講演名 2004/12/13
Reformulating the HMM as a Trajectory Model
,
PDFダウンロードページ PDFダウンロードページへ
抄録(和)
抄録(英) We have shown that the HMM whose state output vector includes static and dynamic feature parameters can be reformulated as a trajectory model by imposing the explicit relationship between the static and dynamic features. The derived model, referred to as "trajectory HMM," can alleviate the limitations of HMMs: i) constant statistics within an HMM state and ii) independence assumption of state output probabilities. In this paper, we first summarize the definition and the training algorithm. Then, to show that the trajectory HMM is a proper generative model, we derive a new algorithm for sampling from the trajectory model, and show the result of an illustrative experiment. A speech recognition experiment demonstrates the consistency between training and decoding criteria is essential: the model should not only be traind as a trajectory model but also be used as a trajectory model in decoding, even though the trajectory model has the same parameterization as the standard HMM.
キーワード(和)
キーワード(英) HMM / speech recognition / speech synthesis / trajectory model / dynamic feature
資料番号 NLC2004-48,SP2004-88
発行日

研究会情報
研究会 SP
開催期間 2004/12/13(から1日開催)
開催地(和)
開催地(英)
テーマ(和)
テーマ(英)
委員長氏名(和)
委員長氏名(英)
副委員長氏名(和)
副委員長氏名(英)
幹事氏名(和)
幹事氏名(英)
幹事補佐氏名(和)
幹事補佐氏名(英)

講演論文情報詳細
申込み研究会 Speech (SP)
本文の言語 ENG
タイトル(和)
サブタイトル(和)
タイトル(英) Reformulating the HMM as a Trajectory Model
サブタイトル(和)
キーワード(1)(和/英) / HMM
第 1 著者 氏名(和/英) / Keiichi TOKUDA
第 1 著者 所属(和/英)
Graduate School of Engineering, Nagoya Institute of Technology
発表年月日 2004/12/13
資料番号 NLC2004-48,SP2004-88
巻番号(vol) vol.104
号番号(no) 541
ページ範囲 pp.-
ページ数 6
発行日