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

Search research articles

Related Experiment Videos

Multiple features analysis of intervocalic English plosives

The Journal of the Acoustical Society of America

|February 1, 1981

Summary

This study evaluated acoustic features for automatic English plosive recognition. Burst/formant-onset frequency and voice onset time (VOT) were most important, with other features offering valuable redundancy.

Related Concept Videos

You might also read

Related Articles

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

Sort by

Same author

Exogenous mineralization of hard tissues using photo-absorptive minerals and femto-second lasers; the case of dental enamel.

Acta biomaterialia·2018

Same author

β-pyrophosphate: A potential biomaterial for dental applications.

Materials science & engineering. C, Materials for biological applications·2017

Same author

Single port laparoscopic right colonic resection using a 'vessel-first' approach.

Colorectal disease : the official journal of the Association of Coloproctology of Great Britain and Ireland·2011

Same author

Short-term outcomes of the prone perineal approach for extra-levator abdomino-perineal excision (elAPE).

The surgeon : journal of the Royal Colleges of Surgeons of Edinburgh and Ireland·2011

Same author

Rectus abdominis myocutaneous flaps for perineal reconstruction: modifications to the technique based on a large single-centre experience.

Annals of the Royal College of Surgeons of England·2011

Same author

Local anaesthetic wound infiltration following paediatric appendicectomy: a randomised controlled trial: Time to stop using local anaesthetic wound infiltration following paediatric appendicectomy?

International journal of surgery (London, England)·2011

Area of Science:

Phonetics and Speech Science
Acoustic Phonetics
Speech Recognition Technology

Background:

Automatic speech recognition (ASR) systems require robust methods for identifying speech sounds.
English plosives present challenges due to their complex acoustic properties and variations.

Purpose of the Study:

To evaluate the effectiveness of various acoustic features for automatic recognition of English plosives.
To determine the most salient acoustic features for identifying plosive voicing and place of articulation.
To assess the contribution of both time-domain and frequency-domain features.

Main Methods:

A controlled study analyzed intervocalic English plosives using multi-feature acoustic analysis.
Time-domain and frequency-domain features were measured computationally.
Maximum a posteriori probability was used to evaluate feature contributions to identification of voicing and place of articulation.

Main Results:

Burst/formant-onset frequency and voice onset time (VOT) were identified as the most significant features for plosive identification.
Features such as 'double-burst release' and 'voicing during stop closure' provided important redundancy.
The study analyzed features for identifying voicing mode and place of articulation across multiple talkers.

Conclusions:

Acoustic analysis provides valuable features for automatic stop recognition.
Combining salient features like burst/formant-onset frequency and VOT with redundant features enhances recognition accuracy.
Further research into time-domain features can improve ASR system performance for plosives.

Related Experiment Videos