Combination of temporal trajectory filtering and projection measure for robust speaker identification

@inproceedings{Yuo2000CombinationOT,
  title={Combination of temporal trajectory filtering and projection measure for robust speaker identification},
  author={Kuo-Hwei Yuo and Tai-Hwei Hwang and Hsiao-Chuan Wang},
  booktitle={INTERSPEECH},
  year={2000}
}
This paper presents a method that combines the techniques of temporal trajectory filtering and projection measure for robust speaker identification. The proposed robust feature, called Relative Autocorrelation Sequence Mel-scale Frequency Cepstral Coefficients (RAS-MFCC), is derived based on filtering the temporal trajectories of short-time one-sided autocorrelation sequences. This filtering process can minimize the effect of additive noise in the noisy speech. Since the norm of RAS-MFCC… CONTINUE READING

Similar Papers

Figures, Tables, and Topics from this paper.

Citations

Publications citing this paper.

References

Publications referenced by this paper.
SHOWING 1-10 OF 10 REFERENCES

RASTA processing of speech

  • IEEE Trans. Speech and Audio Processing
  • 1994
VIEW 4 EXCERPTS
HIGHLY INFLUENTIAL

Speaker-independent isolated word recognition based on emphasized spectral dynamics

  • ICASSP '86. IEEE International Conference on Acoustics, Speech, and Signal Processing
  • 1986
VIEW 1 EXCERPT