Chronological Self-Training for Real-Time Speaker Diarization
share
Diarization partitions an audio stream into segments based on the voices of the speakers. Real-time diarization systems that include an enrollment step should limit enrollment training samples to reduce user interaction time. Although training on a small number of samples yields poor performance, we show that the accuracy can be improved dramatically using a chronological self-training approach. We studied the tradeoff between training time and classification performance and found that 1 second is sufficient to reach over 95 each from 6 different languages and demonstrated average diarization error rates as low as 10
READ FULL TEXT