ABCD: A Simulation Method for Accelerating Conversational Agents With Applications in Aphasia Therapy.

Purpose: Development of aphasia therapies is limited by clinician shortages, patient recruitment challenges, and funding constraints. To address these barriers, we introduce Agent-Based Conversational Dialogue (ABCD), a novel method for simulating goal-driven natural spoken dialogues between two con...

Descripción completa

Detalles Bibliográficos
Publicado en:Journal of Speech, Language & Hearing Research Vol. 68; no. 7; pp. 3322 - 3337
Autores principales: Imaezue, Gerald C., Marampelly, Harikrishna
Formato: Artículo
Publicado: American Speech-Language-Hearing Association Jul2025
Materias:
Acceso en línea:Ver este registro en EBSCOhost
fields @attributes:
  recordID: 1
pdfLink:
plink: https://search.ebscohost.com/login.aspx?direct=true&db=ssf&AN=186522589&site=ehost-live
header:
  @attributes:
    shortDbName: ssf
    uiTerm: 186522589
    longDbName: Social Sciences Full Text (H.W. Wilson)
    uiTag: AN
  controlInfo:
    bkinfo:
    jinfo:
      jid:
        10924388
        1SM
      jtl: Journal of Speech, Language & Hearing Research
      issn: 10924388
      maglogo: N
    pubinfo:
      dt: Jul2025
      vid: 68
      iid: 7
      pid: 42
      pub: American Speech-Language-Hearing Association
    artinfo:
      ui:
        186522589
        10.1044/2025_JSLHR-25-00003
      ppf: 3322
      ppct: 15
      formats:
        fmt:
          @attributes:
            type: P
            size: 978KB
      tig:
        atl: ABCD: A Simulation Method for Accelerating Conversational Agents With Applications in Aphasia Therapy.
      aug:
        au:
          Imaezue, Gerald C.
          Marampelly, Harikrishna
        affil:
          Department of Communication Sciences and Disorders, University of South Florida, Tampa
          Department of Computer Science and Engineering, University of South Florida, Tampa
      su:
        Computer simulation
        Comparative grammar
        Language & languages
        Speech
        Cost effectiveness
        Conversation
        Artificial intelligence
        Communication
        Semantics
        Scale analysis (Psychology)
        Data analysis
        Aphasia
        Natural language processing
        Descriptive statistics
        Content mining
        Statistics
        Data analysis software
        Speech therapy
        Chatbots
      sug:
        subj:
          Computer simulation
          Comparative grammar
          Language & languages
          Speech
          Cost effectiveness
          Conversation
          Artificial intelligence
          Communication
          Semantics
          Scale analysis (Psychology)
          Data analysis
          Aphasia
          Natural language processing
          Descriptive statistics
          Content mining
          Statistics
          Data analysis software
          Speech therapy
          Chatbots
      ab: Purpose: Development of aphasia therapies is limited by clinician shortages, patient recruitment challenges, and funding constraints. To address these barriers, we introduce Agent-Based Conversational Dialogue (ABCD), a novel method for simulating goal-driven natural spoken dialogues between two conversational artificial intelligence (AI) agents--AI clinician (Re-Agent) and AI patient (AI-Aphasic), which vocally mimics aphasic errors. Using ABCD, we simulated response elaboration training between both agents with stimuli varying in semantic constraint (high via pictures, low via topics). Rather than resource-intensive finetuning, we leveraged prompt engineering, chain-of-thought (CoT) and zero-shot techniques for rapid, cost-effective agent development, and piloting. Method: Built on OpenAI's GPT-4o as the foundational large language model, Re-Agent and AI-Aphasic were supplemented with external speech-to-text and naturalistic text-to-speech application programming interfaces to create a multiturn, dynamic dialogue system in English. We used it to evaluate Re-Agent's conversational performance across four experimental conditions (CoT + picture, CoT + topic, zero-shot + picture, zero-shot + topic) and aphasic error at two levels: word and discourse errors. Re-Agent's performance was measured using three discourse metrics: global coherence, local coherence, and grammaticality of utterances. Results: Overall, Re-Agent performed accurately in all the discourse metrics across all levels of semantic parameter, prompting technique and aphasic error. The results also indicated that well-crafted zero-shot prompts induce more direct and logically related responses that are robust to adversarial aphasic speech inputs, whereas CoT might lead to responses that slightly lose local coherence due to additional complex reasoning chains. Conclusions: ABCD represents a foundational computational approach to accelerate the innovation and preclinical testing of conversational AI partners for speechlanguage therapy. ABCD circumvents the barriers of collecting diverse errorful speech samples for clinical conversational AI fine-tuning. As AI systems--including large language models and speech technologies--advance rapidly, ABCD will scale accordingly, further enhancing its potential for clinical integration.
      pubtype: Academic Journal
      doctype: Article
      src: R
    language: English
    refInfo:
    copyright:
      @attributes:
        flag: N
    holdings:
      @attributes:
        islocal: N