A blind approach for estimating the signal to noise ratio (SNR) of a speech signal corrupted by additive noise is proposed. The method is based on a pattern recognition paradigm using various linear predictive based features, a vector quantizer classifier and estimation combination. Blind SNR estimation is very useful in biometric speaker identification systems in which a confidence metric is determined along with the speaker identity. The confidence metric is partially based on the mismatch between the training and testing conditions of the speaker identification system and SNR estimation is very important in evaluating the degree of this mismatch.
The educational impact of this project is two-fold:
1. Undergraduate students are initiated into research/development by working on a team to achieve a software implementation of the SNR estimation system. The students will also evaluate the performance of the system by experimenting with different features and classifiers. Producing a paper in a refereed technical conference is the objective.
2. The students will also write a laboratory manual for a portion of this project to be run in a junior level signals and systems class and a senior level class on speech processing. Producing a paper in a refereed education conference is the objective.
The learning outcomes for the students engaged in research and for the students doing the project in a class include:
• Enhanced application of math skills
• Enhanced software implementation skills
• Enhanced interest in signal processing
• Enhanced ability to analyze experimental results
• Enhanced communication skills
The assessment instruments include:
• Student surveys (target versus control group comparison that includes a statistical analysis)
• Faculty tracking of student learning outcomes based on student work
• Faculty evaluation of student work based on significant rubrics
• A concept inventory test
Rowan University Electrical and Computer Engineering student.
Ravi P. Ramachandran received the B. Eng degree (with great distinction) from Concordia University in 1984, the M. Eng degree from McGill University in 1986 and the Ph.D. degree from McGill University in 1990. From October 1990 to December 1992, he worked at the Speech Research Department at AT&T Bell Laboratories. From January 1993 to August 1997, he was a Research Assistant Professor at Rutgers University. He was also a Senior Speech Scientist at T-Netix from July 1996 to August 1997. Since September 1997, he is with the Department of Electrical and Computer Engineering at Rowan University where he has been a Professor since September 2006. He has served as a consultant to T-Netix, Avenir Inc., Motorola and Focalcool. From September 2002 to September 2005, he was an Associate Editor for the IEEE Transactions on Speech and Audio Processing and was on the Speech Technical Committee for the IEEE Signal Processing society. Since September 2000, he has been on the Editorial Board of the IEEE Circuits and Systems Magazine. Since May 2002, he has been on the Digital Signal Processing Technical Committee for the IEEE Circuits and Systems society. His research interests are in digital signal processing, speech processing, biometrics, pattern recognition and filter design.
Kevin Dahm is a Professor of Chemical Engineering at Rowan University. He earned his BS from Worcester Polytechnic Institute (92) and his PhD from Massachusetts Institute of Technology (98). He has published two books, "Fundamentals of Chemical Engineer
Dr. Nazari is an assistant professor of Civil and Environmental Engineering at Rowan University. His primary research interests are: application of remote sensing in water technologies and environment, resiliency and water reuse, impact assessment of climate change and extreme weather events on cities. Dr. Nazari is has worked with NASA, NOAA, Consortium on Climate Risk in the Urban Northeast, and New York State Resiliency Institute for Storms & Emergencies teams of active researchers who focus on climate issues affecting the urban corridor encompassing the U.S. Northeast. Dr. Nazari has published several book chapters, journal papers and has presented his work in national and international conferences.
Umashanger Thayasivam an Associate Professor of Statistics from Rowan University. I have expertise in robust estimation with mixture models. My research interests include mixture models, robust estimation and statistical applications in STEM. My interdisciplinary statistical research has spanned diverse areas including statistical data mining, speaker recognition systems, spoof detection, spectrum sensing and network security. I have more than ten journal publications and several conference presentations.
I have been PI/co-PI for several internal and external grants and collaborations, including the ongoing three year collaboration data mining project with Bristol Myers Squibb pharmaceutical company, Rowan University Seed grant for a study of statistical and data mining techniques in the field of network security and computer forensics, as well as College of Science and Mathematics grant for evaluation of data classification techniques. I also am performing Biomarker research aimed at optimizing and verifying the utility of autoantibody biomarkers for early diagnosis-Biomarker Discovery Center at Rowan SOM. Where I ensure that all of the data evaluation strategies and methodologies employed in the studies will take full advantage of any recent developments, improvements and alternative analytical approaches.
Are you a researcher? Would you like to cite this paper? Visit the ASEE document repository at peer.asee.org for more tools and easy citations.