Another update to the breaking change text, following feedback from Utkarsh

Author: Darren Cohen

articles/cognitive-services/Speech-Service/includes/release-notes/release-notes-sdk.md

@@ -10,7 +10,7 @@ ms.author: eur
 
 #### Breaking changes
 
-- Language Identification (preview) APIs have been simplified. If you update to Speech SDK 1.25 and see a build break, please visit the [Language Identification (preview)](/azure/cognitive-services/speech-service/language-identification) page to learn about the new property `SpeechServiceConnection_LanguageIdMode`. This single property replaces the two previous ones `SpeechServiceConnection_SingleLanguageIdPriority` and `SpeechServiceConnection_ContinuousLanguageIdPriority`. Prioritizing between low latency and high accuracy is no longer necessary following recent model improvements. Results are very accurate at low latency, therefore we removed the priority option. The only setting supported now is whether to run at-start or continuous Language Identification, when doing continuous speech recognition or translation.
+- Language Identification (preview) APIs have been simplified. If you update to Speech SDK 1.25 and see a build break, please visit the [Language Identification (preview)](/azure/cognitive-services/speech-service/language-identification) page to learn about the new property `SpeechServiceConnection_LanguageIdMode`. This single property replaces the two previous ones `SpeechServiceConnection_SingleLanguageIdPriority` and `SpeechServiceConnection_ContinuousLanguageIdPriority`. Prioritizing between low latency and high accuracy is no longer necessary following recent model improvements. Now, you only need to select whether to run at-start or continuous Language Identification when doing continuous speech recognition or translation.
 
 #### New features