Related Experiment Video
Updated: Feb 17, 2026

Foreign Accent and Forensic Speaker Identification in Voice Lineups: The Influence of Acoustic Features Based on Prosody
Published on: September 27, 2024
Predicting Intelligibility Deficit in Dysphonic Speech with Cepstral Peak Prominence
Keiko Ishikawa1, Alessandro de Alarcon2, Sid Khosla3
11 Department of Speech and Hearing Science, University of Illinois at Urbana-Champaign, Champaign, Illinois, USA.
Cepstral peak prominence (CPP) moderately predicts speech intelligibility deficits in individuals with dysphonia. However, CPP alone is insufficient for fully describing these speech challenges.
Area of Science:
- Speech-language pathology
- Acoustic analysis of voice disorders
- Auditory perception
Background:
- Dysphonia, a voice disorder, often impacts speech intelligibility.
- Objective acoustic measures are needed to quantify speech deficits.
- Cepstral peak prominence (CPP) is a potential acoustic correlate of voice quality.
Purpose of the Study:
- To evaluate the efficacy of cepstral peak prominence (CPP) in predicting intelligibility deficits in dysphonic speech.
- To determine the correlation between CPP measures and intelligibility scores in speakers with and without dysphonia.
Main Methods:
- Recording of Hearing-in-Noise Test sentences from 18 dysphonic and 18 normal-voice speakers.
- Presentation of speech samples to 60 normal-hearing adults in quiet and +0 dB SNR noise conditions.
- Measurement of speech intelligibility via orthographic transcription and acoustic analysis of CPP.
Main Results:
- Dysphonic speech exhibited significantly lower intelligibility than normal speech in noise.
- A moderate correlation was found between CPP and intelligibility scores when averaged per speaker.
- CPP showed a limited ability to predict intelligibility deficits.
Conclusions:
- Cepstral peak prominence (CPP) offers a moderate predictive capability for intelligibility deficits in dysphonic speech.
- CPP alone is not a comprehensive measure for characterizing the full extent of intelligibility impairment in dysphonia.
More Related Videos
06:22Machine Learning-Based Cough Tone Classification: Diagnostic Exploration of Chronic Obstructive Pulmonary Disease and Respiratory Tract Infections
Published on: September 19, 2025
05:48Author Spotlight: Investigating the Impact of Emotional Prosodies on Voice Recognition and Perception
Published on: August 9, 2024
Related Concept Videos
¹³C NMR: Distortionless Enhancement by Polarization Transfer (DEPT)
Non-Verbal Cues