自动语音识别用于对患有脱节症的儿童的可理解性评估
Jiyoung Choi1, Gemma Moya-Galé1, KyungHae Hwang2
1Department of Biobehavioral Sciences, Teachers College, Columbia University, New York, NY.
Journal of speech, language, and hearing research : JSLHR
|February 26, 2026
概括
自动语音识别 (ASR) 显示出对患有脱节症的儿童语音可理解性评估的前景. WhisperX-medium最接近人类转录的准确性,而谷歌云ASR与感知等级保持一致.
科学领域:
- 语音语言病理学 语言病理学
- 计算语言学计算语言学
- 辅助技术是指辅助技术的使用.
背景情况:
- 准确的语音可理解性评估对于患有脑相关性失联症的儿童至关重要.
- 传统的方法,如人类转录和感知等级是耗时和主观的.
- 自动语音识别 (ASR) 提供了一个潜在的客观和高效的替代方案.
研究的目的:
- 评估ASR系统的有效性,以评估患有脱节症的儿童的语音可理解性.
- 确定与人类听众判断相关的最佳ASR系统.
- 探索ASR作为这一群体的临床工具的潜力.
主要方法:
- 五个ASR系统转录了20名患有脱节症的儿童的语音样本.
- 168名成年听众提供了拼写转录和易于理解 (EoU) 评分.
- 单词识别率 (WRR) 计算了ASR和人类转录;斯皮尔曼相关性评估了关系.
主要成果:
- 四个ASR系统 (WhisperX-small, -medium, -large和谷歌云) 与人类WRR显示出强烈的相关性,其中WhisperX-medium是最高的.
- 这四个系统还与人类的EoU评级显示了中度至强度的相关性,以谷歌云ASR为首.
- Wav2Vec2与人类的WRR和EoU等级的相关性很弱.
结论:
- ASR对患有脱节症的儿童的语音可理解性评估具有重大前景.
- 建议使用WhisperX-medium来接近人类的转录精度.
- 建议谷歌云ASR与感知易于理解的评级保持一致.
- 仔细选择ASR系统对于有效的临床应用至关重要.
相关概念视频
02:07Blind Procedures
Ideally, the people who observe and record the children’s behavior are unaware of who was assigned to the experimental or control group, in order to control for experimenter bias. Experimenter bias refers to the possibility that a researcher’s expectations might skew the results of the study. Remember, conducting an experiment requires a lot of planning, and the people involved in the research project have a vested interest in supporting their hypotheses. If the observers knew which child was...
01:25Learning Disabilities
Learning disabilities are cognitive disorders caused by neurological impairments that affect cognitive functions like language and reading, without indicating overall intellectual or developmental challenges. These disabilities differ from global intellectual or developmental disabilities as they are limited to distinct cognitive functions. Common learning disabilities include dysgraphia, dyslexia, and dyscalculia, each of which impacts unique aspects of learning.
Dyslexia
Dyslexia is a...
Dyslexia
Dyslexia is a...