Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy

Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy | Signal Canvas | ScienceToStartup

Page Freshness

Signal Canvas proof surface

Canonical route: /signal-canvas/development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin

stale

Proof freshness: stale
Proof status: unverified
Display score: 7/10
Last proof check: 2026-04-03
Score updated: 2026-04-03
Score fresh until: 2026-05-03
References: 0
Source count: 0
Coverage: 33%

This page is showing the last landed evidence receipt and score bundle because the latest proof data is outside the freshness window.

Agent Handoff

Canonical ID development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin | Route /signal-canvas/development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin

REST example

curl https://sciencetostartup.com/api/v1/agent-handoff/signal-canvas/development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin

MCP example

{
  "tool": "search_signal_canvas",
  "arguments": {
    "mode": "paper",
    "paper_ref": "development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin",
    "query_text": "Summarize Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy"
  }
}

source_context

{
  "surface": "signal_canvas",
  "mode": "paper",
  "query": "Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy",
  "normalized_query": "2604.01705",
  "route": "/signal-canvas/development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin",
  "paper_ref": "development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin",
  "topic_slug": null,
  "benchmark_ref": null,
  "dataset_ref": null
}

Evidence Receipt

Route status: building

Claims: 8

References: Pending verification

Proof: Verification pending

Freshness state: computing

Source paper: Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy

PDF: https://arxiv.org/pdf/2604.01705v1

Source count: Pending verification

Coverage: 33%

Last proof check: 2026-04-03T20:50:40.820Z

Signal Canvas receipt window

Watch and verify: Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy

/buildability/development-and-multi-center-evaluation-of-domain-adapted-speech-recognition-for-human-ai-teaming-in-real-world-gastroin

Watchwatch

Subject: Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy

Verdict

Preparing verified analysis

GitHub Code Pulse

No public code linked for this paper yet.

Claim map

Strong 8Mixed 0Weak 0

Evidencepartial
reducing character error rate (CER) from 20.52% to 14.14%
Implicationpartial
Directly stated in abstract with specific numeric results
Verificationpartial
partial
Evidencepartial
increasing medical term accuracy (Med ACC) from 54.30% to 87.59%
Implicationpartial
Directly stated in abstract with specific numeric results
Verificationpartial
partial
Evidencepartial
CER is reduced from 16.20% to 14.97%
Implicationpartial
Directly stated in abstract with specific numeric results from multi-center study
Verificationpartial
partial
Evidencepartial
Med ACC is improved from 61.63% to 84.16%
Implicationpartial
Directly stated in abstract with specific numeric results from multi-center study
Verificationpartial
partial
Evidencepartial
EndoASR achieves a real-time factor (RTF) of 0.005, significantly faster than Whisper-large-v3 (RTF 0.055)
Implicationpartial
Directly stated in abstract with comparative numeric results
Verificationpartial
partial
Evidencepartial
maintaining a compact model size of 220M parameters, enabling efficient edge deployment
Implicationpartial
Directly stated in abstract with specific parameter count and deployment implication
Verificationpartial
partial
Evidencepartial
integration with large language models demonstrates that improved ASR quality directly enhances downstream structured information extraction and clinician-AI interaction
Implicationpartial
Directly stated in abstract but requires some inference about the causal relationship
Verificationpartial
partial
Evidencepartial
We develop a two-stage adaptation strategy based on synthetic endoscopy reports, targeting domain-specific language modeling and noise robustness
Implicationpartial
Directly stated in abstract describing the method development
Verificationpartial
partial

Author intelligence and commercialization panels stay hidden until the proof receipt is verified, cites at least 3 references, includes at least 2 sources, and clears 50% coverage. The paper narrative and citation surfaces remain public while verification is pending.

Development and multi-center evaluation of domain-adapted speech recognition for human-AI teaming in real-world gastrointestinal endoscopy

Use Signal Canvas as the narrative proof surface

Use this Signal Canvas via API or MCP

Signal Canvas proof surface