Stressed Speech Recognition Method Based on Difference Subspace Combined with Dynamic Time Warping

Abstract:

Speech under G-force which produced when speaker was under different acceleration of gravity was analyzed and researched, considered as principal part and stressed part to research. An isolated word recognition approach was proposed which combined difference subspace means with dynamic time warping technique. The method recognized speech under G-force by constructing a difference subspace to remove the stressed part. Dynamic time warping technique was adopted to make all feature vectors of one word in the training set have equal length, and a corresponding decision criterion was suggested. For a small vocabulary including 15 words, the method obtained the average recognition rate of 98.3%, which almost equal to the rate in normal environment. The method not only worked well in normal conditions but also had good performance for speech under G-force.

• Periodical: Applied Mechanics and Materials (Volumes 241-244)
• Pages: 1640-1646
• DOI: https://doi.org/10.4028/www.scientific.net/AMM.241-244.1640
• Online since: December 2012
• Authors: Cheng Guo Lv, Ru Bo Zhang, Pei Hua Li
• Keywords: Difference Subspace, Dynamic Time Warping, Speech Recognition, Speech under G-Force

References

[1] Y. Chen. IEEE Trans. On acoustics, Speech and Signal Processing. Vol. 36 (1988), p.433.

[2] J.H.L. Hansen and S. Bou-Ghazale. EUROSPEECH'97. Vol. 4 (1997), p.1743.

[3] H.J.M. Steeneken and J.H.L. Hansen. ICASSP'99. Vol. 4 (1999), p. (2079).

[4] S. Bou-Ghazale and J.H.L. Hansen. IEEE Trans. On Speech and Audio Processing. Vol. 8(2000), p.429.

[5] G. Zhou, J.H.L. Hansen and J.F. Kaiser. IEEE Trans. On Speech and Audio Processing. Vol. 9(2001), p.201.

[6] D. Womack and J.H.L. Hansen. IEEE Trans. On Speech and Audio Processing. Vol. 7(1999), p.668.

[7] Ziyun YANG, Jiqing HAN and Jinpei XU. CHINESE JOURNAL OF ACOUSTICS. Vol. 15(1996), p.123.

[8] Jingdong CHEN, Lei YAO and Taiyi HUANG. ACTA ACOUSTIC(In Chinese). Vol. 23(1998), p.537.

[9] Bin TIAN and Kechu YI. ACTA ACOUSTIC(In Chinese). Vol. 28(2003), p.28.

[10] Jialu ZHANG and Shijin QI. ACTA ACOUSTIC(In Chinese). Vol. 9(1984), p.258.

[11] Jialu ZHANG. ACTA ACOUSTIC(In Chinese). Vol. 14(1989), p.401.

[12] Jialu ZHANG. ACTA ACOUSTIC(In Chinese). Vol. 18(1993), p.263.

[13] Yonglin MA, Jiqing HAN and Lei ZHANG. ACTA ACOUSTIC(In Chinese). Vol. 27(2002), p.518.

[14] Yuwei Wang, Lei Zhang and Jiqing Han. SIGNAL PROCESSING(In Chinese). Vol. 18(2002), p.484.

[15] M.B. Gülmezoglu and D. Vakif. IEEE Transactions on Speech and Audio Processing. Vol. 7(1999), p.620.

[16] M.B. Gülmezoglu and D. Vakif. IEEE Transactions on Speech and Audio Processing. Vol. 9(2001), p.655.