Introducing Machine Learning in Undergraduate DSP Classes

Uday S. Shanthamallu, Sunil Rao, Abhinav Dixit, Vivek S. Narayanaswamy, Jie Fan, Andreas Spanias

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Machine Learning (ML) and Artificial Intelligence (AI) algorithms are enabling several modern smart products and devices. Furthermore, several initiatives such as smart cities and autonomous vehicles utilize AI and ML computational engines. The current and emerging applications and the growing industrial interest in AI necessitate introducing ML algorithms at the undergraduate level. In this paper, we describe a series of activities to introduce ML in undergraduate digital signal processing (DSP) classes. These activities include a computational comparative study of ML algorithms for spoken digit recognition using spectral representations of speech. We choose spectral representations and features for speech as those concepts associate with the core topics in DSP such as FFT and autoregressive spectra. Our primary objective is to introduce undergraduate DSP students to feature extraction and classification using appropriate signal analysis and ML tools. An online module on ML along with a computer exercise are developed and assigned as a semester project in the DSP class. The exercise is developed in Python and also on the online JDSP HTML5 environments. An assessment study of the modules and computer exercises are also part of this effort.

Original languageEnglish (US)
Title of host publication2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages7655-7659
Number of pages5
ISBN (Electronic)9781479981311
DOIs
StatePublished - May 1 2019
Event44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Brighton, United Kingdom
Duration: May 12 2019May 17 2019

Publication series

NameICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings
Volume2019-May
ISSN (Print)1520-6149

Conference

Conference44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019
CountryUnited Kingdom
CityBrighton
Period5/12/195/17/19

Fingerprint

Digital signal processing
Learning systems
Artificial intelligence
Learning algorithms
Signal analysis
Fast Fourier transforms
Feature extraction
Students
Engines

Keywords

  • AI
  • DSP education
  • J-DSP
  • Machine Learning
  • Online laboratory
  • Python
  • Spectrogram

ASJC Scopus subject areas

  • Software
  • Signal Processing
  • Electrical and Electronic Engineering

Cite this

Shanthamallu, U. S., Rao, S., Dixit, A., Narayanaswamy, V. S., Fan, J., & Spanias, A. (2019). Introducing Machine Learning in Undergraduate DSP Classes. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings (pp. 7655-7659). [8683780] (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/ICASSP.2019.8683780

Introducing Machine Learning in Undergraduate DSP Classes. / Shanthamallu, Uday S.; Rao, Sunil; Dixit, Abhinav; Narayanaswamy, Vivek S.; Fan, Jie; Spanias, Andreas.

2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. p. 7655-7659 8683780 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings; Vol. 2019-May).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Shanthamallu, US, Rao, S, Dixit, A, Narayanaswamy, VS, Fan, J & Spanias, A 2019, Introducing Machine Learning in Undergraduate DSP Classes. in 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings., 8683780, ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings, vol. 2019-May, Institute of Electrical and Electronics Engineers Inc., pp. 7655-7659, 44th IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019, Brighton, United Kingdom, 5/12/19. https://doi.org/10.1109/ICASSP.2019.8683780
Shanthamallu US, Rao S, Dixit A, Narayanaswamy VS, Fan J, Spanias A. Introducing Machine Learning in Undergraduate DSP Classes. In 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. p. 7655-7659. 8683780. (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings). https://doi.org/10.1109/ICASSP.2019.8683780
Shanthamallu, Uday S. ; Rao, Sunil ; Dixit, Abhinav ; Narayanaswamy, Vivek S. ; Fan, Jie ; Spanias, Andreas. / Introducing Machine Learning in Undergraduate DSP Classes. 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. pp. 7655-7659 (ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings).
@inproceedings{63709e7d57be4874bada8ef69bdc5713,
title = "Introducing Machine Learning in Undergraduate DSP Classes",
abstract = "Machine Learning (ML) and Artificial Intelligence (AI) algorithms are enabling several modern smart products and devices. Furthermore, several initiatives such as smart cities and autonomous vehicles utilize AI and ML computational engines. The current and emerging applications and the growing industrial interest in AI necessitate introducing ML algorithms at the undergraduate level. In this paper, we describe a series of activities to introduce ML in undergraduate digital signal processing (DSP) classes. These activities include a computational comparative study of ML algorithms for spoken digit recognition using spectral representations of speech. We choose spectral representations and features for speech as those concepts associate with the core topics in DSP such as FFT and autoregressive spectra. Our primary objective is to introduce undergraduate DSP students to feature extraction and classification using appropriate signal analysis and ML tools. An online module on ML along with a computer exercise are developed and assigned as a semester project in the DSP class. The exercise is developed in Python and also on the online JDSP HTML5 environments. An assessment study of the modules and computer exercises are also part of this effort.",
keywords = "AI, DSP education, J-DSP, Machine Learning, Online laboratory, Python, Spectrogram",
author = "Shanthamallu, {Uday S.} and Sunil Rao and Abhinav Dixit and Narayanaswamy, {Vivek S.} and Jie Fan and Andreas Spanias",
year = "2019",
month = "5",
day = "1",
doi = "10.1109/ICASSP.2019.8683780",
language = "English (US)",
series = "ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
pages = "7655--7659",
booktitle = "2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings",

}

TY - GEN

T1 - Introducing Machine Learning in Undergraduate DSP Classes

AU - Shanthamallu, Uday S.

AU - Rao, Sunil

AU - Dixit, Abhinav

AU - Narayanaswamy, Vivek S.

AU - Fan, Jie

AU - Spanias, Andreas

PY - 2019/5/1

Y1 - 2019/5/1

N2 - Machine Learning (ML) and Artificial Intelligence (AI) algorithms are enabling several modern smart products and devices. Furthermore, several initiatives such as smart cities and autonomous vehicles utilize AI and ML computational engines. The current and emerging applications and the growing industrial interest in AI necessitate introducing ML algorithms at the undergraduate level. In this paper, we describe a series of activities to introduce ML in undergraduate digital signal processing (DSP) classes. These activities include a computational comparative study of ML algorithms for spoken digit recognition using spectral representations of speech. We choose spectral representations and features for speech as those concepts associate with the core topics in DSP such as FFT and autoregressive spectra. Our primary objective is to introduce undergraduate DSP students to feature extraction and classification using appropriate signal analysis and ML tools. An online module on ML along with a computer exercise are developed and assigned as a semester project in the DSP class. The exercise is developed in Python and also on the online JDSP HTML5 environments. An assessment study of the modules and computer exercises are also part of this effort.

AB - Machine Learning (ML) and Artificial Intelligence (AI) algorithms are enabling several modern smart products and devices. Furthermore, several initiatives such as smart cities and autonomous vehicles utilize AI and ML computational engines. The current and emerging applications and the growing industrial interest in AI necessitate introducing ML algorithms at the undergraduate level. In this paper, we describe a series of activities to introduce ML in undergraduate digital signal processing (DSP) classes. These activities include a computational comparative study of ML algorithms for spoken digit recognition using spectral representations of speech. We choose spectral representations and features for speech as those concepts associate with the core topics in DSP such as FFT and autoregressive spectra. Our primary objective is to introduce undergraduate DSP students to feature extraction and classification using appropriate signal analysis and ML tools. An online module on ML along with a computer exercise are developed and assigned as a semester project in the DSP class. The exercise is developed in Python and also on the online JDSP HTML5 environments. An assessment study of the modules and computer exercises are also part of this effort.

KW - AI

KW - DSP education

KW - J-DSP

KW - Machine Learning

KW - Online laboratory

KW - Python

KW - Spectrogram

UR - http://www.scopus.com/inward/record.url?scp=85069542077&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069542077&partnerID=8YFLogxK

U2 - 10.1109/ICASSP.2019.8683780

DO - 10.1109/ICASSP.2019.8683780

M3 - Conference contribution

T3 - ICASSP, IEEE International Conference on Acoustics, Speech and Signal Processing - Proceedings

SP - 7655

EP - 7659

BT - 2019 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2019 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

ER -