Speech measurement using laser doppler vibrometer


Published on

Published in: Technology
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide

Speech measurement using laser doppler vibrometer

  1. 1. Guided By: Presented By:Asif Ali Shamil. CLecturer in E.I Roll no: 68 E.I
  2. 2.  Introduction Speech measurement with LDV Principe of LDV Measurement Setup Problem formulation Speech Enhancement Algorithm Speckle noise suppression LDV-Based time frequency VAD Spectral gain modification Experimental Results Conclusion
  3. 3.  Achieving high speech intelligibility in noisy environments is one of the most challenging and important problems for existing speech- enhancement and speech-recognition systems. Recently, several approaches have been proposed that make use of auxiliary non acoustic sensors, such as bone and throat- microphones. Major drawback of most existing sensors is the requirement for a physical contact between the sensor and the speaker. Here present an alternative approach that enables a remote measurement of speech, using an auxiliary laser Doppler vibrometer (LDV) sensor.
  4. 4.  fd(t) = 2ν(t) cos(α)/λν(t)=> instantaneous throat-vibrational velocityα => Angle between the object beam and the velocity vectorλ =>laser wavelength. LDV-output signal after an FM-demodulator is Z(t) = fb + [2Av cos(α)/λ].cos(2πfvt). (1)
  5. 5. 
  6. 6.  let y(n) =x(n) + d(n) y(n)-observed signal in the acoustic sensor. x(n) -Speech signal. d(n)-Un correlated additive noise signal. In the STFT domain, Ylk = Xlk + Dlk Where l= 0, 1, . . . is the frame index. k = 0, 1, . . . , N − 1is the frequency- bin index.
  7. 7. Use overlapping frames of N samples with a framing-step of M samples.Let H0lk and H1lk indicate, respectively, speech absence and presence hypotheses in the time-frequency bin (l, k), i.e.,H0lk: Ylk = DlkH1lk: Ylk = Xlk + Dlk. X̂lk = GlkYlk.
  8. 8. The OM-LSA estimator minimizes the log spectral amplitude under signal presence uncertainty resulting in, Glk = {GH1lk}ˆPlk.Gminˆ1−Plk .Where, GH1lk is a conditional gain function given H1lk & Gmin<< 1 is a constant attenuation factor. Plk is the conditional speech presence probability.
  9. 9.  Denoting by ξlk and γlk we get, -Priori SNR -Posteriori SNR is the a priori probability for speech absence,
  10. 10.  Speckle-Noise Suppression The output of the speckle-noise detector is, Wl(n) = Gl Zl(n) Where Gl= Gsmin<<1 for Il = 1(speckle noise is present) Gl = 1 otherwise.
  11. 11. -Represents the noise-estimate bias -Smoothed-version of the power spectrumThen, we propose the following soft-decision VAD:
  12. 12. Speech in a given frame is defined byWe attenuate high-energy transient components to the levelof the stationary background noise by updating the gainfloor to -Stationary noise-spectrum estimate -Smoothed noisy spectrum
  13. 13.  Speckle noise was successfully attenuated from the LDV-measured signal using a kurtosis-based decision rule. A soft-decision VAD was derived in the time-frequency domain and the gain function of the OM-LSA algorithm was appropriately modified. The effectiveness of the proposed approach in suppressing highly non-stationary noise components was demonstrated.
  14. 14.  I. Cohen and B. Berdugo, “Speech enhancement for nonstationary noise environment,” Signal Process., vol. 81 T. F. Quatieri, K. Brady, D. Messing, J. P. Campbell, W. M. Campbell, M. S. Brandstein, C. J.Weinstein, J. D. Tardelli, and P. D. Gatewood, “Exploiting nonacoustic sensors for speech encoding,” T. Dekens, W. Verhelst, F. Capman, and F. Beaugendre, “Improved speech recognition in noisy environments by using a throat microphone for accurate voicing detection,” in 18th European Signal Processing Conf. (EUSIPCO), Aallborg, Denmark, Aug. 2010, pp. 23–27 M. Johansmann, G. Siegmund, and M. Pineda, “Targeting the limits of laser doppler vibrometry,” http://www.metrolaserinc.com