Biofeedback-Enhanced Treatment for Speech Sound Disorder: Randomized Controlled Trial and Delineation of Sensorimotor Subtypes

言语障碍的生物反馈强化治疗：随机对照试验和感觉运动亚型的描述

• 批准号: 10412492
• 负责人: Tara McAllister
• 金额: $ 26.88万
• 依托单位: NEW YORK UNIVERSITY
• 依托单位国家: 美国
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/10412492
• 关键词: Acoustics; Address; Adolescence; Adult; Affect; Age-Years; Articulation Disorders; Articulators; Artificial Intelligence; Auditory; Award; Biofeedback; Biofeedback Training; Child; Childhood; Clinical; Clinical Research; Communication; Data; Databases; Decision Making; Development; Disease; Emotional; Engineering; Enrollment; Exhibits; Feedback; Foundations; Funding; Impairment; Individual; Individual Differences; Intelligence; Intervention; Lead; Learning; Life; Link; Machine Learning; Measures; Methods; Modeling; Motor; Occupational; Oral; Outcome; Parents; Participant; Perception; Performance; Population; Prediction of Response to Therapy; Preparation; Prevalence; Procedures; Production; Public Health; Publishing; Randomized; Randomized Controlled Trials; Recording of previous events; Research; Research Personnel; Residual state; Sampling; School-Age Population; Sensory; Series; Services; Social isolation; Speech; Speech Sound; Stimulus; Surveys; System; Technology; Testing; Time; Training; Treatment Efficacy; Tweens; Ultrasonography; United States National Institutes of Health; Visual; Work; automated speech recognition; base; bullying; clinical application; comparative efficacy; computerized; diverse data; evidence base; experience; experimental study; improved; insight; interest; neural network; novel; peer; personalized learning; predicting response; predictive modeling; preference; recruit; research clinical testing; responders and non-responders; response; sensory feedback; sharing platform; social engagement; socioeconomics; somatosensory; sound; speech accuracy; speech recognition; tool; tool development; trait; trial comparing; visual information

Project Summary/Abstract Children with speech sound disorder show diminished accuracy and intelligibility in spoken communication and may thus be perceived as less capable or intelligent than peers, with negative consequences for both socio- emotional and socioeconomic outcomes [1]–[3]. While most speech errors resolve by the late school-age years, between 2-5% of speakers exhibit residual speech sound disorder (RSSD) that persists through adoles- cence or even adulthood [4], [5], reflecting about 6 million cases in the US. In a series of experimental studies since 2013, our research team has demonstrated that treatment incorporating technologically-enhanced feed- back can improve speech production in individuals with RSSD who have not responded to previous interven- tion [6]–[10]. The primary objective of the parent award (R01 DC017476, “Biofeedback-Enhanced Treatment for Speech Sound Disorder”) is to conduct the first well-powered randomized controlled trial comparing tradi- tional vs biofeedback intervention for the most common type of RSSD, misarticulation of the English /r/ sound. Treatment of RSSD could also be enhanced through the development of tools incorporating artificial intelligence/machine learning (AI/ML). Applications with automated scoring of speech sounds could in principle be used to augment clinician services and achieve higher-intensity practice for faster progress. However, no computerized treatment to date has demonstrated sufficient accuracy for clinical use with children [11]. Existing systems are limited primarily by the fact that publicly available speech corpora have very little representation of either children or individuals with speech impairments. This data scarcity represents a fundamental issue hin- dering advances in clinical applications of automatic speech recognition (ASR) [12]. The proposed sup- plement will address this barrier by modifying and augmenting PERCEPT (Perceptual Error Rating for the Clin- ical Evaluation of Phonetic Targets), an existing corpus of acoustic recordings of child speech assembled through the parent award and the investigators’ previous NIH-funded research since 2013. AI/ML applications of the augmented database are expected to have a twofold scientific impact. First, we anticipate direct benefits for children with RSSD affecting /r/, whose speech samples make up the majority of the current corpus. We will use our database to train a neural network to classify novel child productions containing /r/ as correct or incor- rect. This classifier could then be incorporated into AI tools to increase the efficacy of intervention for children with RSSD. Second, we anticipate that engineers working on the broader problem of ASR for child or clinical speech will be interested in using PERCEPT for model training, especially after the corpus is augmented with more diverse data, as proposed here. We expect to show that acoustic models generated with PERCEPT can improve the performance of currently available open-access speech recognition systems (e.g., Kaldi [13]) in recognition of novel child speech stimuli. The PERCEPT database will be made publicly available through part- nership with PhonBank, an NIH-funded data-sharing platform for speech research (e.g., [14]–[16]).

项目摘要/摘要 言语障碍的儿童表明，口语交流的准确性和清晰度降低了 因此，可能被认为比同龄人的能力或聪明程度较低，对这两个社会都带来负面影响 情绪和社会经济的结果[1] - [3]。虽然大多数语音错误都在较晚的学龄 多年来，在2-5％的说话者暴露了通过Adoles持续存在的残余语音障碍（RSSD） - Cence甚至成年[4]，[5]，反映了美国约600万例。在一系列实验研究中 自2013年以来，我们的研究团队已经证明，增加技术增强的饲料的治疗 - Back可以改善RSSD患者的语音产生 [6] - [10]。父母奖的主要目标（R01 DC017476，“生物反馈增强治疗 对于言语障碍”）是进行第一个比较传统的驱动良好的随机对照试验 - 最常见类型的RSSD类型的Tional VS Biofefback干预，英语 / r /声音的错误。 通过开发增加人工的工具，也可以增强RSSD的处理 智能/机器学习（AI/ML）。语音自动评分的应用原则上可以 用于增强临床服务并实现更高强度的实践，以更快的进步。但是，不 迄今为止，计算机治疗表现出足够的准确性，可以与儿童临床使用[11]。现存的 系统主要受到公开语音语料库几乎没有代表的事实的限制 儿童或言语障碍的人。这些数据稀缺性代表了一个基本问题 自动语音识别（ASR）临床应用中的进展[12]。提议的sup- 拼写将通过修改和增加感知来解决这一障碍（临床的感知错误评级 语音目标的评估），现有的儿童语音录音的语料库 通过父母奖和调查员以来的NIH资助研究。AI/ML申请 预计增强数据库将产生双重科学影响。首先，我们预计会有直接利益 对于RSSD影响 /R /的儿童，其语音样本占当前语料库的大部分。我们将 使用我们的数据库训练神经网络，将包含 / r /的新型儿童制作分类为正确或incor- 矩形。然后可以将此分类器纳入AI工具中以提高儿童干预效率 与RSSD。其次，我们预计工程师致力于为儿童或临床的更广泛的ASR问题 语音将有兴趣使用感知进行模型培训，尤其是在语料库增强之后 如这里提出的那样，更多的数据。我们希望证明具有感知产生的声学模型可以 改善当前可用的开放访问语音识别系统（例如Kaldi [13]）的性能 认识新的儿童言语刺激。感知数据库将通过部分公开提供 与NIH资助的语音研究数据共享平台（例如[14] - [16]）的伙伴关系。