Ajish K. Abraham’s research while affiliated with All India Institute of Speech and Hearing and other places

What is this page?


This page lists works of an author who doesn't have a ResearchGate profile or hasn't added the works to their profile yet. It is automatically generated from public (personal) data to further our legitimate goal of comprehensive and accurate scientific recordkeeping. If you are this author and want this page removed, please let us know.

Publications (4)


Enhancing Stuttering Detection: A Syllable-Level Stutter Dataset
  • Conference Paper

July 2024

·

15 Reads

·

1 Citation

Vamshiraghusimha Narasinga

·

Hina Fathima

·

·

[...]

·

Anil Vuppala

AI-based automated speech therapy tools for persons with speech sound disorder: a systematic literature review

June 2024

·

147 Reads

·

4 Citations

Speech Language and Hearing

In response to the limited availability of speech therapy services, researchers are developing AI-based automated speech therapy tools for individuals with speech sound disorder (SSD). However, their effectiveness/efficacy compared to conventional speech therapy remains unclear, and no guidelines exist for designing these tools or their required automation levels compared to therapy by speech-language pathologists (SLPs). Moreover, AI applications raise concerns about job displacement, biased algorithms, and privacy issues. This systematic review aims to provide comprehensive insights into AI-based automated speech therapy, focusing on (i) types of SSD addressed; (ii) AI techniques used; (iii) autonomy levels achieved; (iv) delivery modes; and (v) effectiveness/efficacy of these tools. PRISMA guidelines were applied across five databases for studies published between January 2007 and February 2022. Twenty-four studies that met the inclusion and exclusion criteria were included. Results suggest that articulation disorders are the most frequently addressed SSD. Various AI techniques were applied, ranging from traditional automatic speech recognition (ASR) to advanced methods. Most studies proposed fully automated tools, often overlooking the role of other stakeholders. Computer-based and gamified applications were the most common intervention modes. The results suggest the potential of AI-based automated speech therapy tools for individuals with SSD; however, only a few studies have compared their effectiveness/efficacy with conventional speech therapy. Further research is needed to develop speech corpora for under-represented languages, apply a Human-Centered AI approach, conduct usability studies on intervention modes, and perform more rigorous effectiveness studies.


Figure 1. Classification of Speech Sound Disorders
Figure 2. Prisma Systematic Review Process applied to 763 papers
Figure 3. Number of papers according to the year of publication
Figure 4. Number of publication type
Figure 5. Main cluster of co-authorship analysis

+6

AI-Based Automated Speech Therapy Tools for persons with Speech Sound Disorders: A Systematic Literature Review
  • Preprint
  • File available

April 2022

·

213 Reads

This paper presents a systematic literature review of published studies on AI-based automated speech therapy tools for persons with speech sound disorders (SSD). The COVID-19 pandemic has initiated the requirement for automated speech therapy tools for persons with SSD making speech therapy accessible and affordable. However, there are no guidelines for designing such automated tools and their required degree of automation compared to human experts. In this systematic review, we followed the PRISMA framework to address four research questions: 1) what types of SSD do AI-based automated speech therapy tools address, 2) what is the level of autonomy achieved by such tools, 3) what are the different modes of intervention, and 4) how effective are such tools in comparison with human experts. An extensive search was conducted on digital libraries to find research papers relevant to our study from 2007 to 2022. The results show that AI-based automated speech therapy tools for persons with SSD are increasingly gaining attention among researchers. Articulation disorders were the most frequently addressed SSD based on the reviewed papers. Further, our analysis shows that most researchers proposed fully automated tools without considering the role of other stakeholders. Our review indicates that mobile-based and gamified applications were the most frequent mode of intervention. The results further show that only a few studies compared the effectiveness of such tools compared to expert Speech-Language Pathologists (SLP). Our paper presents the state-of- the-art in the field, contributes significant insights based on the research questions, and provides suggestions for future research directions.

Download

AI-Based Automated Speech Therapy Tools for persons with Speech Sound Disorders: A Systematic Literature Review

April 2022

·

921 Reads

This paper presents a systematic literature review of published studies on AI-based automated speech therapy tools for persons with speech sound disorders (SSD). The COVID-19 pandemic has initiated the requirement for automated speech therapy tools for persons with SSD making speech therapy accessible and affordable. However, there are no guidelines for designing such automated tools and their required degree of automation compared to the conventional speech therapy given by Speech Language Pathologists (SLPs). In this systematic review, we followed the PRISMA framework to address four research questions: 1) what types of SSD do AI-based automated speech therapy tools address, 2) what is the level of autonomy achieved by such tools, 3) what are the different modes of intervention, and 4) how effective are such tools in comparison with the conventional mode of speech therapy. An extensive search was conducted on digital libraries to find research papers relevant to our study from 2007 to 2022. The results show that AI-based automated speech therapy tools for persons with SSD are increasingly gaining attention among researchers. Articulation disorders were the most frequently addressed SSD based on the reviewed papers. Further, our analysis shows that most researchers proposed fully automated tools without considering the role of other stakeholders. Our review indicates that mobile-based and gamified applications were the most frequent mode of intervention. The results further show that only a few studies compared the effectiveness of such tools compared to the conventional mode of speech therapy. Our paper presents the state-of-the-art in the field, contributes significant insights based on the research questions, and provides suggestions for future research directions.

Citations (2)


... FluencyBank [10]: An interview-based dataset of 32 individuals (≈ 3.5 hours) with labeling similar to the Sep-28k dataset. Recent additions to stutter datasets include a Mandarin corpus [11], which is twice the size of Sep-28k, and a syllable-level stutter dataset in Kannada [12]. Additionally, LibriStutter [8] is a publicly available, synthetically generated English dataset derived from the LibriSpeech ASR corpus, containing time-aligned transcriptions from 20 hours of audio data (50 individuals: 23 male, 27 female). ...

Reference:

Boli: A dataset for understanding stuttering experience and analyzing stuttered speech
Enhancing Stuttering Detection: A Syllable-Level Stutter Dataset
  • Citing Conference Paper
  • July 2024

... Communication aids, such as augmentative and alternative communication tools created with the help of generative AI to generate speech for non-verbal children [16];  Educational support, such as adaptive learning platforms that can personalize, with the help of generative AI, the interactive educational content for their needs [17];  Emotional support such as virtual companions that can adapt to children's behavior using their emotional state and interact with them in a positive way [18];  Social skills training, such as interactive social scenarios and avatars, where generative AI can help children practice and improve their social skills by simulating social situations [19];  Speech and language therapy, such as interactive language exercises with the help of generative AI. In this way, children with speech difficulties can practice pronunciation and grammar and can improve their vocabulary [20];  Cognitive skill enhancement, such as personalized brain training for children that can stimulate their cognitive abilities [21,22];  Sensory integration activities that can include personalized sensory experiences where generative AI can create virtual environments corresponding to the children's sensory sensitivities [23];  Behavioral therapy support with the help of interactive behavior modification tools developed with generative AI. The result consists in offering a secure and controlled environment for children to practice and strengthen their positive behaviors [24];  Customizable assistive technologies [25] such as adaptable interfaces having generative AI integrated to customize them based on the child's specific needs and capabilities. ...

AI-based automated speech therapy tools for persons with speech sound disorder: a systematic literature review
  • Citing Article
  • June 2024

Speech Language and Hearing