a value to use for
    166      * {@link #EXTRA_LANGUAGE_MODEL}.
    167      * @see #EXTRA_LANGUAGE_MODEL
    168      */
    169     public static final String LANGUAGE_MODEL_FREE_FORM = "free_form";
    170     /**
    171      * Use a language model based on web search terms.  This is a value to use for
    172      * {@link #EXTRA_LANGUAGE_MODEL}.
    173      * @see #EXTRA_LANGUAGE_MODEL
    174      */
    175     public static final String LANGUAGE_MODEL_WEB_SEARCH = "web_search";
    176 
    177     /** Optional text prompt to show to the user when asking them to speak. */
    178     public static final String EXTRA_PROMPT = "android.speech.extra.PROMPT";
    179 
    180     /**
    181      * Optional IETF language tag (as defined by BCP 47), for example "en-US". This tag informs the
    182      * recognizer to perform speech recognition in a language different than the one set in the
    183      * {@link java.util.Locale#getDefault()}.
    184      */
    185     public static final String EXTRA_LANGUAGE = "android.speech.extra.LANGUAGE";
    186 
    187     /**
    188      * Optional value which can be used to indicate the referer url of a page in which
    189      * speech was requested. For example, a web browser may choose to provide this for
    190      * uses of speech on a given page.
    191      */
    192     public static final String EXTRA_ORIGIN = "android.speech.extra.ORIGIN";
    193 
    194     /**
    195      * Optional limit on the maximum number of results to return. If omitted the recognizer
    196      * will choose how many results to return. Must be an integer.
    197      */
    198     public static final String EXTRA_MAX_RESULTS = "android.speech.extra.MAX_RESULTS";
    199 
    200     /**
    201      * Optional boolean, to be used with {@link #ACTION_WEB_SEARCH}, to indicate whether to
    202      * only fire web searches in response to a user's speech. The default is false, meaning
    203      * that other types of actions can be taken based on the user's speech.
    204      */
    205     public static final String EXTRA_WEB_SEARCH_ONLY = "android.speech.extra.WEB_SEARCH_ONLY";
    206 
    207     /**
    208      * Optional boolean to indicate whether partial results should be returned by the recognizer
    209      * as the user speaks (default is false).  The server may ignore a request for partial
    210      * results in some or all cases.
    211      */
    212     public static final String EXTRA_PARTIAL_RESULTS = "android.speech.extra.PARTIAL_RESULTS";
    213 
    214     /**
    215      * When the intent is {@link #ACTION_RECOGNIZE_SPEECH}, the speech input activity will
    216      * return results to you via the activity results mechanism.  Alternatively, if you use this
    217      * extra to supply a PendingIntent, the results will be added to its bundle and the
    218      * PendingIntent will be sent to its target.
    219      */
    220     public static final String EXTRA_RESULTS_PENDINGINTENT =
    221             "android.speech.extra.RESULTS_PENDINGINTENT";
    222 
    223     /**
    224      * If you use {@link #EXTRA_RESULTS_PENDINGINTENT} to supply a forwarding intent, you can
    225      * also use this extra to supply additional extras for the final intent.  The search results
    226      * will be added to this bundle, and the combined bundle will be sent to the target.
    227      */
    228     public static final String EXTRA_RESULTS_PENDINGINTENT_BUNDLE =
    229             "android.speech.extra.RESULTS_PENDINGINTENT_BUNDLE";
    230 
    231     /** Result code returned when no matches are found for the given speech */
    232     public static final int RESULT_NO_MATCH = Activity.RESULT_FIRST_USER;
    233     /** Result code returned when there is a generic client error */
    234     public static final int RESULT_CLIENT_ERROR = Activity.RESULT_FIRST_USER + 1;
    235     /** Result code returned when the recognition server returns an error */
    236     public static final int RESULT_SERVER_ERROR = Activity.RESULT_FIRST_USER + 2;
    237     /** Result code returned when a network error was encountered */
    238     public static final int RESULT_NETWORK_ERROR = Activity.RESULT_FIRST_USER + 3;
    239     /** Result code returned when an audio error was encountered */
    240     public static final int RESULT_AUDIO_ERROR = Activity.RESULT_FIRST_USER + 4;
    241 
    242     /**
    243      * An ArrayList&lt;String&gt; of the recognition results when performing
    244      * {@link #ACTION_RECOGNIZE_SPEECH}. Generally this list should be ordered in
    245      * descending order of speech recognizer confidence. (See {@link #EXTRA_CONFIDENCE_SCORES}).
    246      * Returned in the results; not to be specified in the recognition request. Only present
    247      * when {@link Activity#RESULT_OK} is returned in an activity result. In a PendingIntent,
    248      * the lack of this extra indicates failure.
    249      */
    250     public static final String EXTRA_RESULTS = "android.speech.extra.RESULTS";
    251 
    252     /**
    253      * A float array of confidence scores of the recognition results when performing
    254      * {@link #ACTION_RECOGNIZE_SPEECH}. The array should be the same size as the ArrayList
    255      * returned in {@link #EXTRA_RESULTS}, and should contain values ranging from 0.0 to 1.0,
    256      * or -1 to represent an unavailable confidence score.
    257      * <p>
    258      * Confidence values close to 1.0 indicate high confidence (the speech recognizer is
    259      * confident that the recognition result is correct), while values close to 0.0 indicate
    260      * low confidence.
    261      * <p>
    262      * Returned in the results; not to be specified in the recognition request. This extra is
    263      * optional and might not be provided. Only present when {@link Activity#RESULT_OK} is
    264      * returned in an activity result.
    265      */
    266     public static final String EXTRA_CONFIDENCE_SCORES = "android.speech.extra.CONFIDENCE_SCORES";
    267 
    268     /**
    269      * Returns the broadcast intent to fire with
    270      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, Bundle)}
    271      * to receive details from the package that implements voice search.
    272      * <p>
    273      * This is based on the value specified by the voice search {@link Activity} in
    274      * {@link #DETAILS_META_DATA}, and if this is not specified, will return null. Also if there
    275      * is no chosen default to resolve for {@link #ACTION_WEB_SEARCH}, this will return null.
    276      * <p>
    277      * If an intent is returned and is fired, a {@link Bundle} of extras will be returned to the
    278      * provided result receiver, and should ideally contain values for
    279      * {@link #EXTRA_LANGUAGE_PREFERENCE} and {@link #EXTRA_SUPPORTED_LANGUAGES}.
    280      * <p>
    281      * (Whether these are actually provided is up to the particular implementation. It is
    282      * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this
    283      * information, but it is not required.)
    284      *
    285      * @param context a context object
    286      * @return the broadcast intent to fire or null if not available
    287      */
    288     public static final Intent getVoiceDetailsIntent(Context context) {
    289         Intent voiceSearchIntent = new Intent(ACTION_WEB_SEARCH);
    290         ResolveInfo ri = context.getPackageManager().resolveActivity(
    291                 voiceSearchIntent, PackageManager.GET_META_DATA);
    292         if (ri == null || ri.activityInfo == null || ri.activityInfo.metaData == null) return null;
    293 
    294         String className = ri.activityInfo.metaData.getString(DETAILS_META_DATA);
    295         if (className == null) return null;
    296 
    297         Intent detailsIntent = new Intent(ACTION_GET_LANGUAGE_DETAILS);
    298         detailsIntent.setComponent(new ComponentName(ri.activityInfo.packageName, className));
    299         return detailsIntent;
    300     }
    301 
    302     /**
    303      * Meta-data name under which an {@link Activity} implementing {@link #ACTION_WEB_SEARCH} can
    304      * use to expose the class name of a {@link BroadcastReceiver} which can respond to request for
    305      * more information, from any of the broadcast intents specified in this class.
    306      * <p>
    307      * Broadcast intents can be directed to the class name specified in the meta-data by creating
    308      * an {@link Intent}, setting the component with
    309      * {@link Intent#setComponent(android.content.ComponentName)}, and using
    310      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)}
    311      * with another {@link BroadcastReceiver} which can receive the results.
    312      * <p>
    313      * The {@link #getVoiceDetailsIntent(Context)} method is provided as a convenience to create
    314      * a broadcast intent based on the value of this meta-data, if available.
    315      * <p>
    316      * This is optional and not all {@link Activity}s which implement {@link #ACTION_WEB_SEARCH}
    317      * are required to implement this. Thus retrieving this meta-data may be null.
    318      */
    319     public static final String DETAILS_META_DATA = "android.speech.DETAILS";
    320 
    321     /**
    322      * A broadcast intent which can be fired to the {@link BroadcastReceiver} component specified
    323      * in the meta-data defined in the {@link #DETAILS_META_DATA} meta-data of an
    324      * {@link Activity} satisfying {@link #ACTION_WEB_SEARCH}.
    325      * <p>
    326      * When fired with
    327      * {@link Context#sendOrderedBroadcast(Intent, String, BroadcastReceiver, android.os.Handler, int, String, android.os.Bundle)},
    328      * a {@link Bundle} of extras will be returned to the provided result receiver, and should
    329      * ideally contain values for {@link #EXTRA_LANGUAGE_PREFERENCE} and
    330      * {@link #EXTRA_SUPPORTED_LANGUAGES}.
    331      * <p>
    332      * (Whether these are actually provided is up to the particular implementation. It is
    333      * recommended that {@link Activity}s implementing {@link #ACTION_WEB_SEARCH} provide this
    334      * information, but it is not required.)
    335      */
    336     public static final String ACTION_GET_LANGUAGE_DETAILS =
    337             "android.speech.action.GET_LANGUAGE_DETAILS";
    338 
    339     /**
    340      * Specify this boolean extra in a broadcast of {@link #ACTION_GET_LANGUAGE_DETAILS} to
    341      * indicate that only the current language preference is needed in the response. This
    342      * avoids any additional computation if all you need is {@link #EXTRA_LANGUAGE_PREFERENCE}
    343      * in the response.
    344      */
    345     public static final String EXTRA_ONLY_RETURN_LANGUAGE_PREFERENCE =
    346             "android.speech.extra.ONLY_RETURN_LANGUAGE_PREFERENCE";
    347 
    348     /**
    349      * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS}
    350      * which is a {@link String} that represents the current language preference this user has
    351      * specified - a locale string like "en-US".
    352      */
    353     public static final String EXTRA_LANGUAGE_PREFERENCE =
    354             "android.speech.extra.LANGUAGE_PREFERENCE";
    355 
    356     /**
    357      * The key to the extra in the {@link Bundle} returned by {@link #ACTION_GET_LANGUAGE_DETAILS}
    358      * which is an {@link ArrayList} of {@link String}s that represents the languages supported by
    359      * this implementation of voice recognition - a list of strings like "en-US", "cmn-Hans-CN",
    360      * etc.
    361      */
    362     public static final String EXTRA_SUPPORTED_LANGUAGES =
    363             "android.speech.extra.SUPPORTED_LANGUAGES";
    364 }
    365