Bottleneck features and subspace Gaussian mixture models for low-resource speech recognition

doi:10.7523/j.issn.2095-6134.2015.01.016

›› 2015, Vol. 32 ›› Issue (1): 97-102.DOI: 10.7523/j.issn.2095-6134.2015.01.016

Previous Articles Next Articles

Bottleneck features and subspace Gaussian mixture models for low-resource speech recognition

WU Weilan^1,2, CAI Meng³, TIAN Yao³, YANG Xiaohao³, CHEN Zhenfeng^1,2, LIU Jia³, XIA Shanhong²

1. University of Chinese Academy of Sciences, Beijing 100190, China;
2. State Key Laboratory of Transducer Technology, Institute of Electronics, Chinese Academy of Sciences, Beijing 100190, China;
3. Tsinghua National Laboratory for Information Science and Technology, Department of Electronic Engineering, Tsinghua University, Beijing 100084, China

Received:2014-02-27 Revised:2014-03-07 Online:2015-01-15

Abstract

Abstract:

State-of-the-art speech recognition systems often depend on a lot of training data, but perform poorly when limited data is available. In this paper, we study speech recognition systems under low-resource condition. The subspace Gaussian mixture (SGMM) model is first applied to reduce the number of parameters. The model is further enhanced by discriminative training based on maximum mutual information criterion. The bottleneck features based on deep neural networks are then studied to make robust feature extraction. The SGMM model and the bottleneck features are finally combined to produce a novel speech recognition system under low-resource condition. On the standard OpenKWS 2013 evaluation corpus, experimental results show the combination of the two technologies brings substantial relative improvement of about 12% over the baseline system.

Key words: speech recognition, low-resource, acoustic model, acoustic feature

CLC Number:

TP391.42

WU Weilan, CAI Meng, TIAN Yao, YANG Xiaohao, CHEN Zhenfeng, LIU Jia, XIA Shanhong. Bottleneck features and subspace Gaussian mixture models for low-resource speech recognition[J]. , 2015, 32(1): 97-102.

References

[1] Cui X, Xue J, Dognin P L, et al. Acoustic modeling with bootstrap and restructuring for low-resourced languages[C]//Interspeech. 2010: 2 974-2 977.

[2] Vu N T, Schlippe T, Kraus F, et al. Rapid bootstrapping of five eastern european languages using the rapid language adaptation toolkit[C]//Interspeech. 2010: 865-868.

[3] Rabiner L R. A Tutorial on hidden markov models and selected applications in speech recognition[J].Proceedings of IEEE, 1989, 77(2):257-286.

[4] Davis S, Mermelstein P. Comparison of parametric representations formonosyllable word recognition in continuously spoken sentences[J]. IEEE Transactions on Acoustics, Speech, and Signal Processing, 1980, 28(4):357-366.

[5] Povey D, Burget L, Agarwal M, et al. Subspace Gaussian mixture models for speech recognition[C]//Acoustics Speech and Signal Processing (ICASSP), 2010 IEEE International Conference on. IEEE, 2010: 4 330-4 333.

[6] Povey D, Burget L, Agarwal M, et al. The subspace Gaussian mixture model: a structured model for speech recognition[J]. Computer Speech and Language, 2011, 25(2):404-439.

[7] Dahl G, Yu D, Deng L, et al. Context-dependent pre-trained deep neural networks for large vocabulary speech recognition [J]. IEEE Trans on Audio, Speech and Language Processing, 2012, 20(1): 30-42.

[8] Seide F, Li G, Yu D. Conversational speech transcription using context-dependent deep neural networks//Interspeech. 2011: 437-440.

[9] Normandin Y. Hidden Markov models, maximum mutual information estimation, and the speech recognition problem . Canada: McGill University, 1991.

[10] He X D, Deng L, Chou W. Discriminative learning in sequential pattern recognition[J]. IEEE Signal Processing Magazine, 2008, 14(1):14-36.

[11] Yu D, Seltzer M L. Improved bottleneck features using pretrained deep neural networks[C]//INTERSPEECH. 2011: 237-240.

[12] IARPA. OpenKWS13 keyword search evaluation . (2013-01-25) . http://www.nist.gov/itl/iad/mig/upload/OpenKWS13.

[13] 单煜翔. 高效大词汇量连续语音识别解码算法研究与工程化实现[D]. 北京: 清华大学, 2012.

[14] Povey D, Ghoshal A, Boulianne G, et al. The Kaldi speech recognition toolkit[C]//Proc ASRU. 2011: 1-4.

[15] 钱彦旻. 低数据资源条件下的语音识别技术新方法研究[D]. 北京: 清华大学, 2013.

[16] Hinton G, Deng L, Yu D, et al. Deep neural networks for acoustic modeling in speech recognition: the shared views of four research groups[J]. IEEE, Signal Processing Magazine, 2012, 29(6): 82-97.

[17] Hinton G E, Osindero S, Teh Y W. A fast learning algorithm for deep belief nets[J]. Neural computation, 2006, 18(7): 1 527-1 554.

[18] Hinton G E, Salakhutdinov R R. Reducing the dimensionality of data with neural networks[J]. Science, 2006, 313(5786): 504-507.

[19] Fontaine V, Ris C, Boite J M. Nonlinear discriminant analysis for improved speech recognition[C]//Eurospeech. 1997.

[20] Grézl F, Karafiát M, Kontár S, et al. Probabilistic and bottle-neck features for LVCSR of meetings[C]//Proc ICASSP. 2007(4):757-761.

Bottleneck features and subspace Gaussian mixture models for low-resource speech recognition

PDF (PC)

Knowledge

Abstract

Cite this article

share this article

References

Related Articles 5

Recommended Articles

Metrics

Comments

[1]	DING Jiawei, LIU Jia, ZHANG Weiqiang, FENG Yunbo, LIU Lijun, YU Le. Inactive-node detection and memory optimization in WFST decoder lattice generation algorithm [J]. , 2019, 36(1): 109-114.
[2]	Tang Bu-tian , Guo Li , Liu Zhen-hua. An Information Hiding Method in Speech Using MFCC [J]. , 2008, 25(3): 386-394.
[3]	Zhang Ming-xin; Ni Hong; Zhang Dong-bin; Chen Guo-ping. Noise Robust Acoustic Model Research Based on PMC [J]. , 2006, 23(5): 660-664.
[4]	LIU Bin, DU Li-Min. Embedded Speaker-Independent Continuous Speech Recognition System Based on MPC5200 [J]. , 2006, 23(2): 174-177.
[5]	NING Zhen-Jiang, DU Li-Min . An Improved Incremental Approach to Speech Corpus Selection [J]. , 2005, 22(2): 140-146.