[speech-to-text] WebSockets support for speech to text

Author: germanattanasio

pom.xml

@@ -1,5 +1,6 @@
 <?xml version="1.0" encoding="UTF-8"?>
-<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
+<project xmlns="http://maven.apache.org/POM/4.0.0" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance"
+	xsi:schemaLocation="http://maven.apache.org/POM/4.0.0 http://maven.apache.org/xsd/maven-4.0.0.xsd">
 	<modelVersion>4.0.0</modelVersion>
 	<groupId>com.ibm.watson.developer_cloud</groupId>
 	<version>2.5.1-SNAPSHOT</version>
@@ -20,7 +21,7 @@
 		<dependency>
 			<groupId>com.squareup.okhttp</groupId>
 			<artifactId>okhttp</artifactId>
-			<version>2.7.0</version>
+			<version>2.7.2</version>
 		</dependency>
 		<dependency>
 			<groupId>com.google.code.gson</groupId>
@@ -35,9 +36,14 @@
 		<dependency>
 			<groupId>junit</groupId>
 			<artifactId>junit</artifactId>
-			<version>4.11</version>
+			<version>4.12</version>
 			<scope>test</scope>
 		</dependency>
+		<dependency>
+			<groupId>com.neovisionaries</groupId>
+			<artifactId>nv-websocket-client</artifactId>
+			<version>1.19</version>
+		</dependency>
 		<!-- mockserver -->
 		<dependency>
 			<groupId>org.mock-server</groupId>

src/main/java/com/ibm/watson/developer_cloud/http/HttpHeaders.java

@@ -179,4 +179,6 @@ public interface HttpHeaders {
    */
   public static final String WWW_AUTHENTICATE = "WWW-Authenticate";
 
+  /** The Authorization token header. */
+  public static final String X_WATSON_AUTHORIZATION_TOKEN = "X-Watson-Authorization-Token";
 }

src/main/java/com/ibm/watson/developer_cloud/speech_to_text/v1/RecognizeDelegate.java

@@ -0,0 +1,49 @@
+/**
+ * Copyright 2015 IBM Corp. All Rights Reserved.
+ * 
+ * Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except
+ * in compliance with the License. You may obtain a copy of the License at
+ * 
+ * http://www.apache.org/licenses/LICENSE-2.0
+ * 
+ * Unless required by applicable law or agreed to in writing, software distributed under the License
+ * is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express
+ * or implied. See the License for the specific language governing permissions and limitations under
+ * the License.
+ */
+package com.ibm.watson.developer_cloud.speech_to_text.v1;
+
+import com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechResults;
+
+
+
+/**
+ * The Interface RecognizeDelegate.
+ */
+public interface RecognizeDelegate {
+
+  /**
+   * On message.
+   * 
+   * @param speechResults the speech results
+   * @param fin if results are final
+   */
+  public void onMessage(SpeechResults speechResults, boolean fin);
+
+  /**
+   * On connected.
+   */
+  public void onConnected();
+
+  /**
+   * On error.
+   * 
+   * @param e the e
+   */
+  public void onError(Exception e);
+
+  /**
+   * On disconnected.
+   */
+  public void onDisconnected();
+}

src/main/java/com/ibm/watson/developer_cloud/speech_to_text/v1/RecognizeOptions.java

@@ -13,6 +13,9 @@
  */
 package com.ibm.watson.developer_cloud.speech_to_text.v1;
 
+import java.util.List;
+
+import com.google.gson.annotations.SerializedName;
 import com.ibm.watson.developer_cloud.speech_to_text.v1.model.SpeechSession;
 
 
@@ -22,15 +25,27 @@
  */
 public class RecognizeOptions {
 
+  @SerializedName("content-type")
+  private String contentType;
   private Boolean continuous;
   private Integer inactivityTimeout;
+
+  @SerializedName("interim_results")
+  private Boolean interimResults;
+  private List<String> keywords;
+
+  @SerializedName("keywords_threshold")
+  private Double keywordsThreshold;
   private Integer maxAlternatives;
   private String model;
   private String sessionId;
-
   private Boolean timestamps;
-  private Boolean wordConfidence;
 
+  @SerializedName("word_alternatives_threshold")
+  private Double wordAlternativesThreshold;
+
+  @SerializedName("word_confidence")
+  private Boolean wordConfidence;
 
   /**
    * If true, multiple final results that represent multiple consecutive phrases separated by pauses
@@ -44,6 +59,15 @@ public RecognizeOptions continuous(Boolean continuous) {
     return this;
   }
 
+  /**
+   * Gets the content type.
+   * 
+   * @return the contentType
+   */
+  public String getContentType() {
+    return contentType;
+  }
+
   /**
    * Gets the continuous.
    * 
@@ -62,6 +86,33 @@ public Integer getInactivityTimeout() {
     return inactivityTimeout;
   }
 
+  /**
+   * Gets the interim results.
+   * 
+   * @return the interimResults
+   */
+  public Boolean getInterimResults() {
+    return interimResults;
+  }
+
+  /**
+   * Gets the keywords.
+   * 
+   * @return the keywords
+   */
+  public List<String> getKeywords() {
+    return keywords;
+  }
+
+  /**
+   * Gets the keywords threshold.
+   * 
+   * @return the keywordsThreshold
+   */
+  public Double getKeywordsThreshold() {
+    return keywordsThreshold;
+  }
+
   /**
    * Gets the max alternatives.
    * 
@@ -98,7 +149,14 @@ public Boolean getTimestamps() {
     return timestamps;
   }
 
-
+  /**
+   * Gets the word alternatives threshold.
+   * 
+   * @return the wordAlternativesThreshold
+   */
+  public Double getWordAlternativesThreshold() {
+    return wordAlternativesThreshold;
+  }
 
   /**
    * Gets the word confidence.
@@ -121,7 +179,50 @@ public RecognizeOptions inactivityTimeout(Integer inactivityTimeout) {
   }
 
   /**
-   * Maximum number of alternative transcripts returned
+   * If true, the service sends interim results for the transcription. Otherwise, the recognition
+   * ends after first "end of speech" is detected. The default is false..
+   * 
+   * @param interimResults the interim results
+   * @return the recognize options
+   */
+  public RecognizeOptions interimResults(Boolean interimResults) {
+    this.interimResults = interimResults;
+    return this;
+  }
+
+  /**
+   * Specifies an array of keyword strings to be matched in the input audio. By default, the service
+   * does no keyword spotting.
+   * 
+   * 
+   * @param keywords the keywords
+   * @return the recognize options
+   */
+  public RecognizeOptions keywords(List<String> keywords) {
+    this.keywords = keywords;
+    return this;
+  }
+
+
+
+  /**
+   * Specifies a minimum level of confidence that the service must have to report a matching keyword
+   * in the input audio. Specify a probability value between 0 and 1 inclusive. A match must have at
+   * least the specified confidence to be returned. Omit the parameter or specify a value of null
+   * (the default) to spot no keywords. If you specify a valid threshold, you must also specify at
+   * least one keyword.
+   * 
+   * 
+   * @param keywordsThreshold the keywords threshold
+   * @return the recognize options
+   */
+  public RecognizeOptions keywordsThreshold(Double keywordsThreshold) {
+    this.keywordsThreshold = keywordsThreshold;
+    return this;
+  }
+
+  /**
+   * Maximum number of alternative transcripts returned.
    * 
    * @param maxAlternatives the max alternatives
    * @return the recognize options
@@ -132,7 +233,7 @@ public RecognizeOptions maxAlternatives(Integer maxAlternatives) {
   }
 
   /**
-   * Sets the model name used for the recognition
+   * Sets the model name used for the recognition.
    * 
    * @param model the model
    * @return the recognize options
@@ -142,6 +243,17 @@ public RecognizeOptions model(String model) {
     return this;
   }
 
+  /**
+   * Sets the session id.
+   * 
+   * @param session the {@link SpeechSession}
+   * @return the recognize options
+   */
+  public RecognizeOptions session(SpeechSession session) {
+    this.sessionId = session.getSessionId();
+    return this;
+  }
+
   /**
    * Sets session id.
    * 
@@ -154,29 +266,46 @@ public RecognizeOptions sessionId(String sessionId) {
   }
 
   /**
-   * Sets the session id.
+   * If true, time alignment for each word is returned.
    * 
-   * @param session the {@link SpeechSession}
+   * @param timestamps the timestamps
    * @return the recognize options
    */
-  public RecognizeOptions session(SpeechSession session) {
-    this.sessionId = session.getSessionId();
+  public RecognizeOptions timestamps(Boolean timestamps) {
+    this.timestamps = timestamps;
     return this;
   }
 
   /**
-   * If true, time alignment for each word is returned
+   * Specifies a minimum level of confidence that the service must have to report a hypothesis for a
+   * word from the input audio. Specify a probability value between 0 and 1 inclusive. A hypothesis
+   * must have at least the specified confidence to be returned as a word alternative. Omit the
+   * parameter or specify a value of null (the default) to return no word alternatives.
    * 
-   * @param timestamps the timestamps
+   * 
+   * 
+   * @param wordAlternativesThreshold the wordAalternatives threshold
    * @return the recognize options
    */
-  public RecognizeOptions timestamps(Boolean timestamps) {
-    this.timestamps = timestamps;
+  public RecognizeOptions wordAlternativesThreshold(Double wordAlternativesThreshold) {
+    this.wordAlternativesThreshold = wordAlternativesThreshold;
     return this;
   }
 
   /**
-   * If true, confidence measure per word is returned if available
+   * Content type.
+   * 
+   * @param contentType the content type
+   * @return the recognize options
+   */
+  public RecognizeOptions contentType(String contentType) {
+    this.contentType = contentType;
+    return this;
+  }
+
+
+  /**
+   * If true, confidence measure per word is returned if available.
    * 
    * @param wordConfidence the word confidence
    * @return the recognize options

src/main/java/com/ibm/watson/developer_cloud/speech_to_text/v1/SpeechToText.java

@@ -14,6 +14,7 @@
 package com.ibm.watson.developer_cloud.speech_to_text.v1;
 
 import java.io.File;
+import java.io.InputStream;
 import java.util.List;
 
 import com.google.gson.JsonObject;
@@ -262,4 +263,16 @@ public SpeechResults recognize(File audio, String contentType, RecognizeOptions
     requestBuilder.withBody(RequestBody.create(MediaType.parse(contentType), audio));
     return executeRequest(requestBuilder.build(), SpeechResults.class);
   }
+
+  /**
+   * Recognizes using WebSockets.
+   * 
+   * @param audio the audio
+   * @param options the options
+   * @param delegate the delegate
+   */
+  public void recognizeWS(InputStream audio, RecognizeOptions options, RecognizeDelegate delegate) {
+    WebSocketClient webSocket = new WebSocketClient();
+    webSocket.recognize(audio, options, delegate);
+  }
 }