Related Experiment Video
Updated: Jan 11, 2026
06:04
Systematic Hearing Performance Evaluation Process for Adolescents with Cochlear Implantation at Early Ages
Published on: March 24, 2023
739
Testing Sentence-in-Noise Recognition With Synthetic Speech and Automatic Speech Recognition
Lauren Calandruccio1, Dani Weidman2, Aja Leatherwood1
1Department of Psychological Sciences, Case Western Reserve University, Cleveland, OH.
Journal of Speech, Language, and Hearing Research : JSLHR
|November 10, 2025
Summary
This study explored using artificial intelligence for speech-in-noise recognition tests. Results suggest synthetic speech and machine scoring show promise for audiology research, with high agreement between human and machine evaluations.
Area of Science:
- Audiology
- Speech Science
- Artificial Intelligence
Background:
- Speech-in-noise recognition is crucial for audiology and hearing research.
- Current methods use human recordings and testers, which are time-consuming.
- AI offers potential for automating stimulus generation and scoring.
Purpose of the Study:
- To evaluate masked-sentence recognition using synthetic and human speech.
- To compare human and machine scoring methods for speech-in-noise tasks.
- To assess the feasibility of AI in audiology assessments.
Main Methods:
- Young adults with normal hearing completed a speech-in-noise task.
- Open-set sentences were presented at a -6 dB signal-to-noise ratio.
- Both human and automatic speech recognition (ASR) scored listener performance.
Main Results:
- Speech intelligibility varied across human and synthetic talkers.
- Individual differences in recognition were similar for both speech types.
- Human and ASR scoring showed high agreement (~98%).
Conclusions:
- Synthetic speech may offer greater intelligibility consistency.
- Human scoring was more accurate for open-set sentences, but ASR showed close agreement.
- AI tools show potential for automating speech-in-noise recognition evaluation.
Related Concept Videos
01:28Automatic Processing and Automatic Social Behavior
204
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
204
01:00Detection of Gross Error: The Q Test
6.8K
When one or more data points appear far from the rest of the data, there is a need to determine whether they are outliers and whether they should be eliminated from the data set to ensure an accurate representation of the measured value. In many cases, outliers arise from gross errors (or human errors) and do not accurately reflect the underlying phenomenon. In some cases, however, these apparent outliers reflect true phenomenological differences. In these cases, we can use statistical methods...
6.8K