Objectively Quantifying Speech Outcomes of Children with Cleft Palate

客观量化腭裂儿童的言语结果

• 批准号: 9765280
• 负责人: Visar Berisha
• 金额: $ 22.55万
• 依托单位: ARIZONA STATE UNIVERSITY-TEMPE CAMPUS
• 依托单位国家: 美国
• 财政年份: 2018
• 资助国家: 美国
• 起止时间: 2018-08-16 至 2021-12-31
• 项目状态: 已结题
• 来源: https://reporter.nih.gov/project-details/9765280
• 关键词: 7 year old; Acoustics; Age; Algorithms; American; Articulation; Artificial Intelligence; Behavior Therapy; Child; Cleft Palate; Cleft lip with or without cleft palate; Clinic; Clinical; Clinical Research; Communities; Data; Databases; Development; Dimensions; Ear; Ensure; Environment; Evaluation; Exhibits; Four-dimensional; Frequencies; Funding; Gold; Human; Individual; International; Intervention; Judgment; Language; Learning; Maps; Measures; Methods; Modeling; National Institute of Dental and Craniofacial Research; Nose; Operative Surgical Procedures; Outcome; Outcomes Research; Output; Pathologist; Perception; Performance; Population; Positioning Attribute; Production; Protocols documentation; Proxy; Reference Values; Reporting; Research; Sampling; Series; Severities; Signal Transduction; Speech; Speech Acoustics; Speech Disorders; Technology; Time; Training; United States National Institutes of Health; Utah; Validation; Validity and Reliability; Visit; Work; base; cleft lip and palate; clinically relevant; craniofacial; impression; improved outcome; learning algorithm; mobile application; novel; predictive modeling; signal processing; success; tool

Perceptual assessment of hypernasality is considered a critical component when evaluating the speech of children with cleft lip and/or palate (CLP). However, most speech-language pathologists (SLPs) do not receive formal training for perceptual evaluation of speech and, as a result, research shows that the subjective ratings are inherently biased to the perceiver and exhibit considerable variability. In this project, we aim to develop an artificial intelligence (AI) algorithm that automatically evaluates speech along four dimensions deemed to be critically important by the Americleft Speech Outcomes Group (ASOG), namely speech acceptability, articulation, hypernasality, and audible nasal emissions. The AI algorithm in this project is based on an existing database of speech collected as a part of an NIH-funded project to develop reliable speech outcomes by improving the reliability of perceptual ratings by training clinicians (NIDCR DE019-01235, PI: Kathy Chapman). This database contains speech samples from 125 5-7 year olds along with multiple perceptual rating for each speech sample. The clinicians participating in this study were successfully trained using a new protocol from the Americleft Speech Outcomes Group and they exhibit excellent inter-clinician reliability. In SA1 we will develop an AI algorithm that automatically learns the relationship between a comprehensive set of speech acoustics and the average of the ASOG-trained expert ratings for each of the four perceptual dimensions. This approach is based on technology that the PIs have successfully used to evaluate dysarthric speech. Unique to these algorithms is modeling of perceptual judgments of trained experts using tools from statistical signal processing and AI. The output of the algorithms will map to a clinically- relevant scale, rather than to norm-referenced values that may or may not be meaningful. In SA2, we will evaluate the tool on new data by collecting new speech samples using a mobile app at a partner clinic using the same protocol as in the original study. Every collected sample will be further evaluated by ASOG trained clinicians. We will use this data to evaluate the accuracy of the AI model by comparing the model's predictions with the average of ASOG-trained experts. Preliminary results show promise that the proposed approach will yield a successful tool for accurately characterizing perceptual dimensions in the speech of children with CLP. These results indicate that a number of acoustic features that have been developed previously by the PIs accurately capture differences in hypernasality and articulation between the speech of three children with CLP (with varying severity). Furthermore, we show the success of our approach on a different, but related, task: objective evaluation of dysarthric speech. We show that an algorithm that automatically rates hypernasality performs on par with the judgment of human evaluators. The results of the proposed research will form the basis for a subsequent R01 proposal for the development and evaluation of a clinical tool to objectively quantify and track speech production in children with CLP.

在评估说话者的言语时，对鼻音过多的感知评估被认为是一个关键组成部分 患有唇裂和/或腭裂 (CLP) 的儿童。然而，大多数言语病理学家 (SLP) 并没有接受 言语感知评估的正式培训，因此，研究表明主观评分 本质上对感知者有偏见，并且表现出相当大的可变性。在这个项目中，我们的目标是开发一个 人工智能 (AI) 算法可自动沿四个维度评估语音 Americleft 言论成果小组 (ASOG) 认为至关重要，即言论可接受性， 发音、鼻音过多和可闻鼻音。本项目中的AI算法基于现有的 作为 NIH 资助项目的一部分收集的语音数据库，旨在通过以下方式开发可靠的语音结果 通过培训临床医生提高感知评级的可靠性（NIDCR DE019-01235，PI：Kathy Chapman）。 该数据库包含 125 个 5-7 岁儿童的语音样本以及每个样本的多个感知评级 语音样本。参与这项研究的临床医生接受了使用新方案的成功培训 Americleft 语音结果小组，他们表现出出色的临床医生间可靠性。 在 SA1 中，我们将开发一种 AI 算法，自动学习 a 之间的关系 全面的语音声学设置以及经过 ASOG 培训的专家对每个语音的评分的平均值 四个感知维度。该方法基于 PI 已成功使用的技术 评估构音障碍言语。这些算法的独特之处在于对训练有素的专家的感知判断进行建模 使用统计信号处理和人工智能工具。算法的输出将映射到临床上 相关尺度，而不是可能有意义或可能没有意义的规范参考值。在 SA2 中，我们将 通过在合作伙伴诊所使用移动应用程序收集新的语音样本来评估该工具的新数据 与原始研究中相同的方案。每个收集到的样本都将由接受过 ASOG 培训的人员进行进一步评估 临床医生。我们将使用这些数据通过比较模型的预测来评估 AI 模型的准确性 与接受过 ASOG 培训的专家的平均水平相当。初步结果表明所提出的方法有望 产生了一个成功的工具，可以准确描述 CLP 儿童言语中的感知维度。 这些结果表明 PI 之前开发的许多声学特征 准确捕捉三名患有 CLP 的儿童在言语过度和发音方面的差异 （具有不同的严重程度）。此外，我们展示了我们的方法在不同但相关的任务上的成功： 构音障碍言语的客观评估。我们展示了一种自动评估鼻音过多的算法 与人类评估者的判断相当。拟议研究的结果将形成 为随后的 R01 提案奠定基础，以客观地开发和评估临床工具 量化和跟踪 CLP 儿童的言语产生。