Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Classification of Signals01:30

Classification of Signals

575
In signal processing, signals are classified based on various characteristics: continuous-time versus discrete-time, periodic versus aperiodic, analog versus digital, and causal versus noncausal. Each category highlights distinct properties crucial for understanding and manipulating signals.
A continuous-time signal holds a value at every instant in time, representing information seamlessly. In contrast, a discrete-time signal holds values only at specific moments, often denoted as x(n), where...
575

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Mad Honey Poisoning in Nepal: A Case Report.

Clinical case reports·2025
Same author

HIVAC (HIV-associated cardiomyopathy): An overlooked complication of HIV in developing countries.

Clinical case reports·2024
Same author

Hypocalcemic cardiomyopathy with heart failure: A rare Case report.

Clinical case reports·2024
Same author

Use of lecanemab for the treatment of Alzheimer's disease: A systematic review.

Brain and behavior·2024
Same author

A case report of cutaneous tuberculosis.

International journal of dermatology·2023
Same author

Post-COVID-19 Illness Trend in a Local Community in Bangladesh.

Cureus·2023

Related Experiment Video

Updated: Aug 4, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

483

BAAD: A multipurpose dataset for automatic Bangla offensive speech recognition.

Md Fahad Hossain1, Md Al Abid Supto2, Zannat Chowdhury2

  • 1Department of Computer Science and Engineering, Daffodil International University, Bangladesh.

Data in Brief
|April 7, 2023
PubMed
Summary

This study introduces a new Bengali Abusive Words speech dataset, crucial for developing automatic slang speech recognition systems for the Bangla language. The dataset aids in advancing machine learning models for speech recognition in underrepresented languages.

Keywords:
Bangla offensive speechMultipurpose datasetOffensive speechSpeech recognition

More Related Videos

Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

152
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K

Related Experiment Videos

Last Updated: Aug 4, 2025

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
09:09

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody

Published on: September 27, 2024

483
Asthma Detection Research Based on Voice Signal Processing and Machine Learning
04:04

Asthma Detection Research Based on Voice Signal Processing and Machine Learning

Published on: July 22, 2025

152
Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
05:48

Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception

Published on: August 9, 2024

1.6K

Area of Science:

  • Computational Linguistics
  • Speech Technology
  • Natural Language Processing

Background:

  • Bangla, the fifth most spoken native language, is significantly underrepresented in audio and speech recognition research.
  • Existing speech recognition systems lack adequate resources for nuanced linguistic features like slang in Bangla.
  • The development of specialized datasets is essential to bridge this gap and improve language technology accessibility.

Purpose of the Study:

  • To introduce a comprehensive speech dataset of Bengali Abusive Words and closely related non-abusive words.
  • To facilitate the development of automatic slang speech recognition systems for the Bangla language.
  • To establish a new benchmark for speech recognition and machine learning model development in Bangla.

Main Methods:

  • Data collection involved native speakers from over 20 districts in Bangladesh, covering diverse dialects.
  • Annotation and refinement were performed by 60 native speakers for slang words and 23 for non-slang words.
  • The dataset comprises 114 slang words and 43 non-slang words, totaling 6100 audio clips, with input from 10 university students for evaluation.

Main Results:

  • A multipurpose dataset containing 6100 audio clips of Bengali slang and non-slang words has been successfully compiled.
  • The dataset includes phonetic variations from various dialects across Bangladesh, enhancing its real-world applicability.
  • The data has undergone annotation and refinement, ensuring quality for research purposes.

Conclusions:

  • The presented dataset is a valuable resource for researchers aiming to build automatic Bengali Slang speech recognition systems.
  • This resource can serve as a benchmark for future speech recognition and machine learning model development in the Bangla language.
  • The dataset's potential for further enrichment, including the addition of background noise, offers avenues for simulating more realistic scenarios.