Connected Mandarin Digit Speech Recognition Using Two-Layer Acoustic Universal Structure

Abstract:

Because of the single-syllable of Chinese words and the confusing nature of Chinese pronunciation, connected mandarin digit speech recognition (CMDSR) is a challenging task in the field of speech recognition. This paper applied a novel acoustic representation of speech, called the acoustic universal structure (AUS) where the non-linguistic variations such as vocal tract length, lines and noises are well removed. A two-layer matching strategy based on the AUS models of speech, including the digit and string AUS models, is proposed for connected mandarin digit speech recognition. The speech recognition system for connected mandarin digits is described in detail, and the experimental results show that the proposed method can obtain the higher recognition rate.

• Periodical: Advanced Materials Research (Volumes 846-847)
• Pages: 1380-1383
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.846-847.1380
• Online since: November 2013
• Authors: Xian Yi Rui*, Yi Biao Yu, Ying Jiang
• Keywords: Acoustic Universal Structure, Candidate Digit Lattice, Connected Mandarin Digit Speech Recognition

References

[1] R. -C. Shyu, J. -F. Wang and J. -Y. Lee: Improvement in connected mandarin digit recognition by explicitly modeling coarticulatory information, Journal of Information Science and Engineering, Vol. 16, No. 4, pp.649-660, (2000).

[2] J. Gemmeke and B. Cranen: Missing data imputation using compressive sensing techniques for connected digit recognition, International Conference on Digital Signal Processing, pp.1-8, (2009).

DOI: 10.1109/icdsp.2009.5201176

[3] Y. Deng, T. Huang and B. Xu: Towards high performance continuous mandarin digit string recognition, International Conference on Spoken Language Processing (ICSLP), (2000).

DOI: 10.21437/icslp.2000-617

[4] W. Chao, S. Stephanie: Robust pitch tracking for prosodic modeling in telephone speech, International Conference on Acoustics and Signal Processing (ICASSP), pp.1343-1346, (2000).

DOI: 10.1109/icassp.2000.861827

[5] T. Murakami, K. Maruyama, N. Minematsu and K. Hirose: Japanese vowel recognition using external structure of speech, Proceedings of Automatic Speech Recognition and Understanding, pp.203-208, (2005).

DOI: 10.1109/asru.2005.1566481

[6] D. Zeng, Yibiao Yu: Voice conversion using structured Gaussian mixture model, International Conference on Signal Processing (ICSP), Beijing, pp.541-544, (2010).

DOI: 10.1109/icosp.2010.5656960

[7] N. Minematsu, S. Asakawam and K. Hirose: Structural representation of the pronunciation and its use for CALL, Workshop on Spoken Language Technology, pp.126-129, (2006).

DOI: 10.1109/slt.2006.326833