Name
Abstract | ||
|---|---|---|
Speech feature extraction has been a key focus in robust speech recognition research. In this work, we discuss data-driven linear feature transformations applied to feature vectors in the logarithmic mel-frequency filter bank domain. Transformations are based on principal component analysis (PCA), independent component analysis (ICA), and linear discriminant analysis (LDA). Furthermore, this paper introduces a new feature extraction technique that collects the correlation information among phoneme subspaces and reconstructs feature space for representing phonemic information efficiently. The proposed speech feature vector is generated by projecting an observed vector onto an integrated phoneme subspace (IPS) based on PCA or ICA. The performance of the new feature was evaluated for isolated word speech recognition. The proposed method provided higher recognition accuracy than conventional methods in clean and reverberant environments. |
Year | DOI | Venue |
|---|---|---|
2009 | 10.1155/2009/690451 | EURASIP J. Audio, Speech and Music Processing |
Keywords | Field | DocType |
data-driven linear feature,independent component analysis,new feature extraction technique,integrated phoneme subspace method,robust speech recognition research,higher recognition accuracy,speech feature extraction,isolated word speech recognition,reconstructs feature space,proposed speech feature vector,new feature,feature extraction | k-nearest neighbors algorithm,Feature vector,Dimensionality reduction,Pattern recognition,Computer science,Feature (computer vision),Feature extraction,Speech recognition,Feature (machine learning),Artificial intelligence,Kanade–Lucas–Tomasi feature tracker,Linear discriminant analysis | Journal |
Volume | Issue | ISSN |
2009, | 1 | 1687-4722 |
Citations | PageRank | References |
2 | 0.37 | 12 |
Authors | ||
3 | ||
Name | Order | Citations | PageRank |
|---|---|---|---|
| Park, Hyunsin | 1 | 11 | 2.69 |
| Tetsuya Takiguchi | 2 | 308 | 52.22 |
| Yasuo Ariki | 3 | 519 | 88.94 |