DOVER: A Method for Combining Diarization Outputs
This addresses the challenge of speaker diarization in multi-microphone meeting recordings, offering a novel solution for a domain-specific task, though it is incremental as it adapts an existing voting approach.
The paper tackles the problem of improving speaker diarization accuracy by introducing DOVER, a weighted voting algorithm that combines multiple diarization hypotheses, and finds it reduces diarization error rate consistently over average channel results and often outperforms the best single channel.
Speech recognition and other natural language tasks have long benefited from voting-based algorithms as a method to aggregate outputs from several systems to achieve a higher accuracy than any of the individual systems. Diarization, the task of segmenting an audio stream into speaker-homogeneous and co-indexed regions, has so far not seen the benefit of this strategy because the structure of the task does not lend itself to a simple voting approach. This paper presents DOVER (diarization output voting error reduction), an algorithm for weighted voting among diarization hypotheses, in the spirit of the ROVER algorithm for combining speech recognition hypotheses. We evaluate the algorithm for diarization of meeting recordings with multiple microphones, and find that it consistently reduces diarization error rate over the average of results from individual channels, and often improves on the single best channel chosen by an oracle.