Discriminative training

スポンサーリンク

概要

• 論文の詳細を見る

• We address in this paper one of the prominent problems in pattern recognition, namely minimization of classification/recognition error rate. We propose a unconventional approach and a new formulation of the problem aiming at directly achieving a minimum classification error performance. The approach is called discriminative training which differs from the traditional statistical pattern recognition approach in its objective. Unlike the Bayesian framework, the new method does not require estimation of probability distributions which usually cannot be reliably obtained. The new method has been applied in various experimental studies with good results, some of which are high-lighted in the paper to demonstrate the effectiveness of the new method. A board range of problems can benefit from this new formulation.

• 社団法人日本音響学会の論文

著者

• Juang Biing-hwang

  At&ampt Bell Laboratories

• Katagiri Shigeru

  ATR Auditory and Visual Perception Research Laboratories.

• Katagiri Shigeru

  Atr Auditory And Visual Perception Research Laboratories

関連論文

• A Minimum Error Approach to Spotting-Based Pattern Recognition
• GPD training of dynamic programming-based speech recognizers
• Discriminative training
• A hybrid speech recognition system using HMMs with an LVQ-trained codebook

スポンサーリンク