CoDAS · 2026
Effect of speech recognition test presentation on cochlear implant user performance.
СтатьяНазвание и аннотация: Перевод в очереди
Обработка статьи · этапы, ошибки и управление
Загрузка состояния…
Ошибки и ограничения
История · было → стало
Состояние обновляется каждые 5 секунд, пока блок открыт. Процент показывается только там, где известен объём работы. Пауза останавливает продолжение этапа; текущий запрос к источнику может завершиться.
Sousa Aline Faria de, Costa Lucas Bevilacqua Alves da, Brito Neto Rubens Vuono de
Аннотация
PURPOSE: To analyze and compare speech recognition performance in cochlear implant (CI) users assessed with a speech recognition test administered through monitored live voice (MLV) and recorded audio, both in quiet and in noise.
METHODS: This cross-sectional study included 48 participants who underwent medical history assessment, audiometry, and speech recognition testing under four conditions: MLV in quiet, recorded audio in quiet, MLV in noise, and recorded audio with noise. Statistical analyses were performed using nonparametric tests, adopting a 95% confidence interval and a significance level of p < 0.05.
RESULTS: The highest performance was observed in the MLV condition in quiet, although this condition also showed greater response variability, suggesting a potential influence of evaluator-related characteristics. Performance in the MLV-in-noise and recorded-audio-in-quiet conditions was comparable, indicating that noise in live speech has an impact similar to changing the presentation mode from live to recorded speech. The lowest performance was observed in the recorded-in-noise condition, indicating that the combined effect of background noise and the absence of acoustic cues inherent to live speech negatively affects auditory performance. Word-based and sentence-based analyses produced similar outcomes.
CONCLUSION: Speech recognition performance in CI users is influenced by both presentation mode and background noise. These findings indicate that noise may be as detrimental as the transition from live to recorded speech, underscoring the importance of standardizing speech recognition test administration.
METHODS: This cross-sectional study included 48 participants who underwent medical history assessment, audiometry, and speech recognition testing under four conditions: MLV in quiet, recorded audio in quiet, MLV in noise, and recorded audio with noise. Statistical analyses were performed using nonparametric tests, adopting a 95% confidence interval and a significance level of p < 0.05.
RESULTS: The highest performance was observed in the MLV condition in quiet, although this condition also showed greater response variability, suggesting a potential influence of evaluator-related characteristics. Performance in the MLV-in-noise and recorded-audio-in-quiet conditions was comparable, indicating that noise in live speech has an impact similar to changing the presentation mode from live to recorded speech. The lowest performance was observed in the recorded-in-noise condition, indicating that the combined effect of background noise and the absence of acoustic cues inherent to live speech negatively affects auditory performance. Word-based and sentence-based analyses produced similar outcomes.
CONCLUSION: Speech recognition performance in CI users is influenced by both presentation mode and background noise. These findings indicate that noise may be as detrimental as the transition from live to recorded speech, underscoring the importance of standardizing speech recognition test administration.