SpeechCatcher: A universal platform for speech assessment

SpeechCatcher：语音评估的通用平台

• 批准号: 571914-2022
• 负责人: Rose, YvanY
• 金额: $ 1.09万
• 依托单位: Memorial University of Newfoundland
• 依托单位国家: 加拿大
• 项目类别: Idea to Innovation
• 财政年份: 2022
• 资助国家: 加拿大
• 起止时间: 2022-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nserc-crsng.gc.ca/ase-oro/Details-Detailles_eng.asp?id=758097
• 关键词: SpeechCatcher; universal; platform; speech; assessment

Professionals working in the areas of speech therapy typically rely on traditional, form-filling methods to assess language development and speech disorders. There is virtually no modern technology to support their needs. Likewise, academic researchers in speech acquisition and language disorders must scaffold various devices and software programs to conduct their research. Only a few computer-based speech assessments are available, and they are limited to only a few languages (primarily, English); these assessments also mostly consist of digital renditions of form-based assessments, with no support for audio recording, automated measures, or data archival. In sum, there is currently no unifying technological solution to build speech assessments, run these assessments, and analyze the speech productions obtained from these assessments in a systematic or timely fashion. SpeechCatcher is a software program designed to create and run speech assessment tests used by speech therapists, language educators and academic researchers in the areas of speech acquisition and language disorders. Compatible with all mainstream desktop, laptop, and tablet computer platforms, SpeechCatcher will include algorithms for speech data processing and analysis which are readily compatible with the speech systems of all human languages, including the languages and dialects spoken by Indigenous and minority populations worldwide. Using SpeechCatcher, clinicians and academics will be able to quickly access, build or modify fully computerized speech assessments, run these assessments with adult and child participants (or clients) alike, record and process the speech data obtained from them, and extract reports needed to assess performance and/or identify markers of speech disorders. Because our algorithms for speech data processing and analysis are conceived to support the speech properties of all human languages, SpeechCatcher will offer a ready and unifying solution to the global market.

在言语治疗领域工作的专业人员通常依靠传统的表格填写方法来评估语言发展和言语障碍。几乎没有现代技术来支持他们的需求。同样，语言习得和语言障碍方面的学术研究人员必须使用各种设备和软件程序来进行他们的研究。只有几种计算机语音评估可用，而且仅限于几种语言(主要是英语)；这些评估也大多由表格评估的数字版本组成，不支持录音、自动测量或数据存档。总而言之，目前还没有统一的技术解决方案来建立、运行这些评估，并以系统或及时的方式分析从这些评估获得的演讲成果。SpeechCatcher是一个软件程序，旨在创建和运行言语评估测试，供言语治疗师、语言教育者和学术研究人员在言语习得和语言障碍领域使用。SpeechCatcher与所有主流台式电脑、笔记本电脑和平板电脑平台兼容，将包括用于语音数据处理和分析的算法，这些算法可以很容易地与所有人类语言的语音系统兼容，包括世界各地土著和少数民族人口使用的语言和方言。使用SpeechCatcher，临床医生和学者将能够快速访问、建立或修改完全计算机化的言语评估，与成人和儿童参与者(或客户)一起运行这些评估，记录和处理从他们那里获得的语音数据，并提取评估表现和/或识别言语障碍标志所需的报告。由于我们的语音数据处理和分析算法旨在支持所有人类语言的语音特性，SpeechCatcher将为全球市场提供一个现成的统一解决方案。