Robust Speech Recognition with Two-dimensional Frame-and-feature Weighting and Modulation Spectrum Normalization
碩士 === 國立臺灣大學 === 電信工程學研究所 === 100 === In this paper we propose a new approach of two-dimensional frame-and-feature weighted Viterbi decoding performed at the recognizer back-end for robust speech recognition. The frame weighting is based on an Support Vector Machine (SVM) classifier considering the...
Main Authors: | Yang Chang, 張暘 |
---|---|
Other Authors: | 李琳山 |
Format: | Others |
Language: | zh-TW |
Published: |
2012
|
Online Access: | http://ndltd.ncl.edu.tw/handle/80127356350852988068 |
Similar Items
-
Modulation Spectrum Normalization for Robust Speech Recognition
by: Yu-Hung Yang, et al.
Published: (2013) -
Exploring Modulation Spectrum Normalization for Robust Speech Recognition
by: Wen-Yi Chu, et al.
Published: (2011) -
Study of modulation spectrum normalization for robust speech recognition
by: Chien-Chou Lai, et al.
Published: (2011) -
Study of Modulation Spectrum Normalization Techniques for Robust Speech Recognition
by: Chieh-cheng Wang, et al.
Published: (2008) -
The study of modulation spectrum exponential weighting for robust speech recognition
by: Yi-Cheng Lian, et al.
Published: (2012)