diff --git a/Emotion/Python/Jupyter Notebook/Emotion Analysis Example.ipynb b/Emotion/Python/Jupyter Notebook/Emotion Analysis Example.ipynb
index d92337e..a7a9536 100644
--- a/Emotion/Python/Jupyter Notebook/Emotion Analysis Example.ipynb
+++ b/Emotion/Python/Jupyter Notebook/Emotion Analysis Example.ipynb
@@ -60,74 +60,103 @@
"cell_type": "markdown",
"metadata": {},
"source": [
- "## Detect faces from an image retrieved via URL"
+ "## Helper functions"
]
},
{
"cell_type": "code",
"execution_count": 3,
"metadata": {
- "collapsed": false
+ "collapsed": true
},
"outputs": [],
"source": [
- "# URL direction to image\n",
- "urlImage = 'https://raw.githubusercontent.com/Microsoft/ProjectOxford-ClientSDK/master/Face/Windows/Data/detection3.jpg'\n",
+ "def processRequest( json, data, headers ):\n",
"\n",
- "# Emotion parameters\n",
- "params = { } \n",
+ " \"\"\"\n",
+ " Helper function to process the request to Project Oxford\n",
"\n",
- "headers = dict()\n",
- "headers['Ocp-Apim-Subscription-Key'] = _key\n",
- "headers['Content-Type'] = 'application/json' \n",
+ " Parameters:\n",
+ " json: Used when processing images from its URL. See API Documentation\n",
+ " data: Used when processing image read from disk. See API Documentation\n",
+ " headers: Used to pass the key information and the data type request\n",
+ " \"\"\"\n",
"\n",
- "json = { 'url': urlImage } \n",
+ " retries = 0\n",
+ " result = None\n",
"\n",
- "retries = 0\n",
- "result = None\n",
+ " while True:\n",
"\n",
- "while True:\n",
- " \n",
- " response = requests.request( 'post', _url, json = json, data = None, headers = headers, params = params )\n",
+ " response = requests.request( 'post', _url, json = json, data = data, headers = headers, params = None )\n",
"\n",
- " if response.status_code == 429: \n",
- " \n",
- " print \"Message: %s\" % ( response.json()['error']['message'] )\n",
- " \n",
- " if retries <= _maxNumRetries: \n",
- " time.sleep(1) \n",
- " retries += 1\n",
- " continue\n",
- " else: \n",
- " print 'Error: failed after retrying!'\n",
- " break\n",
- "\n",
- " elif response.status_code == 200 or response.status_code == 201:\n",
- "\n",
- " if 'content-length' in response.headers and int(response.headers['content-length']) == 0: \n",
- " result = None \n",
- " elif 'content-type' in response.headers and isinstance(response.headers['content-type'], str): \n",
- " if 'application/json' in response.headers['content-type'].lower(): \n",
- " result = response.json() if response.content else None \n",
- " elif 'image' in response.headers['content-type'].lower(): \n",
- " result = response.content\n",
- " else:\n",
- " print \"Error code: %d\" % ( response.status_code )\n",
- " print \"Message: %s\" % ( response.json()['error']['message'] )\n",
+ " if response.status_code == 429: \n",
+ "\n",
+ " print \"Message: %s\" % ( response.json()['error']['message'] )\n",
+ "\n",
+ " if retries <= _maxNumRetries: \n",
+ " time.sleep(1) \n",
+ " retries += 1\n",
+ " continue\n",
+ " else: \n",
+ " print 'Error: failed after retrying!'\n",
+ " break\n",
+ "\n",
+ " elif response.status_code == 200 or response.status_code == 201:\n",
+ "\n",
+ " if 'content-length' in response.headers and int(response.headers['content-length']) == 0: \n",
+ " result = None \n",
+ " elif 'content-type' in response.headers and isinstance(response.headers['content-type'], str): \n",
+ " if 'application/json' in response.headers['content-type'].lower(): \n",
+ " result = response.json() if response.content else None \n",
+ " elif 'image' in response.headers['content-type'].lower(): \n",
+ " result = response.content\n",
+ " else:\n",
+ " print \"Error code: %d\" % ( response.status_code )\n",
+ " print \"Message: %s\" % ( response.json()['error']['message'] )\n",
+ "\n",
+ " break\n",
" \n",
- " break"
+ " return result"
+ ]
+ },
+ {
+ "cell_type": "code",
+ "execution_count": 4,
+ "metadata": {
+ "collapsed": true
+ },
+ "outputs": [],
+ "source": [
+ "def renderResultOnImage( result, img ):\n",
+ " \n",
+ " \"\"\"Display the obtained results onto the input image\"\"\"\n",
+ " \n",
+ " for currFace in result:\n",
+ " faceRectangle = currFace['faceRectangle']\n",
+ " cv2.rectangle( img,(faceRectangle['left'],faceRectangle['top']),\n",
+ " (faceRectangle['left']+faceRectangle['width'], faceRectangle['top'] + faceRectangle['height']),\n",
+ " color = (255,0,0), thickness = 5 )\n",
+ "\n",
+ "\n",
+ " for currFace in result:\n",
+ " faceRectangle = currFace['faceRectangle']\n",
+ " currEmotion = max(currFace['scores'].iteritems(), key=operator.itemgetter(1))[0]\n",
+ "\n",
+ "\n",
+ " textToWrite = \"%s\" % ( currEmotion )\n",
+ " cv2.putText( img, textToWrite, (faceRectangle['left'],faceRectangle['top']-10), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,0,0), 1 )"
]
},
{
"cell_type": "markdown",
"metadata": {},
"source": [
- "Let's show first the original image"
+ "## Detect faces from an image retrieved via URL"
]
},
{
"cell_type": "code",
- "execution_count": 4,
+ "execution_count": 5,
"metadata": {
"collapsed": false
},
@@ -135,18 +164,18 @@
{
"data": {
"text/plain": [
- "public class AdmRecoOnlyPreferences
-extends java.lang.Object
-| Constructor and Description | -
|---|
AdmRecoOnlyPreferences() |
-
| Modifier and Type | -Method and Description | -
|---|---|
void |
-setClientId(java.lang.String clientId) |
-
void |
-setClientSecret(java.lang.String secret) |
-
void |
-setLocale(java.lang.String locale) |
-
void |
-setLuisAppId(java.lang.String luisAppID) |
-
void |
-setLuisSubscriptionId(java.lang.String luisSubscriptionID) |
-
void |
-setMicrophoneTimeout(int timeout) |
-
void |
-setServiceUri(java.lang.String serviceUri) |
-
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic AdmRecoOnlyPreferences()-
public void setLocale(java.lang.String locale)-
locale - The locale (or location) string.public void setServiceUri(java.lang.String serviceUri)-
serviceUri - The Speech Recognition Service endpoint.public void setClientId(java.lang.String clientId)+ + + + + +
public class AdmRecoOnlyPreferences
+extends java.lang.Object
+| Constructor and Description | +
|---|
AdmRecoOnlyPreferences() |
+
| Modifier and Type | +Method and Description | +
|---|---|
void |
+setClientId(java.lang.String clientId) |
+
void |
+setClientSecret(java.lang.String secret) |
+
void |
+setLocale(java.lang.String locale) |
+
void |
+setLuisAppId(java.lang.String luisAppID) |
+
void |
+setLuisSubscriptionId(java.lang.String luisSubscriptionID) |
+
void |
+setMicrophoneTimeout(int timeout) |
+
void |
+setServiceUri(java.lang.String serviceUri) |
+
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic AdmRecoOnlyPreferences()+
public void setLocale(java.lang.String locale)+
locale - The locale (or location) string.public void setServiceUri(java.lang.String serviceUri)+
serviceUri - The Speech Recognition Service endpoint.public void setClientId(java.lang.String clientId)
clientId - The client id for the Azure account that is associated with the Speech
- Recognition Service.public void setLuisAppId(java.lang.String luisAppID)+ Recognition Service. +
public void setLuisAppId(java.lang.String luisAppID)
luisAppID - Once you have configured the LUIS service to create and publish
an intent model (see https://LUIS.ai) you will be given an Application ID guid.
- Use that GUID here.public void setLuisSubscriptionId(java.lang.String luisSubscriptionID)+ Use that GUID here. +
public void setLuisSubscriptionId(java.lang.String luisSubscriptionID)
luisSubscriptionID - Once you create a LUIS account (see https://LUIS.ai)
- you will be given an Subscription ID. Use that secret here.public void setClientSecret(java.lang.String secret)+ you will be given an Subscription ID. Use that secret here. +
public void setClientSecret(java.lang.String secret)
secret - The client secret provided when signing up for Speech Recognition Service
- in the Azure marketplace.public void setMicrophoneTimeout(int timeout)+ in the Azure marketplace. +
public void setMicrophoneTimeout(int timeout)
timeout - The default microphone timeout in milliseconds. A negative value disables
- automatic microphone shutoff.public enum AudioCompressionType -extends java.lang.Enum<AudioCompressionType>-
| Enum Constant and Description | -
|---|
PCM
-Indicates uncompressed audio
- |
-
Siren7
-Indicates compressed audio
- |
-
| Modifier and Type | -Method and Description | -|||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
static AudioCompressionType |
-Create(int value)
-Convert an integer to its corresponding AudioCompressionType.
- |
-|||||||||||||
short |
-getValue()
-Gets the integer value of the AudioCompressionType.
- |
-|||||||||||||
static AudioCompressionType |
-valueOf(java.lang.String name)
-Returns the enum constant of this type with the specified name.
- |
-|||||||||||||
static AudioCompressionType[] |
-values()
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+com.microsoft.projectoxford.speechrecognition
+Enum AudioCompressionType+
+
+
+
+
-
-
+
|
+
compareTo, equals, getDeclaringClass, hashCode, name, ordinal, toString, valueOfgetClass, notify, notifyAll, wait, wait, waitpublic static final AudioCompressionType PCM+
public static final AudioCompressionType Siren7+
public static AudioCompressionType[] values()
for (AudioCompressionType c : AudioCompressionType.values()) System.out.println(c); -
public static AudioCompressionType valueOf(java.lang.String name)+
public static AudioCompressionType valueOf(java.lang.String name)
name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic final short getValue()-
public static AudioCompressionType Create(int value)-
value - an integer representation of AudioCompressionType.name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic final short getValue()+
public static AudioCompressionType Create(int value)+
value - an integer representation of AudioCompressionType.public enum Confidence -extends java.lang.Enum<Confidence>+ + + + + +
public enum Confidence +extends java.lang.Enum<Confidence>
| Enum Constant and Description | -
|---|
High |
-
Low |
-
None |
-
Normal |
-
| Modifier and Type | -Method and Description | -|||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
static Confidence |
-Create(int value)
-Convert an integer to its corresponding Confidence.
- |
-|||||||||||||||
int |
-getValue()
-Gets the integer value of the Confidence.
- |
-|||||||||||||||
static Confidence |
-valueOf(java.lang.String name)
-Returns the enum constant of this type with the specified name.
- |
-|||||||||||||||
static Confidence[] |
-values()
+ ITN.
+
+
+
+
+
-
-
+
|
+
compareTo, equals, getDeclaringClass, hashCode, name, ordinal, toString, valueOfgetClass, notify, notifyAll, wait, wait, waitpublic static final Confidence None+
public static final Confidence Low+
public static final Confidence Normal+
public static final Confidence High+
public static Confidence[] values()
for (Confidence c : Confidence.values()) System.out.println(c); -
public static Confidence valueOf(java.lang.String name)+
public static Confidence valueOf(java.lang.String name)
name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic final int getValue()-
public static Confidence Create(int value)-
value - an integer representation of Confidence.name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic final int getValue()+
public static Confidence Create(int value)+
value - an integer representation of Confidence.public final class Contract
-extends java.lang.Object
-| Modifier and Type | -Method and Description | -
|---|---|
static void |
-fail()
-Put stack trace on the log and exit program.
- |
-
static void |
-notImplemented()
-Put stack trace on the log and exit program.
- |
-
static void |
-requires(boolean condition)
-Assert condition and if false, put stack trace on the log and exit program.
- |
-
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic static void fail()-
public static void notImplemented()-
public static void requires(boolean condition)-
public final class Contract
+extends java.lang.Object
+| Modifier and Type | +Method and Description | +
|---|---|
static void |
+fail()
+Put stack trace on the log and exit program.
+ |
+
static void |
+notImplemented()
+Put stack trace on the log and exit program.
+ |
+
static void |
+requires(boolean condition)
+Assert condition and if false, put stack trace on the log and exit program.
+ |
+
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic static void fail()+
public static void notImplemented()+
public static void requires(boolean condition)+
public class DataRecognitionClient -extends Conversation+ + + + + +
public class DataRecognitionClient +extends Conversation
| Modifier and Type | -Method and Description | -||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|
void |
-endAudio()
-Notify the server that client is done sending audio buffers to the Speech Recognition Service.
- |
-||||||||||
void |
-finalize()
-Should only be called when client is ready to break the connection with the Speech Recognition Server.
- |
-||||||||||
void |
-sendAudio(byte[] buffer,
- int actualAudioBytesInBuffer)
-Send buffers of audio to the Speech Recognition Service.
- |
-||||||||||
void |
-sendAudioFormat(SpeechAudioFormat audioFormat)
+ recognition results.
+
+
+
+
+
-
-
+
|
+
audioStart, audioStopequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic void sendAudioFormat(SpeechAudioFormat audioFormat)
audioFormat - Audio features that describe the encoding and sampling rate of the audio.public void sendAudio(byte[] buffer, - int actualAudioBytesInBuffer)+ SpeechAudioFormat descriptor to describe the layout and format of your raw audio data.
audioFormat - Audio features that describe the encoding and sampling rate of the audio.public void sendAudio(byte[] buffer, + int actualAudioBytesInBuffer)
buffer - The data bytes of audio to send to the ServeractualAudioBytesInBuffer - The buffer size is allowed to be larger than the actual audio data in the buffer, so
- this parameter states the size of the actual data in the buffer.public void endAudio()+ this parameter states the size of the actual data in the buffer. +
public void endAudio()
public void finalize() - throws java.lang.Throwable+ This work is queued onto a background worker.
public void finalize() + throws java.lang.Throwable
finalize in class Conversationjava.lang.Throwablefinalize in class Conversationjava.lang.Throwablepublic class DataRecognitionClientWithIntent -extends DataRecognitionClient+ + + + + +
public class DataRecognitionClientWithIntent +extends DataRecognitionClient
endAudio, finalize, sendAudio, sendAudioFormataudioStart, audioStopequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitendAudio, finalize, sendAudio, sendAudioFormataudioStart, audioStopequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic interface ISpeechRecognitionServerEvents
-| Modifier and Type | -Method and Description | -||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
void |
-onAudioEvent(boolean recording)
-Invoked when the audio recording state has changed.
- |
-||||||||||||||||
void |
-onError(int errorCode,
- java.lang.String response)
-Invoked when an error is detected
- |
-||||||||||||||||
void |
-onFinalResponseReceived(RecognitionResult response)
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+com.microsoft.projectoxford.speechrecognition
+Interface ISpeechRecognitionServerEvents+
+
+
+
+
-
+
|
+
void onPartialResponseReceived(java.lang.String response)
response - The display textvoid onFinalResponseReceived(RecognitionResult response)+ the current hypothesis text.
response - The display textvoid onFinalResponseReceived(RecognitionResult response)
In LongDictation mode, the client will receive multiple final results, based on where the server thinks sentence pauses are. This event will be fired - for each final result, as the server determines them.
response - A StreamlinedRecognitionResults which contains the n-best recognized
text results and their confidences. A StreamlinedRecognitionResults can
then further be used to obtain a SpeechRecognitionResults which has even
- more n-best result data.void onIntentReceived(java.lang.String payload)-
void onError(int errorCode, - java.lang.String response)-
errorCode - The error code.response - The body of the http response for the error.void onAudioEvent(boolean recording)-
recording - The current recording statevoid onIntentReceived(java.lang.String payload)+
void onError(int errorCode, + java.lang.String response)+
errorCode - The error code.response - The body of the http response for the error.void onAudioEvent(boolean recording)+
recording - The current recording statepublic class MicrophoneRecognitionClient -extends Conversation+ + + + + +
public class MicrophoneRecognitionClient +extends Conversation
| Modifier and Type | -Method and Description | -
|---|---|
void |
-endMicAndRecognition()
-The microphone is turned off and the connection to the Speech Recognition Server is severed.
- |
-
void |
-startMicAndRecognition()
-The microphone is turned on and data from the microphone is sent to the Speech Recognition Service.
- |
-
audioStart, audioStop, finalizeequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, wait| Modifier and Type | +Method and Description | +
|---|---|
void |
+endMicAndRecognition()
+The microphone is turned off and the connection to the Speech Recognition Server is severed.
+ |
+
void |
+startMicAndRecognition()
+The microphone is turned on and data from the microphone is sent to the Speech Recognition Service.
+ |
+
audioStart, audioStop, finalizeequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic void startMicAndRecognition()
public void endMicAndRecognition()-
public void endMicAndRecognition()+
public class MicrophoneRecognitionClientWithIntent -extends MicrophoneRecognitionClient+ + + + + +
public class MicrophoneRecognitionClientWithIntent +extends MicrophoneRecognitionClient
endMicAndRecognition, startMicAndRecognitionaudioStart, audioStop, finalizeequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitendMicAndRecognition, startMicAndRecognitionaudioStart, audioStop, finalizeequals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic class RecognitionResult
-extends java.lang.Object
+
+
+
+
+
+public class RecognitionResult
+extends java.lang.Object
| Modifier and Type | -Field and Description | -
|---|---|
RecognitionStatus |
-RecognitionStatus
-Status on how the recognition was produced.
- |
-
RecognizedPhrase[] |
-Results
-A set of n-best confidence values and recognized texts
- |
-
| Constructor and Description | -
|---|
RecognitionResult() |
-
public RecognitionStatus RecognitionStatus+ single choice), based on where the server thinks sentence pauses are.
| Modifier and Type | +Field and Description | +
|---|---|
RecognitionStatus |
+RecognitionStatus
+Status on how the recognition was produced.
+ |
+
RecognizedPhrase[] |
+Results
+A set of n-best confidence values and recognized texts
+ |
+
| Constructor and Description | +
|---|
RecognitionResult() |
+
public RecognitionStatus RecognitionStatus
public RecognizedPhrase[] Results-
public RecognizedPhrase[] Results+
public enum RecognitionStatus -extends java.lang.Enum<RecognitionStatus>+ + + + + +
public enum RecognitionStatus +extends java.lang.Enum<RecognitionStatus>
| Enum Constant and Description | -
|---|
BabbleTimeout |
-
Cancelled |
-
DictationEndSilenceTimeout |
-
EndOfDictation |
-
HotWordMaximumTime |
-
InitialSilenceTimeout |
-
Intermediate |
-
NoMatch |
-
None |
-
RecognitionError |
-
RecognitionSuccess |
-
| Modifier and Type | -Method and Description | -||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
static RecognitionStatus |
-Create(int value)
-Convert an integer to its corresponding RecognitionStatus.
- |
-||||||||||||||||||||||
int |
-getValue()
-Gets the integer value of the RecognitionStatus.
- |
-||||||||||||||||||||||
static RecognitionStatus |
-valueOf(java.lang.String name)
-Returns the enum constant of this type with the specified name.
- |
-||||||||||||||||||||||
static RecognitionStatus[] |
-values()
+ a result of successful reco, or as a result of canceling the connection, etc...
+
+
+
+
+
-
-
+
|
+
compareTo, equals, getDeclaringClass, hashCode, name, ordinal, toString, valueOfgetClass, notify, notifyAll, wait, wait, waitpublic static final RecognitionStatus None+
public static final RecognitionStatus Intermediate+
public static final RecognitionStatus RecognitionSuccess+
public static final RecognitionStatus NoMatch+
public static final RecognitionStatus InitialSilenceTimeout+
public static final RecognitionStatus BabbleTimeout+
public static final RecognitionStatus HotWordMaximumTime+
public static final RecognitionStatus Cancelled+
public static final RecognitionStatus RecognitionError+
public static final RecognitionStatus DictationEndSilenceTimeout+
public static final RecognitionStatus EndOfDictation+
public static RecognitionStatus[] values()
for (RecognitionStatus c : RecognitionStatus.values()) System.out.println(c); -
public static RecognitionStatus valueOf(java.lang.String name)+
public static RecognitionStatus valueOf(java.lang.String name)
name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic int getValue()-
public static RecognitionStatus Create(int value)-
value - an integer representation of RecognitionStatus.name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullpublic int getValue()+
public static RecognitionStatus Create(int value)+
value - an integer representation of RecognitionStatus.public class RecognizedPhrase
-extends java.lang.Object
+
+
+
+
+
+public class RecognizedPhrase
+extends java.lang.Object
| Modifier and Type | -Field and Description | -
|---|---|
Confidence |
-Confidence
-A value representing high, medium or low confidence.
- |
-
java.lang.String |
-DisplayText
-The recognized phrase with inverse text normalization, capitalization, punctuation and profanity masking applied.
- |
-
java.lang.String |
-InverseTextNormalizationResult
-Inverse text normalization (ITN) converts phrases like "one two three four" to a normalized form such as "1234".
- |
-
java.lang.String |
-LexicalForm
-The recognized phrase, without any post-processing.
- |
-
java.lang.String |
-MaskedInverseTextNormalizationResult
-The recognized phrase with inverse text normalization and profanity masking applied, but not capitalization or punctuation.
- |
-
| Constructor and Description | -
|---|
RecognizedPhrase() |
-
| Modifier and Type | +Field and Description | +
|---|---|
Confidence |
+Confidence
+A value representing high, medium or low confidence.
+ |
+
java.lang.String |
+DisplayText
+The recognized phrase with inverse text normalization, capitalization, punctuation and profanity masking applied.
+ |
+
java.lang.String |
+InverseTextNormalizationResult
+Inverse text normalization (ITN) converts phrases like "one two three four" to a normalized form such as "1234".
+ |
+
java.lang.String |
+LexicalForm
+The recognized phrase, without any post-processing.
+ |
+
java.lang.String |
+MaskedInverseTextNormalizationResult
+The recognized phrase with inverse text normalization and profanity masking applied, but not capitalization or punctuation.
+ |
+
| Constructor and Description | +
|---|
RecognizedPhrase() |
+
public java.lang.String LexicalForm
public java.lang.String DisplayText+ This form is optimal for use by applications that need the raw, unprocessed speech recognition result.
public java.lang.String DisplayText
public java.lang.String InverseTextNormalizationResult+ This form is optimal for use by applications that display the speech recognition results to a user.
public java.lang.String InverseTextNormalizationResult
public java.lang.String MaskedInverseTextNormalizationResult+ which perform queries based on the recognized text.
public java.lang.String MaskedInverseTextNormalizationResult
public Confidence Confidence-
public Confidence Confidence+
public class SpeechAudioFormat
-extends java.lang.Object
+
+
+
+
+
+public class SpeechAudioFormat
+extends java.lang.Object
| Modifier and Type | -Field and Description | -||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
int |
-AverageBytesPerSecond
+ sample rate, bits per sample and other attributes.
+
+
+
+
+
-
+
|
+||||||||||||||||||||||||
short |
+BitsPerSample
+The number of significant bits in each audio sample.
+ |
+||||||||||||||||||||||||
short |
+BlockAlign
+The number of data bytes per sample slice.
+ |
+||||||||||||||||||||||||
short |
+ChannelCount
+The number of separate audio signals in the audio data.
+ |
+||||||||||||||||||||||||
AudioCompressionType |
+EncodingFormat
+Specifies the type of compression used on the audio data as a short.
+ |
+||||||||||||||||||||||||
byte[] |
+FormatSpecificData
+Extra bytes for use to describe parameters to certain audio compression types.
+ |
+||||||||||||||||||||||||
int |
+SamplesPerSecond
+Audio sample slices per second (one slice includes all the channel samples).
+ |
+
| Constructor and Description | +
|---|
SpeechAudioFormat() |
+
| Modifier and Type | +Method and Description | +
|---|---|
static SpeechAudioFormat |
+create16BitPCMFormat(int sampleRate)
+Produces a SpeechAudioFormat for 16-bit PCM data.
+ |
+
static SpeechAudioFormat |
+createSiren7Format(int sampleRate)
+Produces a SpeechAudioFormat for data encoded in Siren7.
+ |
+
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic int AverageBytesPerSecond
public short BitsPerSample-
public short BlockAlign-
public short ChannelCount+ per second in order to play the audio.
public short BitsPerSample+
public short BlockAlign+
public short ChannelCount
public AudioCompressionType EncodingFormat+ A value of 1 means a mono signal, a value of 2 means a stereo signal, etc.
public AudioCompressionType EncodingFormat
public byte[] FormatSpecificData+ Use getEncodingFormat or setEncodingFormat to use this short as a AudioCompressionType.
public byte[] FormatSpecificData
public int SamplesPerSecond+ This field should be null for PCM.
public int SamplesPerSecond
public static SpeechAudioFormat createSiren7Format(int sampleRate)+ Thus this value is unaffected by the number of channels. +
public static SpeechAudioFormat createSiren7Format(int sampleRate)
sampleRate - The samples per second of the audio that was encoded (can only by 8000 or 16000).public static SpeechAudioFormat create16BitPCMFormat(int sampleRate)-
sampleRate - The samples per second of the audio that was encoded (can only by 8000 or 16000).sampleRate - The samples per second of the audio that was encoded (can only by 8000 or 16000).public static SpeechAudioFormat create16BitPCMFormat(int sampleRate)+
sampleRate - The samples per second of the audio that was encoded (can only by 8000 or 16000).public enum SpeechRecognitionMode -extends java.lang.Enum<SpeechRecognitionMode>+ + + + + +
public enum SpeechRecognitionMode +extends java.lang.Enum<SpeechRecognitionMode>
In ShortPhrase mode, an utterance may only up to 14 sec long, as data is @@ -114,227 +114,227 @@
In LongDictation mode, an utterance may be only up to 2 minutes long, as data is sent to the server, the client will receive multiple partial results and multiple - final results, based on where the server thinks sentence pauses are.
| Enum Constant and Description | -||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
LongDictation
+ final results, based on where the server thinks sentence pauses are.
+
+
+
+
+
-
-
+
|
+
compareTo, equals, getDeclaringClass, hashCode, name, ordinal, toString, valueOfgetClass, notify, notifyAll, wait, wait, waitpublic static final SpeechRecognitionMode ShortPhrase
public static final SpeechRecognitionMode LongDictation+ final multiple n-best choice result.
public static final SpeechRecognitionMode LongDictation
public static SpeechRecognitionMode[] values()+ final results, based on where the server thinks sentence pauses are.
public static SpeechRecognitionMode[] values()
for (SpeechRecognitionMode c : SpeechRecognitionMode.values()) System.out.println(c); -
public static SpeechRecognitionMode valueOf(java.lang.String name)+
public static SpeechRecognitionMode valueOf(java.lang.String name)
name - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is nullname - the name of the enum constant to be returned.java.lang.IllegalArgumentException - if this enum type has no constant with the specified namejava.lang.NullPointerException - if the argument is null| Interface | -Description | -
|---|---|
| ISpeechRecognitionServerEvents | -
- Handles callbacks for Speech related events
- |
-
| Class | -Description | -||||||||||||||||||||||||||||||||||||||||||||||||
|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|---|
| AdmRecoOnlyPreferences | -
- A streamlined set of parameters for use for Adm and Reco situations to configure speech services.
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| Contract | -
- Preconditions and assertions
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| DataRecognitionClient | -
- Use the AzureIntelligentServices to do speech recognition with data (for example from a file or audio source).
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| DataRecognitionClientWithIntent | -
- Use the AzureIntelligentServices to do speech recognition with data (for example from a file or audio source).
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| MicrophoneRecognitionClient | -
- AzureIntelligentServices speech recognition from the microphone.
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| MicrophoneRecognitionClientWithIntent | -
- AzureIntelligentServices speech recognition from the microphone.
- |
-||||||||||||||||||||||||||||||||||||||||||||||||
| RecognitionResult | -
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+
+Package com.microsoft.projectoxford.speechrecognition+
+
-
-
-
-
-
-
-
-
-
-
+ to each n-best result.
+
-
-
-
-
- |
+||||||||||||||||||||||||||||||||||||||||||||||||
| RecognitionStatus | +
+ Status on how the recognition was produced.
+ |
+||||||||||||||||||||||||||||||||||||||||||||||||
| SpeechRecognitionMode | +
+ Determines what type of request to make to the Speech Recognition Server.
+ |
+
public class Conversation
-extends java.lang.Object
-| Constructor and Description | -
|---|
Conversation() |
-
| Modifier and Type | -Method and Description | -
|---|---|
void |
-audioStart()
-The microphone is turned on and data from the microphone is sent to the Speech Recognition Service.
- |
-
void |
-audioStop()
-The microphone is turned off and the connection to the Speech Recognition Server is severed.
- |
-
void |
-finalize()
-Should only be called when client is ready to break the connection with the Speech Recognition Server.
- |
-
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic void audioStart()+ + + + + +
public class Conversation
+extends java.lang.Object
+| Constructor and Description | +
|---|
Conversation() |
+
| Modifier and Type | +Method and Description | +
|---|---|
void |
+audioStart()
+The microphone is turned on and data from the microphone is sent to the Speech Recognition Service.
+ |
+
void |
+audioStop()
+The microphone is turned off and the connection to the Speech Recognition Server is severed.
+ |
+
void |
+finalize()
+Should only be called when client is ready to break the connection with the Speech Recognition Server.
+ |
+
equals, getClass, hashCode, notify, notifyAll, toString, wait, wait, waitpublic void audioStart()
public void audioStop()-
public void finalize() - throws java.lang.Throwable+ A built in Silence Detector is applied to the microphone data before it is sent to the recognition service.
public void audioStop()+
public void finalize() + throws java.lang.Throwable
finalize in class java.lang.Objectjava.lang.Throwablefinalize in class java.lang.Objectjava.lang.Throwable