{
  "schema": "vedokrok.public-item.v1",
  "release_id": "MHC-RPUB-20261011-9e4b62c5",
  "url": "/knowledge/do-not-ask-asr-to-train-every-part-of-speech",
  "id": "MHC-D-RESEARCH-9194",
  "version": "0.2.0",
  "title": "Do not ask ASR to train every part of speech",
  "summary": "Match the tool to the feature it can actually help you change.",
  "kind": "principle",
  "body": "ASR evidence is stronger for segmental pronunciation than for suprasegmental features such as rhythm and stress. Use recognition-based practice where it gives a clear, repeatable signal on words or sounds. For phrasing, stress, timing and broader comprehensibility, add a method that exposes those features directly: shadowing, recording against a model, or listener feedback. Keep ASR in the loop, but do not let one automated score become the whole speaking curriculum.",
  "limits": [
    "The underlying meta-analysis covers systems studied through 2021. Modern tools may handle prosody better, so use current product evidence when it exists rather than treating the older subgroup result as a permanent technical limit."
  ],
  "topics": [
    "union-language-asr-pronunciation-feedback"
  ],
  "intents": [],
  "evidence": [
    {
      "claim": "A meta-analysis of 15 ASR pronunciation studies reported a medium overall effect (Hedges' g = 0.69) compared with non-ASR conditions, with substantial heterogeneity across studies.",
      "role": "supports",
      "note": "The synthesis covered ESL/EFL pronunciation studies published through 2021 and does not establish that every ASR system or feedback design is effective.",
      "locator": "Abstract; Results 4.1",
      "source_id": "RS-3A03409139B602294FD0"
    },
    {
      "claim": "The ASR meta-analysis reported larger pooled effects for segmental pronunciation than for suprasegmental pronunciation, and short interventions of one to four weeks showed little differential effect compared with non-ASR conditions.",
      "role": "supports",
      "note": "These subgroup results reflect the ASR systems and study designs available through 2021; newer systems may differ, especially for prosody.",
      "locator": "Results 4.1; target measure and treatment-duration moderators",
      "source_id": "RS-3A03409139B602294FD0"
    }
  ],
  "use_when": [
    "A learner is using speech recognition as the main tool for pronunciation, rhythm, stress and fluency at the same time."
  ],
  "avoid_when": [
    "The underlying meta-analysis covers systems studied through 2021. Modern tools may handle prosody better, so use current product evidence when it exists rather than treating the older subgroup result as a permanent technical limit."
  ],
  "example": "A learner may use ASR to repair a recurring final consonant, then use a recorded project update to check stress and phrasing that the recognizer does not diagnose well.",
  "check": "Each speaking target has a matching measure, and improvement survives in a changed utterance or spontaneous task.",
  "source_ids": [
    "RS-3A03409139B602294FD0"
  ],
  "published_at": "2026-10-01T14:27:00Z",
  "checklist": [
    "When: A recurring consonant or vowel error causes recognition failures\nThen: Use short ASR-supported correction cycles and explicit feedback.",
    "When: The problem is rhythm, stress, pausing or intonation\nThen: Add model comparison, shadowing or listener feedback and test spontaneous speech.",
    "When: A few short sessions feel better but transfer is unclear\nThen: Continue only with a repeated measure on changed utterances rather than trusting immediate scores."
  ],
  "editorial_overlay": null,
  "editorial": null,
  "notices": [],
  "sources": [
    {
      "id": "RS-3A03409139B602294FD0",
      "title": "The effectiveness of automatic speech recognition in ESL/EFL pronunciation: A meta-analysis",
      "url": "https://doi.org/10.1017/S0958344023000113"
    }
  ],
  "relations": [
    {
      "from": "MHC-D-RESEARCH-9194",
      "to": "MHC-D-RESEARCH-1137",
      "type": "useful_with",
      "url": "/knowledge/shadow-for-prosody-then-test-spontaneous-transfer"
    }
  ],
  "collections": [
    {
      "id": "RC-5FA9095B7B870961852E",
      "title": "Use speech recognition as targeted pronunciation feedback",
      "url": "/collections/use-speech-recognition-as-targeted-pronunciation-feedback"
    }
  ],
  "topic_hubs": [],
  "solution_packs": []
}