Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Related Concept Videos

Language Development

Language Development

Children master language quickly and with relative ease, supported by both biological predisposition and reinforcement. B. F. Skinner (1957) proposed that language is learned through reinforcement, while Noam Chomsky (1965) argued that language acquisition mechanisms are biologically determined.
The critical period for language acquisition suggests that the ability to acquire language is at its peak early in life. As people age, this proficiency decreases. Language development begins very...

You might also read

Related Articles

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

Sort by

Same author

Task-Preserving EEG Anonymization Using Latent Feature Masking.

IEEE journal of biomedical and health informatics·2026

Same author

Ghost poisoning: Making users invisible to speaker verification models.

JASA express letters·2026

Same author

Temporal patterns in articulation underlying repetitions, prolongations and blocks.

Journal of fluency disorders·2026

Same author

Neural Responses to Affective Sentences Reveal Signatures of Depression.

Translational psychiatry·2026

Same author

Time-resolved EEG decoding reveals altered neural dynamics of affective semantic evaluation in depression and suicidality.

Communications biology·2026

Same author

Neural evidence of disrupted self-referential processing in suicidal depression.

Journal of affective disorders·2026

Search research articles

Related Experiment Video

Updated: Jun 26, 2026

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

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

Published on: September 27, 2024

A NOVEL ALGORITHM FOR UNSUPERVISED PROSODIC LANGUAGE MODEL ADAPTATION.

Sankaranarayanan Ananthakrishnan¹, Shrikanth Narayanan

¹Speech Analysis and Interpretation Laboratory, Department of Electrical Engineering, University of Southern California, Los Angeles, CA 90089.

Proceedings of the ... IEEE International Conference on Acoustics, Speech, and Signal Processing. ICASSP (Conference)

|January 10, 2009

Summary

This study introduces an unsupervised method to improve prosodic language models (PLMs) for speech recognition. The technique enhances model quality and coverage, making prosody analysis more scalable.

More Related Videos

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Related Experiment Videos

Last Updated: Jun 26, 2026

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

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

Published on: September 27, 2024

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

Area of Science:

Computational Linguistics
Speech Processing
Machine Learning

Background:

Symbolic prosody representations aid spoken language applications like speech recognition.
Categorical prosody models face scalability issues due to extensive annotation requirements.

Purpose of the Study:

To present a novel unsupervised adaptation technique for bootstrapping categorical prosodic language models (PLMs).
To improve the quality and coverage of PLMs using a small annotated training set.

Main Methods:

Developed an unsupervised adaptation algorithm for prosodic language models.
Bootstrapped PLMs from a limited annotated dataset.
Evaluated the adapted PLM on a pitch accent detection task using the Boston University Radio News corpus.

Main Results:

The adaptation algorithm significantly enhanced PLM quality and coverage.
Achieved a 13.8% relative improvement in binary pitch accent detection.
Reduced the out-of-vocabulary (OOV) rate by 16.5% absolute.

Conclusions:

Unsupervised adaptation is effective for bootstrapping and improving categorical prosodic language models.
The proposed technique addresses scalability challenges in prosody modeling for speech applications.