Chinese Connected Word Speech Recognition Based on Derivative Dynamic Time Warping

Abstract:

The algorithm of derivative dynamic time warping (DDTW) can overcome the shortcoming of dynamic time warping (DTW) and the computational complexity has not increased. In this paper, the algorithm of DDTW was applied to Chinese connected word speech recognition. For each isolated word, as an independent reference template and as basic recognition unit, there was an independent reference template to correspond; the matching between some word of the test string and a reference template was done by the DDTW, and the reference string which had the minimum cumulative distance was as output. The experimental results show that our method is obviously superior to all the methods based on DTW, and the recognition rate has reached 90%.

• Periodical: Advanced Materials Research (Volumes 542-543)
• Pages: 1324-1329
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.542-543.1324
• Online since: June 2012
• Authors: Zhi Guo He, Ze Min Liu
• Keywords: Chinese Connected Word, Derivative Dynamic Time Warping, Dynamic Time Warping, Speech Recognition

References

[1] Han Jiqing: Speech Signal Processing. Tsinghua University Press, Beijing (2004) (In Chinese)

[2] Xu Hua, Yu Yibiao: Connected Digit Speech Recognition Based on MIM_LB Algorithm. Microelectronics & Computer, 21(5): 33–36 (2004) (In Chinese)

[3] ZHao Jie, Yu Shuchun, Cai Hegao: Pyramid Two-level Dynamic Programming Stereo Matching Algorithm. Control and Decision, 22(1): 69–76 (2007) (In Chinese)

[4] Carlo Di Brina, Ralph Niels, Anneloes Overvelde: Dynamic Time Warping: A New Method in the Study of Poor Handwriting. Human Movement Science, 27(2): 242–255 (2008)

DOI: 10.1016/j.humov.2008.02.012

[5] Myers C. S., Rabiner L. R.: A Level Building Dynamic Time Warping Algorithm for Connected Word Recognition. IEEE Trans ASSP, 29(2): 284–296 (1981)

DOI: 10.1109/tassp.1981.1163527

[6] Keogh E., Pazzani M.: Scaling up Dynamic Time Warping for Data Mining Applications. In: 6th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, p.285–289, ACM Press, Boston (2000)

DOI: 10.1145/347090.347153

[7] Keogh E., Pazzani M.: Derivative Dynamic Time Warping. In: First SIAM International Conference on Data Mining, p.1–11, Chicago, USA (2001)

DOI: 10.1137/1.9781611972719.1

[8] Berndt D., Clifford J.: Using Dynamic Time Warping to Find Patterns in Time Series. In: AAAI-94 Workshop on Knowledge Discovery in Databases, p.229–248, AAAI Press, Washington (1994)

[9] Kruskall J. B., Liberman M.: The Symmetric Time Warping Algorithm: From Continuous to Discrete. In Time Warps, String Edits and Macromolecules: The Theory and Practice of String Comparison, Addison-Wesley (1983)

[10] Christoph Bregler, Herman Hild: Improving Connected Letter Recognition by Lip Reading. In: Proc. IEEE Int. Conf. on Acoustics, Speech, and Signal Processing, p.557–560, IEEE Press, Minneapolis, USA (1993)

DOI: 10.1109/icassp.1993.319179

[11] Bridle J.S., Brown R. M.: Chamberlain. A One-Pass Algorithm for Connected Word Recognition. In: Proceedings of the IEEE ICASSP, p.899–902, IEEE Press, Paris (1982)

[12] Rabiner L. R., Lee C. H.: HMM Clustering for Connected Word Recognition. In: Proceedings of IEEE ICASSP, p.405–408, IEEE Press, Murray Hill, New Jersey (1989)