We describe in this paper the experiences of the Johns Hopkins University team during the inaugural DIHARD diarization evaluation. This new task provided microphone recordings in a variety of difficult conditions and challenged researchers to fully consider all speaker activity, without the currently typical practices of unscored collars or ignored overlapping speaker segments. This paper explores several key aspects of currently state-of-the-art diarization methods, such as training data selection, signal bandwidth for feature extraction, representations of speech segments (i-vector versus x-vector), and domain-adaptive processing. In the end, our best system clustered x-vector embeddings trained on wideband microphone data followed by Variational-Bayesian refinement, and a speech activity detector specifically trained for this task with in-domain data was found to be the best performing. After presenting these decisions and their final result, we discuss lessons learned and remaining challenges within the lens of this new approach to diarization performance measurement.
|ジャーナル||Proceedings of the Annual Conference of the International Speech Communication Association, INTERSPEECH|
|出版ステータス||Published - 2018|
|イベント||19th Annual Conference of the International Speech Communication, INTERSPEECH 2018 - Hyderabad, India|
継続期間: 2018 9月 2 → 2018 9月 6
ASJC Scopus subject areas