There seems to be some (limited) support for speaker diarization in Microsoft's batch pipeline, but I cannot find any reference to the same in the SDK (we're using Microsoft.CognitiveServices.Speech 1.13.0). Is there some way of requesting speaker diarization using the C# SDK that I'm not aware of? Alternatively, does anyone know if such support is planned in a future version?
1 Answers
Thanks for reaching out. Currently, Azure Speech Service Batch Speech-to-Text doesn't have SDK support (at the moment there's no public information on when support will be available). However, Azure Speech Service SDK's ConversationTranscriber API enables real-time speech recognition, speaker identification, and diarization (it's perfect for transcribing in-person meetings with the ability to distinguish speakers). The ConversationTranscriber API is supported for C# as well.
Related