Merge pull request #82063 from jimxieJ/jimxie/update_diarization_feature

Update cts doc for differentiate speaker property

Author: v-andreaco

articles/cognitive-services/Speech-Service/conversation-transcription.md

@@ -50,10 +50,13 @@ This is a high-level overview of how Conversation Transcription works.
 ## Expected inputs
 
 - **Multi-channel audio stream** – For specification and design details, see [Microsoft Speech Device SDK Microphone](./speech-devices-sdk-microphone.md). To learn more or purchase a development kit, see [Get Microsoft Speech Device SDK](./get-speech-devices-sdk.md).
-- **User voice samples** – Conversation Transcription needs user profiles in advance of the conversation. You will need to collect audio recordings from each user, then send the recordings to the [Signature Generation Service](https://aka.ms/cts/signaturegenservice) to validate the audio and generate user profiles.
+- **User voice samples** – Conversation Transcription needs user profiles in advance of the conversation for speaker identification. You will need to collect audio recordings from each user, then send the recordings to the [Signature Generation Service](https://aka.ms/cts/signaturegenservice) to validate the audio and generate user profiles.
 
 > [!NOTE]
-> User voice samples are optional. Without this input, the transcription will show different speakers, but shown as "Speaker1", "Speaker2", etc. instead of recognizing as pre-enrolled specific speaker names.
+> User voice samples for voice signatures are required for speaker identification. Speakers who do not have voice samples will be recognized as "Unidentified". Unidentified speakers can still be differentiated when the `DifferentiateGuestSpeakers` property is enabled (see example below). The transcription output will then show speakers as "Guest_0", "Guest_1", etc. instead of recognizing as pre-enrolled specific speaker names.
+> ```csharp
+> config.SetProperty("DifferentiateGuestSpeakers", "true");
+> ```
 
 
 ## Real-time vs. asynchronous

articles/cognitive-services/Speech-Service/includes/how-to/conversation-transcription/real-time-csharp.md

@@ -107,6 +107,7 @@ This sample code does the following:
 * Creates a `ConversationTranscriber` using the constructor, and subscribes to the necessary events.
 * Adds participants to the conversation. The strings `voiceSignatureStringUser1` and `voiceSignatureStringUser2` should come as output from the steps above from the function `GetVoiceSignatureString()`.
 * Joins the conversation and begins transcription.
+* If you want to differentiate speakers without providing voice samples, please enable `DifferentiateGuestSpeakers` feature as in [Conversation Transcription Overview](../../../conversation-transcription.md). 
 
 > [!NOTE]
 > `AudioStreamReader` is a helper class you can get on [GitHub](https://github.com/Azure-Samples/cognitive-services-speech-sdk/blob/master/quickstart/csharp/dotnet/conversation-transcription/helloworld/AudioStreamReader.cs).
@@ -133,7 +134,9 @@ public static async Task TranscribeConversationsAsync(string voiceSignatureStrin
 
     var config = SpeechConfig.FromSubscription(subscriptionKey, region);
     config.SetProperty("ConversationTranscriptionInRoomAndOnline", "true");
-    // config.SpeechRecognitionLanguage = "zh-cn"; // en-us by default. This code specifies Chinese.
+
+    // en-us by default. Adding this code to specify other languages, like zh-cn.
+    // config.SpeechRecognitionLanguage = "zh-cn";
     var stopRecognition = new TaskCompletionSource<int>();
 
     using (var audioInput = AudioConfig.FromWavFileInput(filepath))

articles/cognitive-services/Speech-Service/includes/how-to/conversation-transcription/real-time-javascript.md

@@ -72,6 +72,7 @@ This sample code does the following:
 * Creates a `ConversationTranscriber` using the constructor.
 * Adds participants to the conversation. The strings `voiceSignatureStringUser1` and `voiceSignatureStringUser2` should come as output from the steps above.
 * Registers to events and begins transcription.
+* If you want to differentiate speakers without providing voice samples, please enable `DifferentiateGuestSpeakers` feature as in [Conversation Transcription Overview](../../../conversation-transcription.md). 
 
 ```javascript
 (function() {
@@ -93,6 +94,9 @@ This sample code does the following:
 
     var speechTranslationConfig = sdk.SpeechTranslationConfig.fromSubscription(subscriptionKey, region);
     var audioConfig = sdk.AudioConfig.fromStreamInput(pushStream);
+    speechTranslationConfig.setProperty("ConversationTranscriptionInRoomAndOnline", "true");
+
+    // en-us by default. Adding this code to specify other languages, like zh-cn.
     speechTranslationConfig.speechRecognitionLanguage = "en-US";
 
     // create conversation and transcriber