低语语音识别：擦音发音部位和嗓音线索的作用

Identification of words in whispered speech: The role of cues to fricatives' place and voicing.

机构信息

Intelligent Systems Associate Laboratory (LASI), Institute of Electronics and Informatics Engineering of Aveiro (IEETA), School of Health Sciences (ESSUA), University of Aveiro, Aveiro, Portugal.

Institut fur Romanische Sprachen und Literaturen, Goethe Universitat, Frankfurt, Germany.

出版信息

JASA Express Lett. 2023 Aug 1;3(8). doi: 10.1121/10.0020302.

DOI:10.1121/10.0020302

PMID:37555774

Abstract

The temporal distribution of acoustic cues in whispered speech was analyzed using the gating paradigm. Fifteen Portuguese participants listened to real disyllabic words produced by four Portuguese speakers. Lexical choices, confidence scores, isolation points (IPs), and recognition points (RPs) were analyzed. Mixed effects models predicted that the first syllable and 70% of the total duration of the second syllable were needed for lexical choices to be above chance level. Fricatives' place, not voicing, had a significant effect on the percentage of correctly identified words. IP and RP values of words with postalveolar voiced and voiceless fricatives were significantly different.

摘要

使用门控范式分析了耳语语音中声学线索的时间分布。15 名葡萄牙参与者听取了四位葡萄牙语说话者说出的真实双音节词。分析了词汇选择、置信得分、隔离点 (IP) 和识别点 (RP)。混合效应模型预测，第一个音节和第二个音节总时长的 70%需要达到词汇选择的机会水平以上。摩擦音的位置而不是浊音对正确识别单词的百分比有显著影响。后齿龈浊音和清音摩擦音的词的 IP 和 RP 值有显著差异。