Feature extraction for speech recognition based on orthogonal acoustic-feature planes and LDA
Author:
- 1 January 1999
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 1 (15206149) , 421-424 vol.1
Abstract
This paper describes an attempt to extract multiple topological structures, hidden in time-spectrum (TS) patterns, by using multiple mapping operators, and to incorporate the operators into the feature extractor of a speech recognition system. In the previous work, the author proposed a novel feature extraction method based on MAFP/KLT (MAFP: multiple acoustic-feature planes), in which 3/spl times/3 derivative filters were used for mapping operators, and showed that the method achieved significant improvement in preliminary experiments. In this paper, firstly, the mapping operators are directly extracted in the form of a 3/spl times/3 orthogonal basis from a speech database. Next, the operators are evaluated, together with 3/spl times/3 simplified operators modeled on the orthogonal basis. Finally, after comparing the experimental results, the author proposes an effective feature extraction method based on MAFP/LDA, in which a Sobel filter is used for mapping operators.Keywords
This publication has 3 references indexed in Scilit:
- Discriminative learning for minimum error classification (pattern recognition)IEEE Transactions on Signal Processing, 1992
- Speaker-independent isolated word recognition using dynamic features of speech spectrumIEEE Transactions on Acoustics, Speech, and Signal Processing, 1986
- A survey of edge detection techniquesComputer Graphics and Image Processing, 1975