17″ Screen required for Dualtech (BF-polygraph + AVSAPRO)
i5 GHZ processor with 4GIG RAM (i7 /16GIG for Dualtech testing)
4 GIG USB memory stick
RCA analog microphone, Uni-Directional microphone or USB analog headset
Examiner may run email & internet whilst conducting DOD testing
Use same laptop for all other bus apps, including report writing
Sample report templates included
Sample question protocols included
Examiner may build own protocols for auto scoring or manual scoring
Run BF-polygraph and AVSAPRO tests same time, in real time, on same PC using mouse control
Various VSA software programs offer a graphic representation derived from that obtained on the input feed.
AVSAPRO uses sound recordings made in *.WAV format up to 11,025 Hz, 8bits.
Voice sounds are filtered by retaining low frequencies. The envelope is not the most interesting feature. Modulation is added in order to bring out the low frequency oscillations.
Some VSA software programs use a theory developed by the British physiologist Olaf Lippold in 1957, by extracting the low frequency of about 8 to 12 Hz and deducing a value of stress thereon.
Understandably, it’s not too difficult to compute the frequency for the wave displayed in Image 1, but it becomes much more complex for graphs as displayed in image 2.
AVSAPRO software now uses a new technique for calculating the value of stress, to score voice waves and not one based on direct, manual analysis of the micro-tremor.
AVSAPRO software uses a knowledge base collected from several VSA experts. Approximately 5,000 pre-scored voice signatures are retained in a neural network database.
A totally independent scoring exercise was conducted by VSA experts. At the culmination of the project it was notable that 80% of the results presented only 5% difference on the estimated values of stress, which provides a consistent and reliable basis for the techniques used by AVSAPRO Software.
The technique consists in training a neural network with 5,000 phonemes (utterances) from interrogations. The voice samples are processed to obtain the graphs as per Image 1 and Image 2 above.
These graphs were digitized to provide a basic set for training the neural network. The training of the neural network generates a file of weights that are at the heart of the network processor. Some parameters are used to adjust the neural network ; ie : the number of neurons in input, the threshold, the desired error (1%). The duration of training is approximately 45 minutes on a standard PC.
A fundamental property of the neural network is its capability to produce a reliable result when we enter a voice graph for which it has not been trained. When we submit a graph for which it was not trained, it will produce a result with the specified error (1%). Other external errors may influence the overall error rate e.g. examiner training and skill set.
AVSAPRO extracts phonemes in real time and digitizes the waves. Charts are submitted to the network and thereafter the results are displayed. Another interesting neural network property is that there is no need to calculate complicated mathematical formulas in order to extract frequencies of micro tremors. The neural processor teaches itself how to deduct the outcome on the basis of data provided.
It is totally free from the assumption 11-12 Hz for low stress and 4-8 HZ for the presence of stress. Our only certainty is the know-how of human experts who have conducted thousands of successful VSA examinations, together with known solution outcomes.
AVSAPRO software can calculate up to 20 estimates of stress per second on a standard PC. Charted tests (validated protocols) are scored within 2 seconds. Exam scores (average of the tests conducted) are displayed instantly at the culmination of the last test chart. AVSAPRO currently provides THREE commercial versions :
Version 20 : For structured DOD interview examinations + all auto features. Manual operation is still retained.
Version 17 : For free flow, real time narrative screening. Easy to follow graphics for operators processing high volumes of subjects. Two stress levels engines are provided.
Version 100: which combines the two previous versions and includes built-in question libraries and easy Build-A-Test feature with crime specific libraries. Also specific libraries for Pre-Employment screening and Periodic screening.
AVSAPRO may be used easily and successfully over smart phones. A 1:2 RCA splitter, a RCA flylead + mobile headphone is required.
Both programs feature ‘Autogain’ to compensate for low input volumes.