Speaker Recognition without Feature Extraction Process

スポンサーリンク

概要

• 論文の詳細を見る

• By employing the dual Penalized Logistic Regression Machine (dPLRM), this paper explores a speaker identification method which does not require feature extraction process depending on a prior knowledge. The induction machine can discover implicitly speaker characteristics relevant to discrimination only from a set of training data by the mechanism of the kernel regression. Our text-independent speaker identification experiments with training data uttered by 1 0 male speakers in three different sessions show that the proposed method is competitive with the conventional Gaussian mixture model (GMM)-based method with 26-dimensional Mel-frequency cepstrum (MFCC) feature even though our method handle directly coarse data of 256-dimensional log-power spectrum. It is also shown that our method outperforms the GMM-based method especially as the amount of training data becomes smaller.

• 社団法人電子情報通信学会の論文
• 2004-12-13

著者

• MATSUI Tomoko

  The Institute of Statistical Mathematics

• TANABE Kunio

  The Institute of Statistical Mathematics

関連論文

• Speaker Recognition without Feature Extraction Process
• Speaker Recognition without Feature Extraction Process
• Local Convergence Properties of New Methods in Linear Programming
• Speaker Recognition without Feature Extraction Process
• Comparison of Methods for Topic Classification of Spoken Inquiries
• Evaluation Framework Design of Spoken Term Detection Study at the NTCIR-9 IR for Spoken Documents Task

スポンサーリンク