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

Improving Translational Accuracy02:07

Improving Translational Accuracy

11.9K
Base complementarity between the three base pairs of mRNA codon and the tRNA anticodon is not a failsafe mechanism. Inaccuracies can range from a single mismatch to no correct base pairing at all. The free energy difference between the correct and nearly correct base pairs can be as small as 3 kcal/ mol. With complementarity being the only proofreading step, the estimated error frequency would be one wrong amino acid in every 100 amino acids incorporated. However, error frequencies observed in...
11.9K
Sign Test for Matched Pairs01:17

Sign Test for Matched Pairs

216
The sign test for matched pairs offers a robust method for comparing two paired samples, often for the effects of an intervention in one of them. This method is very useful in situations where the underlying distribution of the data is unknown. The test compares two related samples—often pre- and post-treatment measurements on the same subjects—to determine if there are significant differences in their median values.
To conduct the sign test, we first calculate the differences in...
216
Classification of Systems-II01:31

Classification of Systems-II

245
Continuous-time systems have continuous input and output signals, with time measured continuously. These systems are generally defined by differential or algebraic equations. For instance, in an RC circuit, the relationship between input and output voltage is expressed through a differential equation derived from Ohm's law and the capacitor relation,
245
Classification of Systems-I01:26

Classification of Systems-I

326
Linearity is a system property characterized by a direct input-output relationship, combining homogeneity and additivity.
Homogeneity dictates that if an input x(t) is multiplied by a constant c, the output y(t) is multiplied by the same constant. Mathematically, this is expressed as:
326
Random and Systematic Errors01:20

Random and Systematic Errors

12.7K
Scientists always try their best to record measurements with the utmost accuracy and precision. However, sometimes errors do occur. These errors can be random or systematic. Random errors are observed due to the inconsistency or fluctuation in the measurement process, or variations in the quantity itself that is being measured. Such errors fluctuate from being greater than or less than the true value in repeated measurements. Consider a scientist measuring the length of an earthworm using a...
12.7K
Classification of Signals01:30

Classification of Signals

935
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...
935

You might also read

Related Articles

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

Sort by
Same author

Deep Learning and Machine Learning Modeling Identifies Thidiazuron as a Key Modulator of Somatic Embryogenesis and Shoot Organogenesis in <i>Ferula assa-foetida</i> L.

Biology·2025
Same author

HiACC: Hinglish adult & children code-switched corpus.

Data in brief·2025
Same author

Condensate droplet roaming on nanostructured superhydrophobic surfaces.

Nature communications·2025
Same author

A High-Performance Antibacterial Nanostructured ZnO Microfluidic Device for Controlled Bacterial Lysis and DNA Release.

Antibiotics (Basel, Switzerland)·2023
Same author

Theoretical design for covering Engeletin with functionalized nanostructure-lipid carriers as neuroprotective agents against Huntington's disease via the nasal-brain route.

Frontiers in pharmacology·2023
Same author

Ultrathin Durable Organic Hydrophobic Coatings Enhancing Dropwise Condensation Heat Transfer.

Langmuir : the ACS journal of surfaces and colloids·2022

Related Experiment Video

Updated: Sep 20, 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

542

Developing sequentially trained robust Punjabi speech recognition system under matched and mismatched conditions.

Puneet Bawa1, Virender Kadyan2, Abinash Tripathy3

  • 1Centre of Excellence for Speech and Multimodal Laboratory, Chitkara University Institute of Engineering and Technology, Chitkara University, Punjab, India.

Complex & Intelligent Systems
|June 7, 2022
PubMed
Summary

Developing a robust native language automatic speech recognition (ASR) system is challenging. This study found that the PNCC+VTLN front-end approach with TDNN-sMBR optimization significantly improves ASR performance, especially in mismatched conditions.

Keywords:
Children speech recognitionData augmentationMismatched conditionsSequence discriminative training

More Related Videos

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
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

475

Related Experiment Videos

Last Updated: Sep 20, 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

542
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
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
06:04

Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages

Published on: March 24, 2023

475

Area of Science:

  • Speech Processing
  • Machine Learning
  • Signal Processing

Background:

  • Developing robust Automatic Speech Recognition (ASR) systems for native languages presents significant challenges due to environmental variations, large training data complexity, and inter-speaker variability.
  • Effective front-end feature extraction and back-end modeling approaches are crucial for ASR system success.

Purpose of the Study:

  • To investigate and develop a robust native language ASR framework.
  • To evaluate various front-end feature extraction methods and back-end sequence-discriminative training techniques.
  • To optimize system parameters for improved performance across matched and mismatched conditions.

Main Methods:

  • Investigated four front-end approaches: mel-frequency cepstral coefficients (MFCC), Gammatone frequency cepstral coefficients (GFCC), relative spectral-perceptual linear prediction (RASTA-PLP), and power-normalized cepstral coefficients (PNCC).
  • Employed sequence-discriminative training techniques including maximum mutual information (MMI), minimum phone error (MPE), boosted-MMI (bMMI), and state-level minimum Bayes risk (sMBR) for parameter optimization.
  • Tested systems with and without speaker normalization (Vocal Tract Length Normalization - VTLN) and artificial data augmentation on adult and child Punjabi speech corpora.

Main Results:

  • The proposed framework using the PNCC+VTLN front-end approach with a TDNN-sMBR-based model and parameter optimization achieved significant relative improvements.
  • Achieved a 40.18% relative improvement in matched conditions, 47.51% in mismatched conditions, and 49.87% in gender-based in-domain augmented systems.
  • Demonstrated the effectiveness of PNCC features and VTLN for handling acoustic and phonetic variations, particularly under noisy and mismatched scenarios.

Conclusions:

  • The combination of PNCC+VTLN front-end and TDNN-sMBR with parameter optimization offers a highly effective framework for robust native language ASR.
  • Gender-based in-domain data augmentation is a valuable strategy for mitigating performance degradation in mismatched conditions.
  • The developed framework shows substantial improvements in ASR accuracy for Punjabi speech, addressing key challenges in the field.