Audio Processing MATLAB Projects - MATLAB Solutions

Ultra-Short Baseline Acoustic Positioning System

The design, implementation, and testing of an ultra short baseline (USBL) acoustic positioning system for the Amador Valley High School (AVHS) Robotics Clubs Barracuda Mark-X AUV. The system will be used to locate an underwater transducer beacon representing the final waypoint in an obstacle course designed for the AUVSI/ONR RoboSub international collegiate competition.

The USBL acoustic subsystem obtains input from the external environment via an array of four RESON TC4013 Miniature Reference Omni-directional hydrophones. The piezoelectric sensor element contained inside the rubber nibble produces an electrical signal on the order of approximately 40mv, which propagates up the coaxial cable. The electrical signal is amplified to satisfy the requirements of the dspblok ad96k42 audio I/O platform.

Lip Detection and Adaptive Tracking

Performance of automatic speech recognition (ASR) systems utilizing only acoustic information degrades significantly in noisy environments such as car cabins. Incorporating audio and visual information together can improve performance in these situations. This work proposes a lip detection and tracking algorithm to serve as a visual front end to an audio-visual automatic speech recognition (AVASR) system.

Several color spaces are examined that are effective for segmenting lips from skin pixels. These color components and several features are used to characterize lips and to train cascaded lip detectors. Pre- and post-processing techniques are employed to maximize detector accuracy. The trained lip detector is incorporated into an adaptive mean-shift tracking algorithm for tracking lips in a car cabin environment. The resulting detector achieves 96.8% accuracy, and the tracker is shown to recover and adapt in scenarios where mean-shift alone fails.

Active Noise Cancellation

A noise-cancellation system implemented using DSK with two microphones and one speaker. The first microphone samples unexpected external noises while the second collects all sounds, including desired signals and noise. An LMS adaptive filter generates an anti-noise signal with a 180° phase shift which is played back to cancel the unwanted noise.

Detection of Breathing and Infant Sleep Apnea

Develop a device to accurately detect breathing through sound and issue warnings upon cessation. The device is implemented as an embedded systems project on a Xilinx Spartan 6 FPGA to provide a standalone monitoring solution for infants and premature babies.

A Guide to Producing An A Cappella CD and Development of a Pitch Detection Program

An in-depth look at steps required to produce a CD for an a cappella group plus exploration of pitch detection algorithms. The project covers microphone selection, editing, mixing, mastering and a MATLAB implementation of a pitch detection program.

Monophonic Pitch Recognition

Create a system that converts monophonic music into MIDI in real time. The project analyzes a single-pitch audio signal, estimates the fundamental frequency, and outputs MIDI data that represents pitch and timing for real-time transcription and instrument substitution.

Monophonic Pitch Recognition using MATLAB

MATLAB-based implementation for monophonic pitch estimation, using FFT-based power spectrum analysis and region-based processing to make real-time detection efficient and accurate.

Subwoofer Frequency Response Optimization by Means of Active Control

Implement active controls (Linkwitz transform crossover) and MATLAB GUI tools to extend low-end frequency response of a sealed subwoofer enclosure; includes circuit construction and real-time measurements with a Real Time Analyzer.

Development of a Voice Conversion System using MATLAB

Voice conversion techniques to modify a source speaker's utterance so it sounds like a target speaker. The project studies vocal tract structure and pitch conversion approaches and implements methods in MATLAB for static voice conversion.

Characterization of Auditory Evoked Potentials from Transient Binaural Beats

Study auditory steady state responses (ASSR) evoked by binaural beats and analyze small EEG/MEG signals using signal processing techniques to extract ASSR from surrounding cortical activity.

Swept-Tone Evoked Otoacoustic Emissions: Stimulus Calibration and Equalization

Design and equalize swept-tone stimuli for otoacoustic emission acquisition; use deconvolution to compress swept-tone responses and improve OAE detection compared to conventional click stimuli.

Acquisition of Otoacoustic Emissions Using Swept-Tone Techniques

Develop high-resolution instrumentation and acquisition techniques to improve OAE measurements and reveal early-latency, high-frequency otoacoustic emissions using high bit-depth capture hardware.

De-Noising Audio Signals Using MATLAB Wavelets Toolbox

Use wavelet-based denoising techniques in MATLAB to model and remove noise and distortion from audio signals across a range of applications including speech recognition, medical signal processing, sonar, and telecommunications.

Music Note Recognition

Real-time estimation of fundamental frequency for music note recognition using FFT-based power-spectrum analysis and region-based note detection to improve runtime efficiency and accuracy. Sampling typically at 44.1 kHz for compatibility with audio devices.