Improving The Feature Representation of Speech Signals by Self-Organization
碩士 === 國立臺灣大學 === 資訊工程研究所 === 82 === In this paper, a continuous Mandarin speech recognition system in which neural network is applied to the designs of specific modules is described. Fifteen-five Melscale spectral coefficients are used to...
Main Authors: | Chien, Shuen-Der, 簡順德 |
---|---|
Other Authors: | Liou, Cheng-Yuan |
Format: | Others |
Language: | zh-TW |
Published: |
1994
|
Online Access: | http://ndltd.ncl.edu.tw/handle/27455552395855493397 |
Similar Items
-
Improved speech enhancement with on-line signal and noise spectrum estimation
by: Tsai-Kan Chien, et al. -
Optimal Wavelets for Speech Signal Representations
by: Shonda L. Walker, et al.
Published: (2003-08-01) -
An improved method in speech signal input representation based on DTW technique for NN speech recognition system
by: Sudirman, Rubita, et al.
Published: (2007) -
Electrocorticographic Representations of Segmental Features in Continuous Speech
by: Fabien eLotte, et al.
Published: (2015-02-01) -
A linguistic feature representation of the speech waveform
by: Eide, Ellen Marie
Published: (2005)