Mandarin Chinese speech recognition by pediatric cochlear implant users.
Mandarin Chinese speech recognition by pediatric cochlear implant users.
复制标题
儿科人工耳蜗用户的普通话语音识别。
DOI：
10.1016/j.ijporl.2011.03.009
复制
发表时间：
2011-06
影响因子：
1.5
通讯作者：
Chen, Bing
中科院分区：
文献类型：
--
作者：
Zhu, Meimei;Fu, Qian-Jie;Galvin, John J., III;Jiang, Ye;Xu, Jianghong;Xu, Chenmei;Tao, Duoduo;Chen, Bing
由于儿科言语测试存在困难，大多数儿科人工耳蜗 (CI) 言语研究必然涉及基本且简单的感知任务。关于讲普通话的儿科 CI 用户对较难的语音材料（例如，多个讲话者产生的单词和句子）的感知的研究相对较少。困难的言语材料和测试必然需要年龄较大的儿科 CI 用户，他们可能有不同的听力损失病因、耳聋持续时间、CI 经验。本研究通过相对困难的测试材料和方法调查了儿科 CI 患者人口统计数据如何影响语音识别性能。在这项研究中，测量了 37 名讲普通话的儿童 CI 用户对多说话者（两名男性和两名女性）普通话双音节和句子的开放集识别。根据耳聋病因和之前的听觉经验对受试者进行分组。第一组受试者均患有先天性耳聋，几乎没有听觉体验。第 2 组受试者并非先天性耳聋，并且在植入前具有丰富的声学听力经验。使用受试者人口统计数据（例如植入年龄和测试年龄）在每组内进行多元线性回归分析。儿童 CI 表现总体上相当不错。对于第一组，双音节的平均正确率为 82.3%，句子的平均正确率为 82.8%。对于第 2 组，双音节的平均正确率为 76.6%，句子的平均正确率为 84.4%。对于第一组，多元线性回归分析表明，植入年龄预测双音节识别，植入年龄和测试年龄预测句子识别。对于第二组，植入年龄和测试年龄均不能预测双音节或句子识别。女性谈话者的表现明显优于男性谈话者。与之前的研究结果一致，早期植入为重度耳聋儿童提供了显着的优势。对于相对困难的材料和任务，两组的表现通常都相当好，这表明开放式单词和句子识别可能有助于评估老年儿科 CI 用户的言语表现。第 1 组和第 2 组之间双音节识别的差异可能反映了对电刺激的适应差异。第一组受试者仅通过电刺激形成言语模式，而第二组受试者相对于先前的声学模式适应了电刺激。
Because of difficulties associated with pediatric speech testing, most pediatric cochlear implant (CI) speech studies necessarily involve basic and simple perceptual tasks. There are relatively few studies regarding Mandarin-speaking pediatric CI users' perception of more difficult speech materials (e.g., words and sentences produced by multiple talkers). Difficult speech materials and tests necessarily require older pediatric CI users, who may have different etiologies of hearing loss, duration of deafness, CI experience. The present study investigated how pediatric CI patient demographics influence speech recognition performance with relatively difficult test materials and methods. In this study, open-set recognition of multi-talker (two males and two females) Mandarin Chinese disyllables and sentences were measured in 37 Mandarin-speaking pediatric CI users. Subjects were grouped according to etiology of deafness and previous acoustic hearing experience. Group 1 subjects were all congenitally deafened with little-to-no acoustic hearing experience. Group 2 subjects were not congenitally deafened and had substantial acoustic hearing experience prior to implantation. Multiple linear regression analyses were performed within each group using subject demographics such as age at implantation and age at testing. Pediatric CI performance was generally quite good. For Group 1, mean performance was 82.3% correct for disyllables and 82.8% correct for sentences. For Group 2, mean performance was 76.6% correct for disyllables and 84.4% correct for sentences. For Group 1, multiple linear regression analyses showed that age at implantation predicted disyllable recognition, and that age at implantation and age at testing predicted sentence recognition. For Group 2, neither age at implantation nor age at testing predicted disyllable or sentence recognition. Performance was significantly better with the female than with the male talkers. Consistent with previous studies' findings, early implantation provided a significant advantage for profoundly deaf children. Performance for both groups was generally quite good for the relatively difficult materials and tasks, suggesting that open-set word and sentence recognition may be useful in evaluating speech performance with older pediatric CI users. Differences in disyllable recognition between Groups 1 and 2 may reflect differences in adaptation to electric stimulation. The Group 1 subjects developed speech patterns exclusively via electric stimulation, while the Group 2 subjects adapted to electric stimulation relative to previous acoustic patterns.
登录
查看更多内容
影响因子：
3.7
作者：
Sarant, JZ;Blamey, PJ;Gibson, WPR
通讯作者：
Gibson, WPR
影响因子：
1.4
作者：
Oh, SH;Kim, CS;Koo, JW
通讯作者：
Koo, JW
影响因子：
1.7
作者：
Chin, SB;Finnegan, KR;Chung, BA
通讯作者：
Chung, BA
影响因子：
2.1
作者：
O'Neill, C;O'Donoghue, GM;Sach, T
通讯作者：
Sach, T
DOI：
10.1016/j.ijporl.2007.02.008
发表时间：
2007-06-01
影响因子：
1.5
作者：
Han, Demin;Zhou, Ning;Xu, Li
通讯作者：
Xu, Li