Acoustic Model Adaptation by Selective Training Using 2-Stage Clustering

概要

論文の詳細を見る
This paper proposes a method of constructing acoustic models from training data clustered in two stages. The first stage generates cluster models from small-scale training data gathered form a target task. The second stage clusters a large-scale database based on the cluster models. In decoding, the best acoustic model is selected from all the acoustic models based on the GMM likelihood using some initial frames of an input utterance. Broadcast news transcription experiments showed that the proposed models achieved a word error reduction of 20% and a processing time reduction of 22%, compared with a non-clustered model.
社団法人電子情報通信学会の論文
2002-02-01