1. Speaker Verification System Part B Final Presentation
Performed by: Barak Benita & Daniel Adler
Instructor: Erez Sabbag

2. Implementation of a speaker verification algorithm on a DSP
The Project Goal
Implementation of a speaker verification algorithm on a DSP
The verification module will perform a real time authentication of the user based on sampled voice data.
The idea is to integrate the speaker verification model with other security and management models allowing them to grant access to resources based on the speakers voice verification.

3. Introduction
Speaker verification is the process of automatically authenticating the speaker on the basis of individual information included in speech waves.
Speaker’s Identity (Reference)
Speaker’s
Voice
Segment
Speaker
Verification
System
Result [0:1]

4. System Overview Access Denied BT Base Station My name is Bob! LAN
Speaker
Verification
Unit
Server BT
Base Station
LAN

5. System Description
The system is compound from TI’s C6701floating point DSP with the speaker verification algorithm on it. A user with a hand device (e.g. bluetooth on a PDA), will receive access to different resources ( door opening, file access, etc) based on a voice verification process.
The project implements only the speaker verification algorithm on the DSP and has input and output interfaces to interact with other devices (e.g. Bluetooth).
The DSP is encoded with the users voice signature. Each time user verification is needed, the algorithm compares the speakers voice with the signature. 3

6. (training phase – building
System Block Diagram
DSP
Signature
parameters
Enrollment
Server
(training phase – building
A signature)
Codec
Verification Channel
Voice Channel
(optional)
Bluetooth
Radio
Interface
Bluetooth
unit
Codec
Bluetooth
Base station
Authorization
Server
LAN
Voice Channel
(optional)
Voice Channel
“My name is Bob” 5

7. Project Description: Part One: Part Two:
Literature review
Algorithms selection
MATLAB implementation
Result analysis
Part Two:
Implementation of the chosen algorithm on a DSP

8. Speaker Verification Process
Analog Speech
Pre-Processing
Feature
Extraction
Reference
Model
Pattern
Matching
Decision
Result [0:1]

9. Implemented Algorithms: Feature Extraction Module – MFCC
MFCC (Mel Frequency Cepstral Coefficients) is the most common technique for feature extraction. MFCC tries to mimic the way our ears work by analyzing the speech waves linearly at low frequencies and logarithmically at high frequencies.
The idea acts as follows:
Spectrum
Mel Spectrum
FFT
Mel-frequency
Wrapping
Cepstrum
Mel Cepstrum
Windowed
PDS Frame

10. Implemented Algorithms: Pattern Matching Modeling Module – Vector Quantization (VQ)
In the enrolment part we build a codebook of the speaker according to the LBG (Linde, Buzo, Gray) algorithm, which creates an N size codebook from set of L feature vectors.
In the verification stage, we are measuring the distortion of the given sequence of the feature vectors to the reference codebook.
Pattern Matching =
Distortion measure
Reference
Model = Codebook
Distortion Rate
Feature Vector

11. Implemented Algorithms: Decision
In VQ the decision is based on checking if the distortion rate is higher than a preset threshold: acceptance if distortion rate > t, else rejection.
In this project no decision model will be build, the output of the system will be based on the following score rate (values between 0 to 1), which indicates the suitability of the person to the reference model:
Score = exp (-mean distance)

12. Implementation Environment
Hardware tools:
TI DSP 6701 EVM board
PC host station
Software development tools:
TI Code Composer
Matlab 6.1
Programming Languages: C
Assembler
Matlab

13. Working Environment

14. TI DSP 6701 EVM Why? Floating Point
Designed Especially for Voice Applications
Large Bank of On Chip Memory
High level development (C)
PCI Interface
Why Not?
Price
Size
Consumption

15. Program Workflow Program DSP MATLAB Program Analog Speech (input)
Pre-Processing
Feature
Extraction
MATLAB
Program
Reference
Model
Pattern
Matching
Decision
Result [0:1] (output)

16. Step By Step Implementation
Pre-processing a ‘ones’ vector on the DSP and comparing it to the Matlab results
Pre-processing an audio file and comparing to the Matlab results
Feature extracting of the audio file (after pre-processing) and comparing to the Matlab results
Pattern matching the feature vectors to a ‘ones’ codebook matrix and comparing to the Matlab results (running with the same codebook)
Creating a real codebook from a reference speaker importing it to the DSP and comparing the running results of the DSP and the Matlab
Verifying that the distances of the speakers from the codebook in the DSP program and in the Matlab program are the same

17. Creating the Assembler Lookup Files
Creating the output data through Matlab functions (e.g. hamming(n))
Saving the output in an assembler lookup table format
Referencing the lookup table with a name that will be called from the C source code in the DSP project (as a function)
hamming = fopen('hamming.asm', 'wt', 'l');
fprintf(hamming, '; hamming.asm - single precision floating point table generated from MATLAB\n');
fprintf(hamming, '\t.def\t_hamming\n');
fprintf(hamming, '\t.sym\t_hamming, _hamming, 54, 2, %d,, %d\n', size, n);
fprintf(hamming, '\t.data\n');
fprintf(hamming, '_hamming:\n');
fprintf(hamming, '\t.word\t%tXh, %tXh, %tXh, %tXh\n', h);
fprintf(hamming, '\n');
fclose(hamming);
Importing the file as an asm file (adding a file to the project) to the DSP project
; hamming.asm - single precision floating point table generated from MATLAB
.def _hamming
.sym _hamming, _hamming, 54, 2, 8192,, 256
.data
_hamming:
.word 3DA3D70Ah, 3DA4203Fh, 3DA4FBD3h, 3DA669A4h
.word 3DA86978h, 3DAAFB01h, 3DAE1DD8h, 3DB1D180h
.word 3DB61567h, 3DBAE8E1h, 3DC04B30h, 3DC63B7Dh
.word 3DCCB8DCh, 3DD3C24Bh, 3DDB56B1h, 3DE374E1h
.word 3DEC1B99h, 3DF5497Fh, 3DFEFD27h, 3E049A87h
.word 3E09F7D0h, 3E0F9597h, 3E1572FFh, 3E1B8F1Ch
h = hamming(n);
Using the lookup table in the C source code
// Windowing the filtered frame with Hamming ----
for (k=0 ; k < N ; k++){
for (j=0 ; j < N ; j++){
if (k - j < 0) break;
frame[k] += hamming[j]*filtered_frame[k-j]; }

18. Binding All The Pieces DSP Program C Code
Analog Speech (input)
Generation of assembly functions through Matlab
Hamming.asm
Generation of voice data file from a *.wav format file through Matlab waveread function
Sari5fix.asm
DSP
Program
C Code
Pre-Processing
Generation of assembly functions through Matlab
Melbank.asm
Rdct.asm
Feature
Extraction
Generation of assembly functions through Matlab
Codebook.asm
Pattern
Matching
Decision
Result [0:1] (output)

19. Software Modules main init O(1) extract_frame O(n^2) digitrev_index
bitrev
O(n)
hamming
O(1)
bitrev
O(n)
melbank
O(n)
cfftr2_dit
O(nlog(n))
calc_dist
O(1)

20. Project Structure speakerverification.pjt Include Files board.h
codec.h
dma.h
intr.h
mcbsp.h
link.cmd
pci.h
regs.h
Libraries
verification.h
rts6700.lib
Source
bitrevf.asm
cfftr2.asm
codebook.asm
digitrev_index.c
hamming.asm
melbank.asm
rdct.asm
verification.c

21. Tested System The Tested System parameters:
The tested algorithms and methods were the MFCC and VQ with the following parameters:
Sampling Frequency: 11025Hz
Feature Vector Size: 18
Window Size: 256
Offset Size: 128
Codebook Size: 128
Number of iterations for codebook creation: 25
We compared between the Matlab and DSP results based on a codebook created from Daniel’s 60 seconds of random speech and random selection of different five seconds speakers.

22. Verifications The DSP results were compared to the Matlab simulation.
We chose random speakers from the speakers DB with one reference codebook.
For Example:
Person MATLAB DSP
Daniel % (0.4011) 66.95% (0.4011)
Barak % (0.8206) 44.01% (0.8206)
Ayelet % (0.8299) 43.61% (0.8299)
Diego % (0.6166) 53.97% (0.6166)
Adi % (0.8656) 42.07% (0.8656)

23. Conclusions The TI DSP 6701 EVM is capable of preforming speaker
verification analysis and achieve high resolution results (as
achieved in the Matlab)
Speaker Verification algorithms are not mature enough to
become a good biometric detection solution
Code Composer is not stable and good enough to become an “easy
to use” development environment
A second phase project, which will implement a complete verification system should be build

24. Time Table – First Semester
– Project description presentation
– completion of phase A: literature review and algorithm selection
– Handing out the mid-term report
– Beginning of phase B: algorithm implementation in MATLAB
– Publishing the MATLAB results and selecting the algorithm that will be implemented on the DSP

25. Time Table – Second Semester
– Presenting the progress and planning of the project to the supervisor
– Finishing MATLAB Testing
– The beginning of the implementation on the DSP
– Project presentation and handing the project final report

26. Thanks

27. Backup Slides

28. Pre-Processing (step 1)
Analog Speech
Windowed PDS Frames
[1, 2, … , N]
Pre-Processing

29. Pre-Processing module
Analog Speech
Anti aliasing filter to avoid aliasing during sampling. LPF [0, Fs/2]
LPF
Band Limited
Analog Speech
Analog to digital converter with frequency sampling (Fs) of [10,16]KHz
A/D
Digital Speech
Low order digital system to spectrally flatten the signal (in favor of vocal tract parameters), and make it less susceptible to later finite precision effects
First Order FIR
Pre-emphasized
Digital Speech
(PDS)
Frame Blocking
Frame blocking of the sampled signal. Each frame is of N samples overlapped with N-M samples of the previous frame. Frame rate ~ 100 Frames/Sec
N values: [200,300], M values: [100,200]
PDS Frames
Frame
Windowing
Using Hamming (or Hanning or Blackman) windowing in order to minimize the signal discontinuities at the beginning and end of each frame.
Windowed PDS Frames

30. Feature Extraction (step 2)
Windowed PDS Frames
Set of Feature Vectors
[1, 2, … , N]
[1, 2, … , K]
Feature
Extraction
Extracting the features of speech from each frame and representing it in a vector (feature vector).

31. MFCC – Mel-frequency Wrapping
Psychophysical studies have shown that human perception of the frequency contents of sounds for speech signals does not follow a linear scale. Thus for each tone with an actual frequency, f, measured in Hz, a subjective pitch is measured on a scale called the ‘mel’ scale. The mel-frequency scale is a linear frequency spacing below 1000 Hz and a logarithmic spacing above 1000 Hz. Therefore we can use the following approximate formula to compute the mels for a given frequency f in Hz:

32. MFCC – Filter Bank
One way to simulating the spectrum is by using a filter bank, spaced uniformly on the mel scale. That filter bank has a triangular bandpass frequency response, and the spacing as well as the bandwidth is determined by a constant mel frequency interval.

33. MFCC – Cepstrum
Here, we convert the log mel spectrum back to time. The result is called the mel frequency cepstrum coefficients (MFCC). Because the mel spectrum coefficients are real numbers, we can convert them to the time domain using the Discrete Cosine Transform (DCT) and get a featured vector.

34. Pattern Matching Modeling (step 3)
The pattern matching modeling techniques is divided into two sections:
The enrolment part, in which we build the reference model of
the speaker.
The verifications (matching) part, where the users will be
compared to this model.

35. Enrollment part – Modeling
Set of Feature Vectors
[1, 2, … , K]
Modeling
Speaker Model
This part is done outside the DSP and the DSP receives only the speaker model (calculated offline in a host).

36. Pattern Matching Speaker Model Pattern Matching Matching Rate
Set of Feature Vectors
[1, 2, … , K]
Pattern
Matching
Matching Rate

37. Decision Module (Optional)
In VQ the decision is based on checking if the distortion rate is higher than a preset threshold:
if distortion rate > t, Output = Yes,
else Output = No.
In HMM the decision is based on checking if the probability score is higher than a preset threshold:
if probability scores > t, Output = Yes,

38. The Voice Database
Two reference models were generated (one male and one female),
each model was trained in 3 different ways:
repeating the same sentence for 15 seconds
repeating the same sentence for 40 seconds
reading random text for one minute
The voice database is compound from 10 different speakers (5
males and 5 females), each speaker was recorded in 3 ways:
repeating the reference sentence once (5 seconds)
repeating the reference sentence 3 times (15 seconds)
speaking a random sentence for 5 seconds

39. Experiment Description Cont.
Conclusions:
Window size of 330 and offset of 110 samples performs better than window size of 256 and offset of 128 samples

40. Experiment Description Cont.
Conclusions:
Feature vector of 18 coeffs is better than feature vector of 12 coeffs

41. Experiment Description Cont.
Conclusions:
Worst combinations:
5 seconds of fixed sentence for testing with an
enrolment of 15 seconds of the same sentence.
enrolment of 40 seconds of the same sentence.
Best combinations:
15 seconds of fixed sentence for testing with an
enrolment of 40 seconds of the same sentence.
enrolment of 60 seconds of random sentences.
5 seconds of a random sentence with an

42. Experiment Description Cont.
The Best Results:

43. Additional verification results
The DSP results were compared to the Matlab simulation.
We chose random speakers from the speakers DB with one reference codebook.
For Example:
Person MATLAB DSP
Alex % (0.3627) % (0.3627)
Sari % (0.4835) % (0.4835)
Roee % (0.6938) % (0.6938)
Eran % (0.6023) % (0.6023)
Hila % (0.5849) 55.72% (0.5849)