A Mathematical Morphological Processing of Spectrograms for the Tone of Chinese Vowels Recognition

Abstract:

As One of Features from other Languages, the Chinese Tone Changes of Chinese are Mainly Decided by its Vowels, so the Vowel Variation of Chinese Tone Becomes Important in Speech Recognition Research. the Normal Tone Recognition Ways are Always Based on Fundamental Frequency of Signal, which can Not Keep Integrity of Tone Signal. we Bring Forward to a Mathematical Morphological Processing of Spectrograms for the Tone of Chinese Vowels. Firstly, we will have Pretreatment to Recording Good Tone Signal by Using Cooledit Pro Software, and Converted into Spectrograms; Secondly, we will do Smooth and the Normalized Pretreatment to Spectrograms by Mathematical Morphological Processing; Finally, we get Whole Direction Angle Statistics of Tone Signal by Skeletonization way. the Neural Networks Stimulation Shows that the Speech Emotion Recognition Rate can Reach 92.50%.

• Periodical: Applied Mechanics and Materials (Volumes 571-572)
• Pages: 665-671
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.571-572.665
• Online since: June 2014
• Authors: Sen Xu, Xu Zhao, Cheng Hua Duan, Xiao Lin Cao, Hui Yan Li, Shi Li Liang*, Shuan Wei Wang
• Keywords: Mathematical Morphology Image Processing, Neural Network (NN), Skeletonization, Speech Emotion Recognition, Speech Spectrogram, Tone Recognition

References

[1] J. Cadore,A. Gallardo-Antolín,C. Peláez-Moreno: Advances in Nonlinear Speech Processing Lecture Notes in Computer Science , 2011, Volume 7015, pp.224-231.

DOI: 10.1007/978-3-642-25020-0_29

[2] Cadore, J. Valverde-Albacete, F. J. Gallardo-Antolín, A. Peláez-Moreno, C. Auditory-Inspired Morphological Processing of Speech Spectrograms: Applications in Automatic Speech Recognition and Speech Enhancement. Cognitive Computation, 2012, 1-16.

DOI: 10.1007/s12559-012-9196-6

[3] Cadore, J. Gallardo-Antolín, A. Peláez-Moreno, C. Morphological processing of spectrograms for speech enhancement. 2011, 7015 LNAI, 224-231.

DOI: 10.1007/978-3-642-25020-0_29

[4] Ariki Y, Kato S, and Takiguchi T. phoneme Recognition Based on Fisher Weight Map to Higher-Order Local Auto-Correlation, Proc. of Interspeech, 2006, 377-380.

DOI: 10.21437/interspeech.2006-126

[5] S. Raphael O.S. Douglas: Segmentation of a Speech Spectrogram using Mathematical Morphology[J]. Proceeding of IEEE ICASSP, 2008, 1637-1640.

[6] Yin, H. Nadeu, C. Hohmann, V. Pitch- and formant-based order adaptation of the fractional fourier transform and its application to speech recognition. Eurasip Journal on Audio, Speech, and Music Processing. (2009).

DOI: 10.1155/2009/304579

[7] Cao, J. Li, A. Hu, F. Zhang, L. Application of phonetic knowledge in automatic speech recognition - Case analysis. Qinghua Daxue Xuebao/Journal of Tsinghua University, 2008, 48, SUPPL, 748-753.

[8] Serra J. Image analysis and mathematical morphology[C]. London: Academic Press, 1982, 115.

[9] Mellinger, D. K. Clark, C. W. Recognizing transient low-frequency whale sounds by spectrogram correlation. Journal of the Acoustical Society of America. 2000, 107, 6, 3518-3529.

DOI: 10.1121/1.429434

[10] Ashish B. Ingale, D. S. Chaudhari. Speech Emotion Recognition. International Journal of Soft Computing and Engineering . March 2012 , Volume-2, Issue-1.

[11] Shinha D and Dougherty E R. Fuzzy mathematical morphology[J]. J Vision, Communication and Imagine and Representation, 1992, 3( 3): 286-302.

[12] Evangelista G. Pitch-Synchronous Wavelet Representations of Speech and Music Signal. IEEE. Trans on 1993, 41(12): 3313-3330.

DOI: 10.1109/78.258076

[13] Nwe, Tin Lay. Foo, Say Wei. De Silva, Liyanage C. Speech emotion recognition using hidden Markov models. Speech Communication. 2003, 41, 4, 603-623.

DOI: 10.1016/s0167-6393(03)00099-2

[14] Schuller B. Rigoll G. Lang M. Hidden Markov model-based speech emotion recognition. 2003 April, II - 1-4 vol. 2.

DOI: 10.1109/icassp.2003.1202279

[15] Hunt, Melvyn J. Lefebvre, Claude. Speech recongnition using an auditory model with pitch-synchronous analysis. Proceedings - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing. 1987, 813-816.

DOI: 10.1109/icassp.1987.1169585

[16] Lam L, Suen C Y. An evaluation of parallel thinning algorithms for character recognition[J]. IEEE Trans on Pattern Analysis and Machine Intelligence, 1995, 17(9): 914-919.

DOI: 10.1109/34.406659

[17] Gasteratos A, Tsalides S. Fuzzy soft mathematical morphology[J]. Image Signal Processing, 1998, 145(1): 41- 49.

DOI: 10.1049/ip-vis:19981557

[18] Chen Sin-Homg, Senior Member, and Wang Yih-Ru. Tone Recognition of Continuous Mandarin Speech Based on Neural Networks[J]. IEEE Transactions on Speech and Audio Processing, 1995, 3(2): 146-150.

DOI: 10.1109/89.366544

[19] Yang W J. Hidden Markov Model for Mandarin lexical tone recognition, IEEE Trans. Acoust Speech Signal Process, 1988, 36: 988-992.

DOI: 10.1109/29.1620

[20] Chennonkh S, Gerrits A, Miet G, et al. Speech Enhancement via Frequency Extension using Spectral Frequency[A]. Proc. ICASSP[C]. SaltLakeCity, 2001, 5.

[21] Rea J A, Longbotham H G, Kothari H.N. Fuzzy Logic Mathematical Morphology: implementation by Stack Filter. IEEE Trans. on Signal Processing, 1996, 44(l): 142-147.

DOI: 10.1109/78.482024

[22] Blum H. A Transformation for Extracting New Descriptors of Shape, Models for the Perception of Speech and Visual Forms,W. Watheen Dunn, Ed. Cambridge, MA: MIT Press, (1967).