正则化分段区分性特征变换方法

doi:10.3969/j.issn.1001-2400.2016.02.018

Abstract

Abstract:

In order to improve the stability of the frame based feature transform method, a segment based discriminative feature transform method is proposed, and the feature transform matrix of each speech segment is determined using the regularization technique. In the novel method, the feature transform is viewed as a parameter selection problem with limited data. In the training stage, an over-complete dictionary is constructed by the feature transform matrices of tied-state based region dependent linear transform. During testing, after the speech signal is segmented through force alignment, an appropriate regularization term is added to the likelihood objective function. An optimal subset of the transform matrices is selected from the dictionary and their corresponding coefficients are estimated following the fast iterative shrinkage thresholding optimization algorithm. Experimental results show that compared with the tied-state RDLT method, after combining L₁ and L₂ regularization, the recognition rate is increased by 1.30％ using the maximum likelihood training criterion. The performance gain is increased to 1.66％ after discriminative training.

Key words: feature transform, speech recognition, region dependent, regularization, discriminative training

CLC Number:

TN912.3

CHEN Bin;ZHANG Lianhai;QU Dan;LI Bicheng. Regularized discriminative segmental feature transform method[J].Journal of Xidian University, 2016, 43(2): 102-107.

References

［1］ NASERSHARIF B, AKBARI A. SNR-dependent Compression of Enhanced Mel Subband Energies for Compensation of Noise Effects on MFCC Features ［J］. Pattern Recognition Letters, 2011, 28(11): 1320-1326.
［2］ POVEY D, KINGSBURY B, MANGU L, et al. fMPE: Discriminatively Trained Features for Speech Recognition［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2005: 961-964.
［3］ ZHANG B, MATSOUKAS S, SCHWARTZ R. Recent Progress on the Discriminative Region-dependent Transform for Speech Feature Extraction［C］//Proceedings of the 9th International Conference on Spoken Language Processing. Baixas: ISCA, 2006: 1495-1498.
［4］ FUKUDA T, ICHIKAWA O, NISHIMURA M, et al. Regularized Feature-space Discriminative Adaptation for Robust ASR［C］//Proceedings of the Annual Conference of the International Speech Communication Association. Baixas: ISCA, 2014: 2185-2188.
［5］ POVEY D. Improvements to fMPE for Discriminative Training of Features［C］//Proceedings of the Annual Conference of the International Speech Communication Association. Baixas: ISCA, 2005: 2977-2980.
［6］ KARAFIAT M, JANDA M, CERNOCKY J, et al. Region Dependent Linear Transforms in Multilingual Speech Recognition［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2012: 4885-4888.
［7］ DENG L, CHEN J S. Sequence Classification Using the High-Level Features Extracted from Deep Neural Networks ［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2014: 6844-6898.
［8］ LIU D Y, WEI S, GUO W, et al. Lattice Based Optimization of Bottleneck Feature Extractor with Linear Transformation［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2014: 5617-5621.
［9］ YAN Z J, HUO Q, XU J, et al. Tied-state Based Discriminative Training of Context-expanded Region-dependent Feature Transforms for LVCSR［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2013:6940-6944.
［10］ ZIBULEVSKY M. L₁-L₂ Optimization in Signal and Image Processing ［J］. IEEE Signal Processing Magazine, 2010, 27(3): 76-88.
［11］ EMRE Y, JORT F G, HUGO V H. Noise Robust Exemplar Matching Using Sparse Representations of Speech ［J］. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014, 22(8): 1306-1319.
［12］ ZHANG W B, FUNG P. Discriminatively Trained Sparse Inverse Covariance Matrices for Speech Recognition ［J］. IEEE/ACM Transactions on Audio, Speech, and Language Processing, 2014, 22(5): 873-882.
［13］ LU L, GHOSHAL A, RENALS S. Regularized Subspace Gaussian Mixture Models for Speech Recognition ［J］. IEEE Signal Processing Letters, 2011, 18(7): 419-422.
［14］ YU Z, EKAPOL C, JAMES G. Extracting Deep Neural Network Bottleneck Features Using Low-rank Matrix Factorization［C］//Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing. Piscataway: IEEE, 2014: 185-189.
［15］ BECK A, TEBOULLE M. A Fast Iterative Shrinkage-thresholding Algorithm for Linear Inverse Problems ［J］. SIAM Journal on Imaging Sciences, 2009, 2(1): 183-202.

[1]	QIAO Yu,FENG Xiangchu. Image denoising and boundary extraction based on game theory [J]. Journal of Xidian University, 2021, 48(4): 128-135.
[2]	ZHANG Shudong,GAO Haichang,CAO Xiwen,KANG Shuai. Adaptive fast and targeted adversarial attack for speech recognition [J]. Journal of Xidian University, 2021, 48(1): 168-175.
[3]	BAI Jing,SHI Yanyan,XUE Peiyun,GUO Qianyan. CFCC feature extraction for fusion of the power-law nonlinearity function and spectral subtraction [J]. Journal of Xidian University, 2019, 46(1): 86-92.
[4]	FANG Jiaqi;FENG Dazheng;LI Jin. Research on modified Newton and Taylor-series methods in TDOA [J]. Journal of Xidian University, 2016, 43(6): 27-33.
[5]	YAO Hui;SUN Ying;ZHANG Xueying. Research on nonlinear dynamics features of emotional speech [J]. Journal of Xidian University, 2016, 43(5): 167-172.
[6]	LI Hong;LIU Fang;ZHANG Kai. Remote sensing image fusion based on sparse non-negative matrix factorization [J]. Journal of Xidian University, 2016, 43(2): 193-198.
[7]	LUO Xiaomei;SUO Zhiyong;LIU Qiegen. InSAR noise reduction using adaptive dictionary learning [J]. J4, 2016, 43(1): 18-23.
[8]	CHENG Jingxing;HOU Yuqing;DONG Fang;HE Xiaowei;YU Jingjing. Fluorescence molecular tomography based on the sparse regularization and adaptive finite element method [J]. J4, 2015, 42(2): 174-179.
[9]	LI Wei;YI Huangjian;ZHANG Qitan;LIANG Jimin. Fluorescence molecular tomography method using simplified spherical harmonics approximation and Laplace regularization [J]. J4, 2015, 42(1): 82-85.
[10]	HAN Bing;QIU Wenliang. Aurora images classification via features salient coding [J]. J4, 2013, 40(6): 180-186.
[11]	YAN Yunbin;QUAN Houde;CUI Peizhang. Novel reconstruction method for frequency-hopping signals [J]. J4, 2013, 40(5): 163-168.
[12]	CUI Yan-peng;HU Jian-wei;YANG Shao-quan;ZHU Yan. Automatic target recognition of ISAR images based on SIFT features [J]. J4, 2009, 36(4): 725-729.

Regularized discriminative segmental feature transform method

PDF (PC)

Like

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 12

Metrics

Comments

Recommended 10