Abstract

This work in progress paper describes software that enables online machine learning experiments in an undergraduate DSP course. This software operates in HTML5 and embeds several digital signal processing functions. The software can process natural signals such as speech and can extract various features, for machine learning applications. For example in the case of speech processing, LPC coefficients and formant frequencies can be computed. In this paper, we present speech processing, feature extraction and clustering of features using the K-means machine learning algorithm. The primary objective is to provide a machine learning experience to undergraduate students. The functions and simulations described provide a user-friendly visualization of phoneme recognition tasks. These tasks make use of the Levinson-Durbin linear prediction and the K-means machine learning algorithms. The exercise was assigned as a class project in our undergraduate DSP class. The description of the exercise along with assessment results is described.

Original languageEnglish (US)
Title of host publicationFrontiers in Education
Subtitle of host publicationFostering Innovation Through Diversity, FIE 2018 - Conference Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781538611739
DOIs
StatePublished - Mar 4 2019
Event48th Frontiers in Education Conference, FIE 2018 - San Jose, United States
Duration: Oct 3 2018Oct 6 2018

Publication series

NameProceedings - Frontiers in Education Conference, FIE
Volume2018-October
ISSN (Print)1539-4565

Conference

Conference48th Frontiers in Education Conference, FIE 2018
CountryUnited States
CitySan Jose
Period10/3/1810/6/18

Fingerprint

Learning systems
experiment
Speech processing
learning
Experiments
Learning algorithms
Digital signal processing
visualization
Feature extraction
Visualization
Students
simulation
software
experience
student

Keywords

  • Linear Predictive Coding
  • Machine Learning
  • Online labs
  • Speech recognition

ASJC Scopus subject areas

  • Software
  • Education
  • Computer Science Applications

Cite this

Dixit, A., Shanthamallu, U. S., Spanias, A., Berisha, V., & Banavar, M. (2019). Online Machine Learning Experiments in HTML5. In Frontiers in Education: Fostering Innovation Through Diversity, FIE 2018 - Conference Proceedings [8659113] (Proceedings - Frontiers in Education Conference, FIE; Vol. 2018-October). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/FIE.2018.8659113

Online Machine Learning Experiments in HTML5. / Dixit, Abhinav; Shanthamallu, Uday Shankar; Spanias, Andreas; Berisha, Visar; Banavar, Mahesh.

Frontiers in Education: Fostering Innovation Through Diversity, FIE 2018 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. 8659113 (Proceedings - Frontiers in Education Conference, FIE; Vol. 2018-October).

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

Dixit, A, Shanthamallu, US, Spanias, A, Berisha, V & Banavar, M 2019, Online Machine Learning Experiments in HTML5. in Frontiers in Education: Fostering Innovation Through Diversity, FIE 2018 - Conference Proceedings., 8659113, Proceedings - Frontiers in Education Conference, FIE, vol. 2018-October, Institute of Electrical and Electronics Engineers Inc., 48th Frontiers in Education Conference, FIE 2018, San Jose, United States, 10/3/18. https://doi.org/10.1109/FIE.2018.8659113
Dixit A, Shanthamallu US, Spanias A, Berisha V, Banavar M. Online Machine Learning Experiments in HTML5. In Frontiers in Education: Fostering Innovation Through Diversity, FIE 2018 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc. 2019. 8659113. (Proceedings - Frontiers in Education Conference, FIE). https://doi.org/10.1109/FIE.2018.8659113
Dixit, Abhinav ; Shanthamallu, Uday Shankar ; Spanias, Andreas ; Berisha, Visar ; Banavar, Mahesh. / Online Machine Learning Experiments in HTML5. Frontiers in Education: Fostering Innovation Through Diversity, FIE 2018 - Conference Proceedings. Institute of Electrical and Electronics Engineers Inc., 2019. (Proceedings - Frontiers in Education Conference, FIE).
@inproceedings{bb34b2872db24417b5f8df6e42d202ef,
title = "Online Machine Learning Experiments in HTML5",
abstract = "This work in progress paper describes software that enables online machine learning experiments in an undergraduate DSP course. This software operates in HTML5 and embeds several digital signal processing functions. The software can process natural signals such as speech and can extract various features, for machine learning applications. For example in the case of speech processing, LPC coefficients and formant frequencies can be computed. In this paper, we present speech processing, feature extraction and clustering of features using the K-means machine learning algorithm. The primary objective is to provide a machine learning experience to undergraduate students. The functions and simulations described provide a user-friendly visualization of phoneme recognition tasks. These tasks make use of the Levinson-Durbin linear prediction and the K-means machine learning algorithms. The exercise was assigned as a class project in our undergraduate DSP class. The description of the exercise along with assessment results is described.",
keywords = "Linear Predictive Coding, Machine Learning, Online labs, Speech recognition",
author = "Abhinav Dixit and Shanthamallu, {Uday Shankar} and Andreas Spanias and Visar Berisha and Mahesh Banavar",
year = "2019",
month = "3",
day = "4",
doi = "10.1109/FIE.2018.8659113",
language = "English (US)",
series = "Proceedings - Frontiers in Education Conference, FIE",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
booktitle = "Frontiers in Education",

}

TY - GEN

T1 - Online Machine Learning Experiments in HTML5

AU - Dixit, Abhinav

AU - Shanthamallu, Uday Shankar

AU - Spanias, Andreas

AU - Berisha, Visar

AU - Banavar, Mahesh

PY - 2019/3/4

Y1 - 2019/3/4

N2 - This work in progress paper describes software that enables online machine learning experiments in an undergraduate DSP course. This software operates in HTML5 and embeds several digital signal processing functions. The software can process natural signals such as speech and can extract various features, for machine learning applications. For example in the case of speech processing, LPC coefficients and formant frequencies can be computed. In this paper, we present speech processing, feature extraction and clustering of features using the K-means machine learning algorithm. The primary objective is to provide a machine learning experience to undergraduate students. The functions and simulations described provide a user-friendly visualization of phoneme recognition tasks. These tasks make use of the Levinson-Durbin linear prediction and the K-means machine learning algorithms. The exercise was assigned as a class project in our undergraduate DSP class. The description of the exercise along with assessment results is described.

AB - This work in progress paper describes software that enables online machine learning experiments in an undergraduate DSP course. This software operates in HTML5 and embeds several digital signal processing functions. The software can process natural signals such as speech and can extract various features, for machine learning applications. For example in the case of speech processing, LPC coefficients and formant frequencies can be computed. In this paper, we present speech processing, feature extraction and clustering of features using the K-means machine learning algorithm. The primary objective is to provide a machine learning experience to undergraduate students. The functions and simulations described provide a user-friendly visualization of phoneme recognition tasks. These tasks make use of the Levinson-Durbin linear prediction and the K-means machine learning algorithms. The exercise was assigned as a class project in our undergraduate DSP class. The description of the exercise along with assessment results is described.

KW - Linear Predictive Coding

KW - Machine Learning

KW - Online labs

KW - Speech recognition

UR - http://www.scopus.com/inward/record.url?scp=85063513851&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85063513851&partnerID=8YFLogxK

U2 - 10.1109/FIE.2018.8659113

DO - 10.1109/FIE.2018.8659113

M3 - Conference contribution

AN - SCOPUS:85063513851

T3 - Proceedings - Frontiers in Education Conference, FIE

BT - Frontiers in Education

PB - Institute of Electrical and Electronics Engineers Inc.

ER -