Representing dynamic features of phonetic segment in an orthogonalized codebook of HMM based speech recognition system

  • Authors:

  • Tsuneo Nitta;Jun'ichi Iwasaki;Yasuyuki Masai;Hiroshi Matsu'ura

  • Affiliations:

  • Information Systems Engineering Laboratory, Toshiba Corp., Kawasaki, Japan;Information Systems Engineering Laboratory, Toshiba Corp., Kawasaki, Japan;Information Systems Engineering Laboratory, Toshiba Corp., Kawasaki, Japan;Information Systems Engineering Laboratory, Toshiba Corp., Kawasaki, Japan

  • Venue:
  • ICASSP'92 Proceedings of the 1992 IEEE international conference on Acoustics, speech and signal processing - Volume 1
  • Year:
  • 1992

Quantified Score

Hi-index 0.00

Visualization

Abstract

In this paper, we propose a new matrix quantization (MQ) algorithm named Statistical MQ (SMQ) using an orthogonalized phonetic segment codebook. The SMQ effectively incorporates pattern variations of each phonetic segment into the orthogonalized phonetic segment codebook, and transforms an input speech to a sequence of phonetic symbols which include about 700 types of phonetic segments. We also propose a simple SMQ-HMM algorithm called an Equally-counted K-best in which each phonetic event observed within the best K is equally counted in a model and output probabilities are smoothed without fuzzy rule. The proposed algorithm has been tested on a 546- word vocabulary data set uttered by 10 unknown speakers, using a real time recognition system, and has achieved the high performance of 96.5%.