+ All Categories
Home > Documents > Compressed Sensing for Loss-Tolerant Audio Transport

Compressed Sensing for Loss-Tolerant Audio Transport

Date post: 21-Jan-2016
Category:
Upload: major
View: 36 times
Download: 0 times
Share this document with a friend
Description:
Compressed Sensing for Loss-Tolerant Audio Transport. Clay, Elena, Hui. Introduction to CS. Basic idea: Given a signal S of length d (large) S can be recovered from a much smaller measurement vector v ! ( if S is sparse ). signal. Sparse. compressed. Introduction to CS. - PowerPoint PPT Presentation
Popular Tags:
23
6.829 Computer Networks 1 Compressed Sensing for Loss-Tolerant Audio Transport Clay, Elena, Hui
Transcript
Page 1: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 1

Compressed Sensing for Loss-Tolerant Audio Transport

Clay, Elena, Hui

Page 2: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 2

Introduction to CS

Basic idea:

Given a signal S of length d (large)

S can be recovered from a much smaller measurement vector v ! ( if S is sparse )

Sparse compressedsignal

Page 3: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 3

Introduction to CS

signal: s= (0, 1, 1, 1, 0, 0, 0, 0, 0, 0, 0, 0, 1)

measurements: projections of s onto some small number of basis vectors

Questions: 1. what basis vectors?2. how many measurements are enough?

Page 4: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 4

Intro to CS

Sometimes imperfection is OK! We only want to have to transmit enough for a “reasonable” reconstruction.

Reduce the number of bits used to transmit a signal

Page 5: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 5

Motivation

Direct applicability to low-power sensor networks (data is sparse)

Applications to medical imaging

How does CS apply to audio signals?

Page 6: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 6

CS and sound reconstruction

Compressed Sensing is:

loss-tolerant

universal

But:

is it practical? Particularly for audio?

how about quality of reconstructed sound?

Page 7: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 7

Approach/contributions

- Use a modified version of the classical Orthogonal Matching Pursuit

1. optimized the main iterative step2. dealt with MATLAB memory overflow for

matrix storage3. split original large data samples into

smaller frames and combine at the end4. Quantify relationship between quality and

compression parameters m, c.

Page 8: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 8

Parameters

• m: sparsity level of original data

• d: data space dimension

• N: # of measurements

N= c m ln(d)

Page 9: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 9

OMP(Orthogonal Matching Pursuit)

• InputΦ: N x d measurement matrixv: N-dimensional data vectorm: data sparsity

• Outputs: estimated signal in Rd

• Procedure

v= Φ * s

Page 10: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 10

OMP Procedure

Determine which columns of Φ participate in the measurement vector v, in greedy fashion.1. Initialization 2. IterationIn each iteration, choose one column Φ that is most strongly correlated with the remaining part of v. Then we subtract off its contribution to v and iterate on the residual.3. ReconstructionUse the chosen columns of Φ and approximation to reconstruct the signal.

Page 11: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 11

I-OMP on Audio Signal Recovery

• Original sound signal (Source: s4d.wav)

• Reconstructed by setting m = 256 and 500

Page 12: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 12

Tests

Test the impact of the parameters m, c on the quality of the reconstruction

Method: MOS (Mean Opinion Score)

Page 13: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 13

Sparsity and MOS

m as fraction of number of samples

MO

S

scor

e

Page 14: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 14

Quality of reconstruction

Sum of squared differences between original and reconstructed signal

m = 1233

d = 8821

c

Page 15: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 15

Piecewise Compression

• Original:

• Recovered:

• MOS = 2.8

Page 16: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 16

I-OMP on image recovery

Different m = 256, 512, 1024

Source: moon.bmp

Page 17: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 17

I-OMP on Image Recovery

• Different value of parameter c

• Original, c=2,4,20

Page 18: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 18

The End

Page 19: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 19

• 1. Initialization residual r = v; Index set Λ = empty;

• 2. Iteration

• 3. Reconstruction

Page 20: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 20

OMP Procedure• 1. Initialization• 2. Iteration

For t=0: m-1• Find the index λ that solves• λ= arg max j=1,…,d |<r,φj>|• Λ = Λ U {λ}• Re-compute projection P on φΛ.

A = P* vr = v - A

• 3. Reconstruction

Page 21: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 21

OMP Procedure

• 1. Initialization

• 2. Iteration

• 3. Reconstruction

The estimate s for the ideal signal has non-zero coefficients sλ at the components li

sted in Λ.

A = Σ λ∈Λ φλ* sλ

Page 22: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 22

Iterative OMP

• 1. Initializationr = v;s = 0d;

• 2. IterationFor t=0: m-1

• Find the index λ that solves λ= arg max j=1,…,d |<r,φj>|

• sλ = <r, φλ >/ || φλ ||2

• r = r - sλ * φλ

• A= A + sλ * φλ

• 3. Reconstruction

Page 23: Compressed Sensing for Loss-Tolerant Audio Transport

6.829 Computer Networks 23

Iterative OMP -2


Recommended