M
Masoumeh P. Ghaemmaghami
Researcher at Islamic Azad University
Publications - 5
Citations - 173
Masoumeh P. Ghaemmaghami is an academic researcher from Islamic Azad University. The author has contributed to research in topics: TIMIT & Feature extraction. The author has an hindex of 5, co-authored 5 publications receiving 152 citations. Previous affiliations of Masoumeh P. Ghaemmaghami include Islamic Azad University, Science and Research Branch, Tehran.
Papers
More filters
Journal ArticleDOI
Feature extraction using discrete cosine transform and discrimination power analysis with a face recognition technology
TL;DR: The proposed approach, against the conventional approaches, is data-dependent and is able to find DCs on each database, and a new modification of PCA and LDA is proposed namely, DPA-PCA andDPA-LDA, which achieve the performance of PC a/LDA or better with less complexity.
Proceedings ArticleDOI
Automatic meter classification in Persian poetries using support vector machines
TL;DR: The proposed meter classification system for Persian poems based on features extracted from uttered poem shows 91% accuracy in three top meter style choices and is robust against syllables insertion, deletion or classification.
Proceedings ArticleDOI
Robust phoneme recognition using MLP neural networks in various domains of MFCC features
TL;DR: This paper focuses on enhancing MFCC features using a set of MLP NN in order to improve phoneme recognition accuracy under different noise types and SNRs and shows that the highest improvement is achievable in LOG domain.
Proceedings ArticleDOI
Robust speech recognition using MLP neural network in log-spectral domain
TL;DR: An efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion, employed to minimize the difference between noisy and clean speech is proposed.
Proceedings ArticleDOI
Noise reduction algorithm for robust speech recognition using MLP neural network
TL;DR: An efficient and effective nonlinear feature domain noise suppression algorithm, motivated by the minimum mean square error (MMSE) optimization criterion, that minimizes the difference between noisy and clean speech is proposed.