Optimization of data-driven filterbank for automatic speaker verification
@article{Sarangi2020OptimizationOD, title={Optimization of data-driven filterbank for automatic speaker verification}, author={Susanta Sarangi and M. Sahidullah and G. Saha}, journal={Digit. Signal Process.}, year={2020}, volume={104}, pages={102795} }
Abstract Most of the speech processing applications use triangular filters spaced in mel-scale for feature extraction. In this paper, we propose a new data-driven filter design method which optimizes filter parameters from a given speech data. First, we introduce a frame-selection based approach for developing speech-signal-based frequency warping scale. Then, we propose a new method for computing the filter frequency responses by using principal component analysis (PCA). The main advantage of… CONTINUE READING
Figures, Tables, and Topics from this paper
2 Citations
A Hybrid Meta-Heuristic Feature Selection Method for Identification of Indian Spoken Languages From Audio Signals
- Computer Science
- IEEE Access
- 2020
- 1
- PDF
References
SHOWING 1-10 OF 90 REFERENCES
A novel approach in feature level for robust text-independent speaker identification system
- Computer Science
- 2012 4th International Conference on Intelligent Human Computer Interaction (IHCI)
- 2012
- 14
Data-driven spectral basis functions for automatic speech recognition
- Computer Science
- Speech Commun.
- 2003
- 23
Improved Closed Set Text-Independent Speaker Identification by Combining MFCC with Evidence from Flipped Filter Banks
- Engineering
- 2008
- 90
Optimization of temporal filters for constructing robust features in speech recognition
- Mathematics, Computer Science
- IEEE Transactions on Audio, Speech, and Language Processing
- 2006
- 66
- PDF
Design, analysis and experimental evaluation of block based transformation in MFCC computation for speaker recognition
- Mathematics, Computer Science
- Speech Commun.
- 2012
- 279
- PDF
Mean Hilbert envelope coefficients (MHEC) for robust speaker and language identification
- Computer Science
- Speech Commun.
- 2015
- 47
Power-Normalized Cepstral Coefficients (PNCC) for Robust Speech Recognition
- Computer Science
- IEEE/ACM Transactions on Audio, Speech, and Language Processing
- 2016
- 315
- PDF
A perceptually-motivated low-complexity instantaneous linear channel normalization technique applied to speaker verification
- Computer Science
- Comput. Speech Lang.
- 2015
- 10
- PDF
Data-Driven Temporal Filters and Alternatives to GMM in Speaker Verification
- Computer Science
- Digit. Signal Process.
- 2000
- 30
- PDF