ダウンロード数: 435

このアイテムのファイル:
ファイル 記述 サイズフォーマット 
TSA.2005.848890.pdf470.14 kBAdobe PDF見る/開く
タイトル: Speaker model selection based on the Bayesian information criterion applied to unsupervised speaker indexing
著者: Nishida, M.
Kawahara, T.  kyouindb  KAKEN_id  orcid https://orcid.org/0000-0002-2686-2296 (unconfirmed)
著者名の別形: 河原, 達也
発行日: Jul-2005
出版者: IEEE
誌名: IEEE Transactions on Speech and Audio Processing
巻: 13
号: 4
開始ページ: 583
終了ページ: 592
抄録: In conventional speaker recognition tasks, the amount of training data is almost the same for each speaker, and the speaker model structure is uniform and specified manually according to the nature of the task and the available size of the training data. In real-world speech data such as telephone conversations and meetings, however, serious problems arise in applying a uniform model because variations in the utterance durations of speakers are large, with numerous short utterances. We therefore propose a flexible framework in which an optimal speaker model (GMM or VQ) is automatically selected based on the Bayesian Information Criterion (BIC) according to the amount of training data available. The framework makes it possible to use a discrete model when the data is sparse, and to seamlessly switch to a continuous model after a large amount of data is obtained. The proposed framework was implemented in unsupervised speaker indexing of a discussion audio. For a real discussion archive with a total duration of 10 hours, we demonstrate that the proposed method has higher indexing performance than that of conventional methods. The speaker index is also used to adapt a speaker-independent acoustic model to each participant for automatic transcription of the discussion. We demonstrate that speaker indexing with our method is sufficiently accurate for adaptation of the acoustic model.
著作権等: © 2005 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other users, including reprinting/ republishing this material for advertising or promotional purposes, creating new collective works for resale or redistribution to servers or lists, or reuse of any copyrighted components of this work in other works.
URI: http://hdl.handle.net/2433/128903
DOI(出版社版): 10.1109/TSA.2005.848890
出現コレクション:学術雑誌掲載論文等

アイテムの詳細レコードを表示する

Export to RefWorks


出力フォーマット 


このリポジトリに保管されているアイテムはすべて著作権により保護されています。