feat: add speaker_tag to WordInfo

.github/ISSUE_TEMPLATE/bug_report.md

@@ -21,7 +21,7 @@ If you are still having issues, please include as much information as possible:
    General, Core, and Other are also allowed as types
 2. OS type and version:
 3. Java version:
-4. google-cloud-speect version(s):
+4. google-cloud-speech version(s):
 
 #### Steps to reproduce
 

.kokoro/continuous/propose_release.sh

@@ -22,7 +22,7 @@ if [ -f ${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-url-release-please ]; th
   # Groom the release PR as new commits are merged.
   npx release-please release-pr --token=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-token-release-please \
     --repo-url=googleapis/java-speech \
-    --package-name="google-cloud-speect" \
+    --package-name="google-cloud-speech" \
     --api-url=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-url-release-please \
     --proxy-key=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-key-release-please \
     --release-type=java-yoshi

.kokoro/release/bump_snapshot.sh

@@ -22,7 +22,7 @@ if [ -f ${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-url-release-please ]; th
   # Groom the snapshot release PR immediately after publishing a release
   npx release-please release-pr --token=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-token-release-please \
     --repo-url=googleapis/java-speech \
-    --package-name="google-cloud-speect" \
+    --package-name="google-cloud-speech" \
     --api-url=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-url-release-please \
     --proxy-key=${KOKORO_KEYSTORE_DIR}/73713_github-magic-proxy-key-release-please \
     --snapshot \

.kokoro/release/drop.cfg

@@ -4,6 +4,3 @@ env_vars: {
   key: "TRAMPOLINE_BUILD_FILE"
   value: "github/java-speech/.kokoro/release/drop.sh"
 }
-
-# Download staging properties file.
-gfile_resources: "/bigstore/cloud-devrel-kokoro-resources/java/releases/java-speech"

.kokoro/release/promote.cfg

@@ -4,7 +4,3 @@ env_vars: {
   key: "TRAMPOLINE_BUILD_FILE"
   value: "github/java-speech/.kokoro/release/promote.sh"
 }
-
-# Download staging properties file.
-gfile_resources: "/bigstore/cloud-devrel-kokoro-resources/java/releases/java-speech"
-

.kokoro/release/publish_javadoc.sh

@@ -33,7 +33,7 @@ python3 -m pip install gcp-docuploader
 # compile all packages
 mvn clean install -B -DskipTests=true
 
-NAME=google-cloud-speect
+NAME=google-cloud-speech
 VERSION=$(grep ${NAME}: versions.txt | cut -d: -f3)
 
 # build the docs

google-cloud-speech/src/test/java/com/google/cloud/speech/v1/SpeechSmokeTest.java

@@ -53,7 +53,7 @@ public static void executeNoCatch() throws Exception {
               .setSampleRateHertz(sampleRateHertz)
               .setEncoding(encoding)
               .build();
-      String uri = "gs://gapic-toolkit/hello.flac";
+      String uri = "gs://cloud-samples-data/speech/brooklyn_bridge.flac";
       RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(uri).build();
 
       RecognizeResponse response = client.recognize(config, audio);

google-cloud-speech/src/test/java/com/google/cloud/speech/v1p1beta1/SpeechSmokeTest.java

@@ -53,7 +53,7 @@ public static void executeNoCatch() throws Exception {
               .setSampleRateHertz(sampleRateHertz)
               .setEncoding(encoding)
               .build();
-      String uri = "gs://gapic-toolkit/hello.flac";
+      String uri = "gs://cloud-samples-data/speech/brooklyn_bridge.flac";
       RecognitionAudio audio = RecognitionAudio.newBuilder().setUri(uri).build();
 
       RecognizeResponse response = client.recognize(config, audio);

proto-google-cloud-speech-v1/src/main/java/com/google/cloud/speech/v1/SpeakerDiarizationConfig.java

@@ -174,15 +174,13 @@ public int getMaxSpeakerCount() {
    *
    *
    * <pre>
-   * A distinct integer value is assigned for every speaker within
-   * the audio. This field specifies which one of those speakers was detected to
-   * have spoken this word. Value ranges from '1' to diarization_speaker_count.
-   * speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-   * top alternative.
+   * Unused.
    * </pre>
    *
-   * <code>int32 speaker_tag = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];</code>
+   * <code>int32 speaker_tag = 5 [deprecated = true, (.google.api.field_behavior) = OUTPUT_ONLY];
+   * </code>
    */
+  @java.lang.Deprecated
   public int getSpeakerTag() {
     return speakerTag_;
   }
@@ -704,31 +702,27 @@ public Builder clearMaxSpeakerCount() {
      *
      *
      * <pre>
-     * A distinct integer value is assigned for every speaker within
-     * the audio. This field specifies which one of those speakers was detected to
-     * have spoken this word. Value ranges from '1' to diarization_speaker_count.
-     * speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-     * top alternative.
+     * Unused.
      * </pre>
      *
-     * <code>int32 speaker_tag = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];</code>
+     * <code>int32 speaker_tag = 5 [deprecated = true, (.google.api.field_behavior) = OUTPUT_ONLY];
+     * </code>
      */
+    @java.lang.Deprecated
     public int getSpeakerTag() {
       return speakerTag_;
     }
     /**
      *
      *
      * <pre>
-     * A distinct integer value is assigned for every speaker within
-     * the audio. This field specifies which one of those speakers was detected to
-     * have spoken this word. Value ranges from '1' to diarization_speaker_count.
-     * speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-     * top alternative.
+     * Unused.
      * </pre>
      *
-     * <code>int32 speaker_tag = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];</code>
+     * <code>int32 speaker_tag = 5 [deprecated = true, (.google.api.field_behavior) = OUTPUT_ONLY];
+     * </code>
      */
+    @java.lang.Deprecated
     public Builder setSpeakerTag(int value) {
 
       speakerTag_ = value;
@@ -739,15 +733,13 @@ public Builder setSpeakerTag(int value) {
      *
      *
      * <pre>
-     * A distinct integer value is assigned for every speaker within
-     * the audio. This field specifies which one of those speakers was detected to
-     * have spoken this word. Value ranges from '1' to diarization_speaker_count.
-     * speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-     * top alternative.
+     * Unused.
      * </pre>
      *
-     * <code>int32 speaker_tag = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];</code>
+     * <code>int32 speaker_tag = 5 [deprecated = true, (.google.api.field_behavior) = OUTPUT_ONLY];
+     * </code>
      */
+    @java.lang.Deprecated
     public Builder clearSpeakerTag() {
 
       speakerTag_ = 0;

proto-google-cloud-speech-v1/src/main/java/com/google/cloud/speech/v1/SpeakerDiarizationConfigOrBuilder.java

@@ -66,14 +66,12 @@ public interface SpeakerDiarizationConfigOrBuilder
    *
    *
    * <pre>
-   * A distinct integer value is assigned for every speaker within
-   * the audio. This field specifies which one of those speakers was detected to
-   * have spoken this word. Value ranges from '1' to diarization_speaker_count.
-   * speaker_tag is set if enable_speaker_diarization = 'true' and only in the
-   * top alternative.
+   * Unused.
    * </pre>
    *
-   * <code>int32 speaker_tag = 5 [(.google.api.field_behavior) = OUTPUT_ONLY];</code>
+   * <code>int32 speaker_tag = 5 [deprecated = true, (.google.api.field_behavior) = OUTPUT_ONLY];
+   * </code>
    */
+  @java.lang.Deprecated
   int getSpeakerTag();
 }

proto-google-cloud-speech-v1/src/main/java/com/google/cloud/speech/v1/SpeechProto.java

@@ -145,89 +145,90 @@ public static com.google.protobuf.Descriptors.FileDescriptor getDescriptor() {
           + "ioEncoding\022\030\n\024ENCODING_UNSPECIFIED\020\000\022\014\n\010"
           + "LINEAR16\020\001\022\010\n\004FLAC\020\002\022\t\n\005MULAW\020\003\022\007\n\003AMR\020\004"
           + "\022\n\n\006AMR_WB\020\005\022\014\n\010OGG_OPUS\020\006\022\032\n\026SPEEX_WITH"
-          + "_HEADER_BYTE\020\007\"\216\001\n\030SpeakerDiarizationCon"
+          + "_HEADER_BYTE\020\007\"\220\001\n\030SpeakerDiarizationCon"
           + "fig\022\"\n\032enable_speaker_diarization\030\001 \001(\010\022"
           + "\031\n\021min_speaker_count\030\002 \001(\005\022\031\n\021max_speake"
-          + "r_count\030\003 \001(\005\022\030\n\013speaker_tag\030\005 \001(\005B\003\340A\003\""
-          + "\240\010\n\023RecognitionMetadata\022U\n\020interaction_t"
-          + "ype\030\001 \001(\0162;.google.cloud.speech.v1.Recog"
-          + "nitionMetadata.InteractionType\022$\n\034indust"
-          + "ry_naics_code_of_audio\030\003 \001(\r\022[\n\023micropho"
-          + "ne_distance\030\004 \001(\0162>.google.cloud.speech."
-          + "v1.RecognitionMetadata.MicrophoneDistanc"
-          + "e\022Z\n\023original_media_type\030\005 \001(\0162=.google."
-          + "cloud.speech.v1.RecognitionMetadata.Orig"
-          + "inalMediaType\022^\n\025recording_device_type\030\006"
-          + " \001(\0162?.google.cloud.speech.v1.Recognitio"
-          + "nMetadata.RecordingDeviceType\022\035\n\025recordi"
-          + "ng_device_name\030\007 \001(\t\022\032\n\022original_mime_ty"
-          + "pe\030\010 \001(\t\022\023\n\013audio_topic\030\n \001(\t\"\305\001\n\017Intera"
-          + "ctionType\022 \n\034INTERACTION_TYPE_UNSPECIFIE"
-          + "D\020\000\022\016\n\nDISCUSSION\020\001\022\020\n\014PRESENTATION\020\002\022\016\n"
-          + "\nPHONE_CALL\020\003\022\r\n\tVOICEMAIL\020\004\022\033\n\027PROFESSI"
-          + "ONALLY_PRODUCED\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021\n\rV"
-          + "OICE_COMMAND\020\007\022\r\n\tDICTATION\020\010\"d\n\022Microph"
-          + "oneDistance\022#\n\037MICROPHONE_DISTANCE_UNSPE"
-          + "CIFIED\020\000\022\r\n\tNEARFIELD\020\001\022\014\n\010MIDFIELD\020\002\022\014\n"
-          + "\010FARFIELD\020\003\"N\n\021OriginalMediaType\022#\n\037ORIG"
-          + "INAL_MEDIA_TYPE_UNSPECIFIED\020\000\022\t\n\005AUDIO\020\001"
-          + "\022\t\n\005VIDEO\020\002\"\244\001\n\023RecordingDeviceType\022%\n!R"
-          + "ECORDING_DEVICE_TYPE_UNSPECIFIED\020\000\022\016\n\nSM"
-          + "ARTPHONE\020\001\022\006\n\002PC\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n\007VE"
-          + "HICLE\020\004\022\030\n\024OTHER_OUTDOOR_DEVICE\020\005\022\027\n\023OTH"
-          + "ER_INDOOR_DEVICE\020\006\" \n\rSpeechContext\022\017\n\007p"
-          + "hrases\030\001 \003(\t\"D\n\020RecognitionAudio\022\021\n\007cont"
-          + "ent\030\001 \001(\014H\000\022\r\n\003uri\030\002 \001(\tH\000B\016\n\014audio_sour"
-          + "ce\"U\n\021RecognizeResponse\022@\n\007results\030\002 \003(\013"
-          + "2/.google.cloud.speech.v1.SpeechRecognit"
-          + "ionResult\"`\n\034LongRunningRecognizeRespons"
-          + "e\022@\n\007results\030\002 \003(\0132/.google.cloud.speech"
-          + ".v1.SpeechRecognitionResult\"\236\001\n\034LongRunn"
-          + "ingRecognizeMetadata\022\030\n\020progress_percent"
-          + "\030\001 \001(\005\022.\n\nstart_time\030\002 \001(\0132\032.google.prot"
-          + "obuf.Timestamp\0224\n\020last_update_time\030\003 \001(\013"
-          + "2\032.google.protobuf.Timestamp\"\261\002\n\032Streami"
-          + "ngRecognizeResponse\022!\n\005error\030\001 \001(\0132\022.goo"
-          + "gle.rpc.Status\022C\n\007results\030\002 \003(\01322.google"
-          + ".cloud.speech.v1.StreamingRecognitionRes"
-          + "ult\022]\n\021speech_event_type\030\004 \001(\0162B.google."
-          + "cloud.speech.v1.StreamingRecognizeRespon"
-          + "se.SpeechEventType\"L\n\017SpeechEventType\022\034\n"
-          + "\030SPEECH_EVENT_UNSPECIFIED\020\000\022\033\n\027END_OF_SI"
-          + "NGLE_UTTERANCE\020\001\"\362\001\n\032StreamingRecognitio"
-          + "nResult\022J\n\014alternatives\030\001 \003(\01324.google.c"
-          + "loud.speech.v1.SpeechRecognitionAlternat"
-          + "ive\022\020\n\010is_final\030\002 \001(\010\022\021\n\tstability\030\003 \001(\002"
-          + "\0222\n\017result_end_time\030\004 \001(\0132\031.google.proto"
-          + "buf.Duration\022\023\n\013channel_tag\030\005 \001(\005\022\032\n\rlan"
-          + "guage_code\030\006 \001(\tB\003\340A\003\"z\n\027SpeechRecogniti"
-          + "onResult\022J\n\014alternatives\030\001 \003(\01324.google."
-          + "cloud.speech.v1.SpeechRecognitionAlterna"
-          + "tive\022\023\n\013channel_tag\030\002 \001(\005\"w\n\034SpeechRecog"
-          + "nitionAlternative\022\022\n\ntranscript\030\001 \001(\t\022\022\n"
-          + "\nconfidence\030\002 \001(\002\022/\n\005words\030\003 \003(\0132 .googl"
-          + "e.cloud.speech.v1.WordInfo\"t\n\010WordInfo\022-"
-          + "\n\nstart_time\030\001 \001(\0132\031.google.protobuf.Dur"
-          + "ation\022+\n\010end_time\030\002 \001(\0132\031.google.protobu"
-          + "f.Duration\022\014\n\004word\030\003 \001(\t2\321\004\n\006Speech\022\220\001\n\t"
-          + "Recognize\022(.google.cloud.speech.v1.Recog"
-          + "nizeRequest\032).google.cloud.speech.v1.Rec"
-          + "ognizeResponse\".\202\323\344\223\002\031\"\024/v1/speech:recog"
-          + "nize:\001*\332A\014config,audio\022\344\001\n\024LongRunningRe"
-          + "cognize\0223.google.cloud.speech.v1.LongRun"
-          + "ningRecognizeRequest\032\035.google.longrunnin"
-          + "g.Operation\"x\202\323\344\223\002$\"\037/v1/speech:longrunn"
-          + "ingrecognize:\001*\332A\014config,audio\312A<\n\034LongR"
-          + "unningRecognizeResponse\022\034LongRunningReco"
-          + "gnizeMetadata\022\201\001\n\022StreamingRecognize\0221.g"
+          + "r_count\030\003 \001(\005\022\032\n\013speaker_tag\030\005 \001(\005B\005\030\001\340A"
+          + "\003\"\240\010\n\023RecognitionMetadata\022U\n\020interaction"
+          + "_type\030\001 \001(\0162;.google.cloud.speech.v1.Rec"
+          + "ognitionMetadata.InteractionType\022$\n\034indu"
+          + "stry_naics_code_of_audio\030\003 \001(\r\022[\n\023microp"
+          + "hone_distance\030\004 \001(\0162>.google.cloud.speec"
+          + "h.v1.RecognitionMetadata.MicrophoneDista"
+          + "nce\022Z\n\023original_media_type\030\005 \001(\0162=.googl"
+          + "e.cloud.speech.v1.RecognitionMetadata.Or"
+          + "iginalMediaType\022^\n\025recording_device_type"
+          + "\030\006 \001(\0162?.google.cloud.speech.v1.Recognit"
+          + "ionMetadata.RecordingDeviceType\022\035\n\025recor"
+          + "ding_device_name\030\007 \001(\t\022\032\n\022original_mime_"
+          + "type\030\010 \001(\t\022\023\n\013audio_topic\030\n \001(\t\"\305\001\n\017Inte"
+          + "ractionType\022 \n\034INTERACTION_TYPE_UNSPECIF"
+          + "IED\020\000\022\016\n\nDISCUSSION\020\001\022\020\n\014PRESENTATION\020\002\022"
+          + "\016\n\nPHONE_CALL\020\003\022\r\n\tVOICEMAIL\020\004\022\033\n\027PROFES"
+          + "SIONALLY_PRODUCED\020\005\022\020\n\014VOICE_SEARCH\020\006\022\021\n"
+          + "\rVOICE_COMMAND\020\007\022\r\n\tDICTATION\020\010\"d\n\022Micro"
+          + "phoneDistance\022#\n\037MICROPHONE_DISTANCE_UNS"
+          + "PECIFIED\020\000\022\r\n\tNEARFIELD\020\001\022\014\n\010MIDFIELD\020\002\022"
+          + "\014\n\010FARFIELD\020\003\"N\n\021OriginalMediaType\022#\n\037OR"
+          + "IGINAL_MEDIA_TYPE_UNSPECIFIED\020\000\022\t\n\005AUDIO"
+          + "\020\001\022\t\n\005VIDEO\020\002\"\244\001\n\023RecordingDeviceType\022%\n"
+          + "!RECORDING_DEVICE_TYPE_UNSPECIFIED\020\000\022\016\n\n"
+          + "SMARTPHONE\020\001\022\006\n\002PC\020\002\022\016\n\nPHONE_LINE\020\003\022\013\n\007"
+          + "VEHICLE\020\004\022\030\n\024OTHER_OUTDOOR_DEVICE\020\005\022\027\n\023O"
+          + "THER_INDOOR_DEVICE\020\006\" \n\rSpeechContext\022\017\n"
+          + "\007phrases\030\001 \003(\t\"D\n\020RecognitionAudio\022\021\n\007co"
+          + "ntent\030\001 \001(\014H\000\022\r\n\003uri\030\002 \001(\tH\000B\016\n\014audio_so"
+          + "urce\"U\n\021RecognizeResponse\022@\n\007results\030\002 \003"
+          + "(\0132/.google.cloud.speech.v1.SpeechRecogn"
+          + "itionResult\"`\n\034LongRunningRecognizeRespo"
+          + "nse\022@\n\007results\030\002 \003(\0132/.google.cloud.spee"
+          + "ch.v1.SpeechRecognitionResult\"\236\001\n\034LongRu"
+          + "nningRecognizeMetadata\022\030\n\020progress_perce"
+          + "nt\030\001 \001(\005\022.\n\nstart_time\030\002 \001(\0132\032.google.pr"
+          + "otobuf.Timestamp\0224\n\020last_update_time\030\003 \001"
+          + "(\0132\032.google.protobuf.Timestamp\"\261\002\n\032Strea"
+          + "mingRecognizeResponse\022!\n\005error\030\001 \001(\0132\022.g"
+          + "oogle.rpc.Status\022C\n\007results\030\002 \003(\01322.goog"
+          + "le.cloud.speech.v1.StreamingRecognitionR"
+          + "esult\022]\n\021speech_event_type\030\004 \001(\0162B.googl"
+          + "e.cloud.speech.v1.StreamingRecognizeResp"
+          + "onse.SpeechEventType\"L\n\017SpeechEventType\022"
+          + "\034\n\030SPEECH_EVENT_UNSPECIFIED\020\000\022\033\n\027END_OF_"
+          + "SINGLE_UTTERANCE\020\001\"\362\001\n\032StreamingRecognit"
+          + "ionResult\022J\n\014alternatives\030\001 \003(\01324.google"
+          + ".cloud.speech.v1.SpeechRecognitionAltern"
+          + "ative\022\020\n\010is_final\030\002 \001(\010\022\021\n\tstability\030\003 \001"
+          + "(\002\0222\n\017result_end_time\030\004 \001(\0132\031.google.pro"
+          + "tobuf.Duration\022\023\n\013channel_tag\030\005 \001(\005\022\032\n\rl"
+          + "anguage_code\030\006 \001(\tB\003\340A\003\"z\n\027SpeechRecogni"
+          + "tionResult\022J\n\014alternatives\030\001 \003(\01324.googl"
+          + "e.cloud.speech.v1.SpeechRecognitionAlter"
+          + "native\022\023\n\013channel_tag\030\002 \001(\005\"w\n\034SpeechRec"
+          + "ognitionAlternative\022\022\n\ntranscript\030\001 \001(\t\022"
+          + "\022\n\nconfidence\030\002 \001(\002\022/\n\005words\030\003 \003(\0132 .goo"
+          + "gle.cloud.speech.v1.WordInfo\"\216\001\n\010WordInf"
+          + "o\022-\n\nstart_time\030\001 \001(\0132\031.google.protobuf."
+          + "Duration\022+\n\010end_time\030\002 \001(\0132\031.google.prot"
+          + "obuf.Duration\022\014\n\004word\030\003 \001(\t\022\030\n\013speaker_t"
+          + "ag\030\005 \001(\005B\003\340A\0032\321\004\n\006Speech\022\220\001\n\tRecognize\022("
+          + ".google.cloud.speech.v1.RecognizeRequest"
+          + "\032).google.cloud.speech.v1.RecognizeRespo"
+          + "nse\".\202\323\344\223\002\031\"\024/v1/speech:recognize:\001*\332A\014c"
+          + "onfig,audio\022\344\001\n\024LongRunningRecognize\0223.g"
+          + "oogle.cloud.speech.v1.LongRunningRecogni"
+          + "zeRequest\032\035.google.longrunning.Operation"
+          + "\"x\202\323\344\223\002$\"\037/v1/speech:longrunningrecogniz"
+          + "e:\001*\332A\014config,audio\312A<\n\034LongRunningRecog"
+          + "nizeResponse\022\034LongRunningRecognizeMetada"
+          + "ta\022\201\001\n\022StreamingRecognize\0221.google.cloud"
+          + ".speech.v1.StreamingRecognizeRequest\0322.g"
           + "oogle.cloud.speech.v1.StreamingRecognize"
-          + "Request\0322.google.cloud.speech.v1.Streami"
-          + "ngRecognizeResponse\"\000(\0010\001\032I\312A\025speech.goo"
-          + "gleapis.com\322A.https://www.googleapis.com"
-          + "/auth/cloud-platformBr\n\032com.google.cloud"
-          + ".speech.v1B\013SpeechProtoP\001Z<google.golang"
-          + ".org/genproto/googleapis/cloud/speech/v1"
-          + ";speech\370\001\001\242\002\003GCSb\006proto3"
+          + "Response\"\000(\0010\001\032I\312A\025speech.googleapis.com"
+          + "\322A.https://www.googleapis.com/auth/cloud"
+          + "-platformBr\n\032com.google.cloud.speech.v1B"
+          + "\013SpeechProtoP\001Z<google.golang.org/genpro"
+          + "to/googleapis/cloud/speech/v1;speech\370\001\001\242"
+          + "\002\003GCSb\006proto3"
     };
     com.google.protobuf.Descriptors.FileDescriptor.InternalDescriptorAssigner assigner =
         new com.google.protobuf.Descriptors.FileDescriptor.InternalDescriptorAssigner() {
@@ -404,7 +405,7 @@ public com.google.protobuf.ExtensionRegistry assignDescriptors(
         new com.google.protobuf.GeneratedMessageV3.FieldAccessorTable(
             internal_static_google_cloud_speech_v1_WordInfo_descriptor,
             new java.lang.String[] {
-              "StartTime", "EndTime", "Word",
+              "StartTime", "EndTime", "Word", "SpeakerTag",
             });
     com.google.protobuf.ExtensionRegistry registry =
         com.google.protobuf.ExtensionRegistry.newInstance();