Measuring Speech Intelligibility with Romanian Synthetic Unpredictable Sentences in Normal Hearing

Abstract

Background/objectives: Understanding speech in background noise is a challenging task for listeners with normal hearing and even more so for individuals with hearing impairments. The primary objective of this study was to develop Romanian speech material in noise to assess speech perception in diverse auditory populations, including individuals with normal hearing and those with various types of hearing loss. The goal was to create a versatile tool that can be used in different configurations and expanded for future studies examining auditory performance across various populations and rehabilitation methods.

Methods: This study outlines the development of Romanian speech material for speech-in-noise testing, initially presented to normal-hearing listeners to establish baseline data. The material consisted of unpredictable sentences, each with a fixed syntactic structure, generated using speech synthesis from all Romanian phonemes. A total of 50 words were selected and organized into 15 lists, each containing 10 sentences, with five words per sentence. Two evaluation methods were applied in two sessions to 20 normal-hearing volunteers. The first method was an adaptive speech-in-noise recognition test designed to assess the speech recognition threshold (SRT) by adjusting the signal-to-noise ratio (SNR) based on individual performance. The intelligibility of the lists was further assessed at the sentence level to evaluate the training effect. The second method was used to obtain normative data for the SRT, defined as the SNR at which a subject correctly recognizes 50% of the speech material, as well as for the slope, which refers to the steepness of the psychometric function derived from threshold recognition scores measured at three fixed SNRs (-10 dB, -7 dB, and -4 dB) during the measurement phase.

Results: The adaptive method showed that the training effect was established after two lists and remained consistent across both sessions. During the measurement phase, the fixed SNR method yielded a mean SRT50 of -7.38 dB with a slope of 11.39%. These results provide reliable and comparable data, supporting the validity of the material for both general population testing and future clinical applications.

Conclusions: This study demonstrates that the newly developed Romanian speech material is effective for evaluating speech recognition abilities in noise. The training phase successfully mitigated initial unfamiliarity with the material, ensuring that the results reflect realistic auditory performance. The obtained SRT and slope values provide valuable normative data for future auditory assessments. Due to its flexible design, the material can be further developed and extended to accommodate various auditory rehabilitation methods and diverse populations in future studies.

Keywords: Romanian speech; sentence in noise; speech recognition threshold; synthetic speech; text-to-speech system.

Figure 1

Diagram of the experiment divided into a training phase and a measurement phase. Numbers 1 to 15 represent the number of lists in random order, not the list titles, except for List 15 in the training phase. In Session 1, the training phase includes Lists 1 to 7, and the measurement phase includes Lists 8 to 15. In Session 2, the training phase includes Lists 8 to 14, and the Measurement Phase includes Lists 1 to 8. These lists were presented in random order.

Figure 2

Phoneme frequency distribution in the Romanian speech material (represented in blue) compared to the reference phoneme frequency distribution for the Romanian language (represented in red). The phonemes are transcribed using International Phonetic Alphabet (IPA) symbols.

Figure 3

Speech recognition scores for all listeners across different word categories at the three signal-to-noise ratios (SNRs) from all measurement lists. The horizontal lines inside the boxes represent the median values, while the lines extending from the boxes indicate the minimum (lower) and maximum (upper) values. The circles represent outliers. The interquartile range (IQR) is represented by the width of the box, which spans from the first quartile (Q1) to the third quartile (Q3).

Figure 4

Individual psychometric functions for each list are in dashed blue lines. The mean psychometric functions with average curve parameters are shown as black line.

Figure 5

SRT50 in dB SNR across 20 listeners for 15 measurement lists. The lines inside the boxes represent the mean, while the lines extending from the boxes indicate the minimum and maximum values. Circles represent outliers, and the interquartile range (IQR) is shown by the width of the box, spanning from the first quartile (Q1) to the third quartile (Q3).

Figure 6

The mean SRTs for training phase (eight lists in each session) using the adaptive procedure. Training was randomized between test lists. The number of the lists represents the order of presentation and not the title of the lists with the exception of List 15, which was presented first in noise in both training sessions.