Evidano is an AI-powered qualitative data analysis platform that ingests audio captions, interview transcripts, and sensor-derived annotations to produce thematic, frequency, and cross-segment analyses with visualizations and exportable codebooks. AI-enabled qualitative research for assistive tech is how teams turn complex, multimodal field work into action in days rather than months. The Dari project (26-week design process; core outputs published May 8, 2025) combines EMG sign-recognition (Woori), smart-glass captioning (Sari) and a companion app, producing transcripts, signal logs, and co-design interview data that need integrated analysis. Researchers and product teams often struggle to align interview transcripts, sensor logs, and caption streams into themes and user journeys. Read the Core77 project for the public report: Core77.
Key Takeaways
The Dari project shows that aligning transcripts, caption streams, and EMG signal logs produces actionable priorities for assistive communication products. Evidano ingests those multimodal inputs and accelerates thematic, frequency, and cross-segment analysis so teams can move from data to decisions in hours rather than weeks. This post summarizes the Dari findings, the data types you will see, and a 7-step checklist to pilot a Dari-style study.
- Dari combined three components (Woori EMG armband; Sari smart glasses; companion app) during a 26-week design process reported May 8, 2025.
- Key research outputs to align are interview transcripts, time-stamped caption text, and EMG-derived event logs to preserve conversational nuance and measure latency.
- Evidano ingests multimodal corpora, aligns timestamps, runs automated thematic coding, and produces cross-segment reports and exportable codebooks.
Fast take: what the Dari project shows
The Dari project shows that a three-part assistive communication ecosystem surfaces adoption barriers, privacy trade-offs, and UX priorities that require multimodal analysis. Dari is an assistive communication ecosystem that aims to bridge Deaf-hearing conversation with three integrated components: Woori (EMG armband), Sari (smart glasses captioning), and a mobile companion app. The project was developed over a 26-week design process and reported publicly on May 8, 2025, in Core77.
- Problem: fragmented inputs (interviews, EMG signals, caption text) and a need to preserve conversational nuance.
- Opportunity: combine qualitative interviews and multimodal logs to surface adoption barriers, privacy concerns, and UX trade-offs.
- Payoff: actionable priorities (device accuracy, gaze-preserving caption UX, offline interpreter fallbacks).
Findings snapshot
This findings snapshot summarizes the project timeline, core components, primary methods, and design goals identified in the public report.
Findings snapshot table
| Date / Metric | Value | Source | Implication |
|---|---|---|---|
| Project timeline | 26-week design process (started 2024) | Core77 | Iterative co-design with Deaf community |
| Core components | 3 (Woori EMG armband; Sari smart glasses; companion app) | Core77 | Multimodal data types to analyze |
| Primary methods | Interviews, co-design workshops, prototypes | Core77 | Rich qualitative corpus + sensor logs |
| Design goals | Natural two-way communication; reduce dependency; preserve social cues | Core77 | Research should link experience → behavior → adoption |
How Dari works (plain English)
This section explains how Dari works in plain English by describing its three core components and their data outputs. Woori is an EMG armband that captures forearm muscle signals and uses machine learning to infer sign gestures without cameras, reducing environmental constraints and privacy concerns. Sari is smart glasses that display real-time captions in the user's field of view so Deaf users can keep eye contact and see conversational context. The companion app provides device management, personalization, communication history, and settings that stitch wearable outputs with conversation logs.
- Data outputs you will see in a research corpus: interview transcripts, annotated caption text (time-stamped), EMG-derived event logs, usability notes from co-design sessions.
- Analytically relevant problems: aligning timestamps across modalities, coding non-verbal cues, measuring perceived conversational flow versus objective latency.
AI-enabled qualitative research for assistive tech: implications for teams
UX researchers
UX researchers should combine interviews and caption transcripts to track where captions break conversational flow and tag moments with EMG mismatch events to find high-friction gestures. Use frequency and co-occurrence analysis to surface recurring context, for example noisy transit or medical settings.
Product managers
Product managers should prioritize features by cross-tabulating expressed user needs (narrative data) with objective failure rates from EMG translation confidence scores. Set acceptance criteria that include both qualitative sentiment and quantitative latency thresholds.
Policy & accessibility analysts
Policy and accessibility analysts should translate lived-experience quotes with timestamps into evidence for policy briefs, preserving originals and coded themes for auditability. Document privacy trade-offs, EMG versus camera, as part of procurement recommendations.
Do more, faster with Evidano
Ingest multimodal corpora
Evidano ingests interview transcripts, caption SRT files, and EMG event logs into one project and aligns timestamps so researchers can see a single conversation timeline.
Automated thematic + cross-segment analysis
Evidano runs thematic coding across interviews and caption text, produces frequency tables, and compares segments (for example healthcare versus transit) in minutes rather than weeks.
Custom transcription & translation
Evidano provides transcription with a custom dictionary for domain terms and sign labels and translates captions while preserving codeable tokens.
AI chat over your data & visualizations
Evidano supports natural-language questions about themes, pulls supporting quotes with timestamps, and generates stakeholder-ready visuals such as word clouds, co-occurrence networks, and hierarchical code trees.
Security & reproducibility
Evidano stores data encrypted and does not use research data to train third-party models, which helps with sensitive accessibility research and complying with participant consent constraints.
FAQ: AI-enabled qualitative research for assistive tech
What did the Dari project demonstrate about assistive communication systems?
The Dari project demonstrated that a multimodal assistive ecosystem can surface practical adoption barriers, privacy trade-offs, and UX priorities that require integrated analysis. The project combined Woori (EMG armband), Sari (smart glasses captions), and a companion app in a 26-week design process and was reported on May 8, 2025 in Core77.
What types of data does Dari generate and why should teams align them?
Dari generates interview transcripts, time-stamped caption text, EMG-derived event logs, and usability notes, and teams should align them to preserve conversational nuance and measure latency and gesture accuracy. Aligning timestamps lets researchers link lived-experience quotes to objective device events for reproducible evidence.
How can teams analyze Dari-style multimodal data using Evidano?
Teams can import transcripts, caption SRT files, and EMG logs into Evidano, align timestamps, run automated transcription normalization and AI-assisted coding, and then produce cross-segment reports and exportable codebooks in hours. The post includes a 7-step checklist that starts with collecting raw inputs and importing them into Evidano.
What privacy trade-offs did the Dari design highlight?
The Dari design highlighted privacy trade-offs between EMG-based gesture inference and camera-based solutions, reporting that EMG reduces environmental constraints and privacy concerns compared to cameras. Policy recommendations in the report include documenting these trade-offs for procurement and accessibility audits.
How do I run a pilot to reproduce Dari-style insights?
Follow the 7-step checklist in this post: collect interviews, SRT caption files, and EMG logs; import and align them in Evidano; run transcription normalization and AI-assisted coding; validate with participants; and deliver a one-page decision memo. Step-by-step details are in the checklist below.
Checklist: 7-step pilot for Dari-style studies
This checklist gives a seven-step pilot to reproduce Dari-style insights using aligned multimodal data.
Step 1: Collect raw inputs, interviews, SRT caption files from Sari prototypes, EMG logs from Woori (timestamped).
Step 2: Import to Evidano (Evidano) and align timestamps across modalities.
Step 3: Run automated transcription normalization and apply a custom dictionary for sign labels.
Step 4: Apply initial codebook (importable) and run AI-assisted coding to generate preliminary themes.
Step 5: Produce cross-segment reports (location, device confidence, participant persona) and flag high-impact quotes.
Step 6: Validate with 2–3 participant reviewers and update codes; keep versioned exports for audit.
Step 7: Deliver a one-page decision memo with prioritized product changes and metrics (latency reduction, error hotspots, adoption risk).
Wrapping up & next steps
Dari demonstrates how multimodal assistive systems generate research challenges that are solvable with integrated qualitative analysis by aligning transcripts, captions, and sensor logs to preserve conversational nuance while producing evidence product teams can act on. Ready to reproduce this workflow? Try Evidano for free and upload your interview transcripts, caption files, and EMG logs to run thematic, frequency, and cross-segment analyses in hours.