吉林大学学报(工学版) ›› 2013, Vol. 43 ›› Issue (增刊1): 6-10.

Previous Articles     Next Articles

Optimal setting method for frame length and frame shift of interframe difference phase spectrum

WANG Jin-fang, GUO Ming, NIE Xin-li   

  1. College of Communication Engineering, Jilin University, Changchun 130012, China
  • Received:2012-05-25 Published:2013-06-01

Abstract:

The phase part of short-time Fourier transform involved in most speaker recognition algorithms was often ignored because of the difficulties in processing the function expressions.The feature extraction procedure of interframe difference phase spectrum sticks to making a reasonable compromise between the two factors of the detection ability of sudden phase changes and phase warping,but the determination of frame length and frame shift based on empirical analysis lacks the rational basis.Thus the optimal setting method using mutual information criterion was proposed.The speaker recognition test experiments on TIMIT speech database show that the performance on the condition of the optimized frame length and frame shift is superior to that with empirical analysis.

Key words: speaker recognition, interframe difference phase spectrum, mutual information criterion

CLC Number: 

  • TN912

[1] Al-Nashi H.Phase unwrapping of digital signals[J].IEEE Transactions on Acoustics,Speech and Signal Processing,1989,37(11):1693-1702.

[2] Murthy H A, Madhu Murthy K V, Yegnanarayana B.Formant extraction from phase using weighted group delay function[J].Electronics Letters,1989,25(23):1609-1611.

[3] Yegnanarayana B,Murthy H A.Significance of group delay functions in spectrum estimation[J].IEEE Transactions on Signal Processing,1992,40(9):2281-2289.

[4] Alsteris L D,Paliwal K K.Further intelligibility results from human listening tests using the short-time phase spectrum[J].Speech Communication,2006,48(6):727-736.

[5] Liu L,He J,Palm G.Effects of phase on the perception of intervocalic stop consonants[J].Speech Communication,1997,22(4):403-417.

[6] Oppenheim A V,Lim J S.The importance of phase in signals[J].Proceedings of the IEEE,1981,69(5):529-541.

[7] Schroeder M R.Models of hearing[J].Proceedings of the IEEE,1975,63(9):1332-1350.

[8] Alsteris L D,Paliwal K K.Short-time phase spectrum in speech processing:A review and some experimental results[J].Digital Signal Processing,2007,17(3):578-616.

[9] Reddy N, Swamy M.Derivative of phase spectrum of truncated autoregressive signals[J].IEEE Transactions on Circuits and Systems,1985,32(6):616-618.

[10] Alsteris L D,Paliwal K K.Importance of window shape for phase-only reconstruction of speech[C]// in Proc.IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP'04),Montreal,Quebec,Canada,2004:573-576.

[11] Wang Y,Hansen J, Allu G K,et al.Average instantaneous frequency (AIF) and average log-envelopes (ALE) for ASR with the Aurora 2 database[C]// in Proc.Interspeech 2003,Geneva,Switzerland,2003:25-28.

[12] Stark A P,Paliwal K K.Speech analysis using instantaneous frequency deviation[C]//in Proc.Interspeech 2008,Brisbance,Australia,2008:2602-2605.

[13] Murthy H A,Gadde V.The modified group delay function and its application to phoneme recognition[C]//in Proc.IEEE International Conference on Acoustics,Speech,and Signal Processing (ICASSP'03),Hong Kong,China,2003:68-71.

[14] McCowan I, Dean D, McLaren M,et al.The delta-phase spectrum with application to voice activity detection and speaker recognition[J].IEEE Transactions on Audio,Speech,and Language Processing,2011,19(7):2026-2038.

[15] McEliece R J.信息论与编码理论(第二版)[M]:北京:电子工业出版社,2003.

[16] Eriksson T,Kim S, Hong-Goo K,et al.An information-theoretic perspective on feature selection in speaker recognition[J].IEEE Signal Processing Letters,2005,12(7):500-503.

[17] Rajan P, Hegde R M, Murthy H A.Dynamic selection of magnitude and phase based acoustic feature streams for speaker verification [C]//in Proc.European Signal Process.Conf.,Glasgow,Scotland,2009:1244-1248.

[1] SHEN Xuan-jing, ZHAI Yu-jie, LU Yu-tong, WANG Yu, CHEN Hai-peng. Speaker recognition algorithm based on channel compensation [J]. 吉林大学学报(工学版), 2016, 46(3): 870-875.
[2] LIN lin, CHEN Hong, CHEN Jian, JIN Huan-mei. Speaker recognition with short utterances based on multiple kernel SVM-GMM [J]. 吉林大学学报(工学版), 2013, 43(02): 504-509.
[3] Lin Lin; Wang Shu-xun; Wei Xiao-li. Gaussian mixture model training method based on genetic algorithms and fuzzy approach [J]. 吉林大学学报(工学版), 2006, 36(06): 967-0972.
Viewed
Full text


Abstract

Cited

  Shared   
  Discussed   
No Suggested Reading articles found!