Noise Supression Techniques for Speech Enhancement Using Adaptive Filtering

1
Noise Supression Techniques for Speech
Enhancement Using Adaptive Filtering

• Derek Shiell
• 03/09/2006
• ECE 463 Project Presentation
• Professor Michael Honig

2
Overview

• Objective/Problem Description
• Applications
• Overview of Noise Reduction Methods
• System Description
• Filter analysis
• Linear methods
• Wiener approximation
• KLT preprocessing
• Signal subspace embedding
• Kalman filter based methods
• Non-linear methods
• Current results
• Future work
• Implementation/ practical considerations
• Conclusions

3
Objective/Problem Description

• The goal of my project was to research noise
  reduction techniques specifically for automatic
  speech recognition system front-end processing on
  a single microphone without an independent noise
  recording or clean reference signal.

4
Applications

• Cell phone speech enhancement
• Automatic speech recognition
• Speaker identification
• Biomedical signal processing

(1)
(2)

1. http//images.businessweek.com/mz/04/45/techbuy/im
   ages/razr_phone.jpg
2. http//www.nanopac.com/images/smnsbox.jpg
3. http//ldt.stanford.edu/sgilutz/Shulis_Portfolio/
   fall/hci/images/sensory.jpg

(3)
5
Overview of Speech Enhancement

• Microphone Array Processing
• Utilizing multiple microphones, blind source
  separation (BSS) techniques such as independent
  component analysis (ICA) may be used to
  distinguish one speaker from other directional or
  diffuse noises.
• Active echo/noise cancellation (ANC)
• In this case, the echo or noise is estimated and
  re-generated with opposite phase to destructively
  interfere with the original echo or noise.
• Blind noise suppression
• In this case, there is a single speech signal
  corrupted by noise, no separate noise recording
  with which to make noise estimates, and no source
  signal to reference.

6
System Descriptions
BSS/ICA
ANC
Active Noise Cancellation with single
microphone/speaker 4
BSS based on frequence domain ICA 6
Blind Noise Reduction
Blind noise reduction schematic 1
7
Filter Analysis (1)
Linear MMSE (Wiener approximation)
MMSE cost function
Reduces to (frame length N)
8
Filter Analysis (2)

• Linear Estimation (continued)

Signal is estimated from a linear filtering of
the corrupted signal
Minimizing the MMSE cost function with respect to
w the result is as follows
This is an approximation to the Wiener solution
where we are estimating the crosscorrelation
vector p with (ry rn) (similar to spectral
subtraction)
9
Filter Analysis (3)

• Linear estimation with Karhunen Lòeve Transform
  (KLT)

Preprocessing the signal using KLT (or PCA)
separates the signal into its directions of
greatest variance. Using the transform the
signal can be mapped into a lower dimensional
space which helps decorrelate the signal from
noise. For a changing signal this requires that
U be adaptively updated. Define U the KLT
transform as the eigenvectors of Ry the
autocorrelation matrix of the noisy
signal. Using this transformation we can define
the transformed yk as The resulting closed
form solution for the weight vector is
10
Filter Analysis (4)

• Signal subspace embedding
• This method allows for a matrix of gain
  factors, W, rather than simply a weight vector, w
  (MIMO) so that a simultaneous block estimate of
  can be made. In addition the matrix Q can be
  chosen as either I or to taper the tap weights by
  some factor(s) such that is emphasized more
  in the minimization phase.
• MMSE cost function
• Update Equations for the filter matrix
  and transform basis can be found iteratively

11
Filter Analysis (5)

• Kalman Filtering Approaches
• Kalman filters are widely used in speech
  enhancement and much theoretical work has been
  done analyzing Kalman filters. The Kalman filter
  is the minimum mean-square estimator of the state
  of a linear dynamical system and can be used to
  derive many types of RLS filters. Extended
  Kalman filters can be expanded to handle
  nonlinear models through a linearization process.
• Kalman filters have the advantages that they are
• more robust (stationarity not assumed)
• require only the previous estimate for the next
  estimation (versus all passed values for
  instance)
• computationally efficient

Standard linear state-space model for Kalman
filter
12
Filter Analysis (6)

• Nonlinear filtering
• Many nonlinear filtering methods exist to
  suppress noise in noisy speech. Examples include
  filters based on neural networks or phase space
  reconstruction. In general, they are very complex
  to analyze, but do not require estimation of
  noise or speech spectra and are not characterized
  by musical tone artifacts.

Feed forward neural network (1)
Phase space reconstruction for different speech
phonemes 9

1. http//research.yale.edu/ysm/images/78.2/articles-
   neural-network.jpg

13
Typical Results
Segmental SNR results (left) and SNR results
(below) for various linear and nonlinear noise
reduction methods 8
Noisy Speech Signal (white noise)
Wiener Filtered
Ephraim Filtered

• Comparison of segmental SNR performance for
  different noise sources
• White noise (SNR 6.08 dB)
• Pink noise (SNR 4.34 dB)
• Factory noise (SNR 5.16 dB)
• F16 noise (SNR 4.61 dB)
• a) Linear estimation b) linear estimation with
  KLT preprocessing c) signal subspace embedding d)
  weighted signal subspace embedding e) NN with KLT
  f) linear with clean target g) nonlinear with
  clean target h) standard spectral subtraction
  method (3dB segmental SNR 5dB SNR) 1

14
Future Work

• Perform ASR after noise reduction filtering
• AVICAR database
• Data collected in a car environment
• Time varying SNR
• No independent noise recording (detecting speech
  is difficult)
• Experiments
• KLT preprocessing linear estimation (Wiener)
• Ephraim filter (ML short time spectral amplitude
  estimator)
• Nonlinear methods

15
Implementation/Practical Considerations

• Real-time processing
• Applications require computationally efficient
  algorithms to be feasible.
• Determining noise sample
• Single microphone, speech detection to estimate
  noise statistics is difficult.
• Use visual information to detect speech or
  nonlinear noise reduction methods

16
Conclusions

• Noise suppression methods have become
  increasingly important due to the proliferation
  of mobile devices, ASR systems, and biometrics/
  bioinformatics
• Speech enhancement is a very broad field
• Array processing for source separation, noise
  cancellation
• Interested in blind noise reduction
• Linear, Linear KLT preprocessing, Signal
  subspace embedding
• Kalman filter based methods, Non-linear methods
• Using state-of-the-art noise reduction methods,
  typical SNR improvements are 5 dB
• Proposed experiments to test ASR improvement

17
References

1. Eric A. Wan and Rudolph van der Merwe,
   Noise-Regularized Adaptive Filtering for Speech
   Enhancement, Proc. Eurospeech, pp. 2643-2646,
   1999.
2. Ki Yong Lee., Byung-Gook Lee, Iickho Song, and
   Souguil Ann, Robust Estimation of AR Parameters
   and its Application for Speech Enhancement,
   Proc. IEEE ICASSP, pp. 309 - 312, 1992.
3. Phil S. Whitehead, David V. Anderson, and Mark A.
   Clements, Adaptive, Acoustic Noise Suppression
   for Speech Enhancement. Proc. IEEE ICME, pp. 565
   568, 2003.
4. A. V. Oppenheim, E. Weinstein, K. C. Zangi, M.
   Feder, and D. Gauger, Single Sensor Active Noise
   Cancellation Based on the EM Algorithm, Proc.
   IEEE ICASSP, pp. 277 280, 1992.
5. T. Rutkowski, A. Cichocki, and A. K. Barros,
   Speech Enhancement Using Adaptive Filters and
   Independent Component Analysis Approach, Proc.
   AISAT, 2000.
6. H. Saruwatari, K. Sawai, A. Lee, K. Shikano, A.
   Kaminuma, and M. Sakata, Speech Enhancement and
   Recognition in Car Environment Using Blind Source
   Separation and Subband Elimination Processing,
   Proc. ICA, pp. 367 372, 2003.
7. Simon Haykin, Adaptive Filter Theory,
   Prentice-Hall Inc., Upper Saddle River, NJ, pp
   466 501, 2002.
8. M. T. Johnson, A. C. Lindgren, R. J. Povinelli,
   and X. Yuan, Performance of Nonlinear Speech
   Enhancement using Phase Space Reconstruction,
   Proc IEEE ICASSP, pp. 872 875, 2003.
9. Andrew C. Lindgren, Speech Recognition Using
   Features Extracted from Phase Space
   Reconstructions, Thesis, Marquette University,
   Milwaukee WI, May 2003.

18

• END