How to improve accuracy of speaker diarization?

Question

What steps can I take to improve AWS Transcribe's Speaker Diarization accuracy?

Unfortunately the algorithm is not doing a great job of correctly identifying who is talking, even with a clean audio recording. Its even having trouble distinguishing between a man and a woman's voice.

Much appreciated!

Answer

Other than a clean audio recording, I'd optimize the following factors:
* When using custom vocabularies: keep the list small, and provide IPA pronunciations if you can.
* When using real-time streams: two to five speakers seem best.
* When using an audio source: set the "Maximum number of speaker" to the actual number of speakers in the file.

For sources and more information:  
https://aws.amazon.com/transcribe/faqs/  
https://docs.aws.amazon.com/transcribe/latest/dg/diarization.html

How to improve accuracy of speaker diarization?

Conteúdo relevante