Transcript example
Department of Electrical Engineering | University of Texas at Dallas Erik Jonsson School of Engineering & Computer Science | Richardson, Texas 75083-0688, U.S.A. Design and fabricate a new microphone array system which will: Minimize the feature size of the array system by integration of the microphone and preamplifier circuit. Reduce noise factors and electro magnetic interferences Be a portable microphone array and power regulation system Determine the array configuration and array processing method that will give the optimum speech to noise ratio. Implement a speaker recognition system to determine who is speaking among a closed set of known drivers. Explore the use of Wireless Transmission, VoIP, and Packet Loss Concealment Power Regulation Microphone Array Microphone Array Circuit Design Power Regulation Circuit Design • Designed and simulated using TinyCad and PSpice • Integrated Microphone & Preamplifier • Bandpass filtering through 100Hz to 20kHz • Gain 45V/V • Designed and simulated using TinyCad and PSpice • Design for ±5VDC output power for Multiple Power Outlets • Used Positive Voltage Regulator and Voltage Converter • Bypass Capacitor: Stable Output Power Create PCB Layout • • • • • Create PCB Layout Layout design by FreePCB Feature size: 24mm x 24mm Edited Footprint for SMD type Left side: Top view of Mic. PCB Right side: Bottom view of Mic. PCB • • • • Layout design by FreePCB Feature size: 66mm x 45mm Green Trace: Top view Red Trace: Bottom view Fabricate Microphone Array • Used LPKF ProtoMat PCB Milling Plotter • Yields: 3 Arrays (15 Microphones) • Components: • Op-Amp (MC33204DTB), • Microphone (EK-23024), • SMD Resistors and Capacitors Microphone Preamplifier Circuit Power Regulator Microphone & Preamplifier Circuit Data Acquisition (DEWTRON) • • • • • Used LPKF ProtoMat PCB Milling Plotter Five power outlet in one line Input Power: 12VDC and 3A Output Power: +5VDC and -5VDC Components: • Positive Voltage Regulator(7805) • Voltage Converter(LMC7660) Performance • • • • • Bandpass filtering frequency: 50Hz-10kHz Gain: 45V/V Diode indicators for power/signal Input Power: +5VDC and -5VDC Feature Size: Same size as a dime (24mm x 24mm) Data Acquisition (DEWTRON) DASB Segmented SNR Power Regulator Bandpass Filter for Human Voice (20Hz – 20kHz) Fabricate Power Regulator Differential Amplifier Gain: 45 V/V CSA-BF close talk Channel 3 close talk Channel 3 Linear Sample 18.0166 dB 28.6192 dB 27.9125 dB 28.0366 dB Logarithmic Sample 18.1457 dB 28.0393 dB 28.1584 dB 28.1943 dB CSA-BF showed significant improvement over DASB in the segmental signal-to-noise ratio test and the logarithmic array setup showed a small increase in the segmental SNR over the linear array setup. Test Previous Microphone Array System Design New Microphone Array System 0.04 50 0.03 48 46 44 0.02 40 0.01 -0.04 • Design microphone circuitry • Design power supply circuitry • Create microphone PCB • Create power supply PCB • Design new microphone enclosure • Construct physical array • Fix problems with old array. Sean Stixrud Corrupted • Array configuration to yield an optimum speech to noise ratio • Signal processing methods to yield an optimum speech to noise ratio Jeffery Leinbaugh Kevin Derischebourg • Set up and test speaker recognition software • Evaluate speaker recognition performance with in car audio with engine noise • Evaluate speaker recognition performance using high pass filter to remove engine noise • Study Wireless Transmission • Study Voice over IP (VoIP) • Practice and determine the best Packet Loss Concealment Algorithm 15-inset EER 4 seconds 6 seconds 8 seconds 15-inset EER 44.213 42.963 40.833 47.500 30-inset EER 45.000 45.833 45.833 43.333 45-inset EER 46.944 48.889 45.833 41.667 Frame Repeat Frame (Recovered) Interpolation (Recovered) Given a corrupted signal, we used two different PLC Algorithms to “fill” the gaps. Chance Kelly 49001 48951 48901 48851 -0.03 Jeong Hee Kim and Tae Hwan Kim 2 seconds 2 seconds 4 seconds 6 seconds 8 seconds -0.02 Assemble and Test 30-inset EER 36 0 -0.01 Design and Construct PCB Enclosures 45-inset EER 38 48800 Amplitude Populate Circuit Board Fabricate Microphone Array Circuitry 42 Speaker recognition test with UTDrive corpus database using 2-8 seconds of speech MICROPHONES In the future, audio collected during UTDrive may be sent wirelessly for collection rather than recorded to a hard drive physically present in the vehicle. VoIP allows transmission of speech over the Internet real-time, which can be effective for recording to a hard drive remotely. VoIP audio, however, suffers quality loss when packets are dropped from poor connections. The received audio has gaps where the packets are dropped and causes the audio to have significantly degraded quality. As quality continues to drop, it becomes harder to understand what the speaker is saying. A further loss in quality makes it difficult to understand who is even speaking, let alone what they are saying. To help understand these premises we: Created a survey to determine a minimum quality of voice that a listener was willing to listen to and could understand. Surveyed listeners to see what minimum quality is needed to at least understand who the speaker is, given an unaffected voice sample. Surveyed listeners to see which packet loss concealment scheme (a simple one) is useful for recovering lost quality. Packet loss concealment is used to make up for times when packets are dropped---trying to fill in the "blanks" can potentially recover lost quality. Speaker recognition is a process by which the identity of a speaker can be determined. This project is only concerned with closed set speaker recognition, meaning the speaker is assumed to belong to a known set of people whose voices have already been collected and processed to produce Gaussian Mixture Models (GMMs). The speaker recognition software will perform feature extraction on short voice samples and compare them to the existing GMMs to determine a best fit. PREAMPLIFIER DATA ACQUISITION MICROPHONES WITH PREAMPLIFIER POWER SIGNAL BOX POWER Because the close talk microphone sample was not very clean, the comparison of the beam formed sample to channel 3 resulted in a higher segmented SNR value than that of the beam formed sample and the close talk microphone. This problem with the close talk microphone will be addressed in the next phase of the project. HTK was used to perform speaker recognition on clean out of car data. Results for in car recordings could not be obtained for various reasons, including engine noise, interference, and competing speakers in the vehicle. These problems will be addressed next semester with the new microphone array and beam forming software.