# Live Call Transcription That Drafts a 16-Field Emergency Form While the Operator Listens

> On an emergency medical consultation line, operators had to listen to a worried caller and type a sixteen-field record at the same time. We built a system that transcribes the call live in Japanese, separates the speakers, fills the form as the conversation happens and leaves the operator to review and save it.

- Source: https://synconai.com/case-studies/emergency-consultation-live-form-extraction
- Publisher: SynconAI (https://synconai.com)
- Type: Case study
- Evidence: Delivered client engagement. The client is anonymised; the industry, products and outcomes are theirs.
- Organisation: A Japanese contact centre operator running an emergency medical consultation line for a regional public sector client, where callers ask whether a situation needs an ambulance
- Industry: Healthcare & Life Sciences
- Products: Custom AI, Speech-to-text, Speaker separation, Large language models, AWS, Web application
- Service: Custom AI Development (https://synconai.com/custom-ai-development)
- Reading time: 6 minutes

## In short

We built production AI for an emergency medical consultation line in Japan. It transcribes the call live, separates operator and caller, drafts the sixteen-field consultation form as the conversation happens and produces an end-of-call summary, while the trained operator reviews and saves every record. Regional vocabulary engineering and regression tests protect accuracy on local place names.

## Key points

- On an emergency line, the operator must keep listening. Moving the typing to AI, with review at the end, protects the most important part of the call.
- Speaker separation is not optional. A symptom described by the caller and a question asked by the operator must never be confused in the record.
- Local vocabulary decides whether operators trust the system. Place names need managed vocabularies, careful corrections and regression tests.
- Ship recorded before live. Proving transcription and extraction on recordings first made the live system safer to introduce.

## From live call to approved record

The call audio is captured live. Speech recognition tuned for Japanese produces a running transcript and separates the operator from the caller. An extraction step reads the transcript and fills the sixteen fields of the consultation form as the information is spoken. Regional vocabulary and context-gated corrections fix the place names and local terms general models mishear. At the end of the call, the operator reviews the draft, corrects anything wrong and saves it, and an end-of-call summary is attached. An earlier phase handles recorded audio and text uploads with the same transcription and extraction, exporting to Excel.

### 1. Capture

- Live call audio
- Recorded upload (Phase 1)

Live and recorded calls share one pipeline.

### 2. Transcribe

- Japanese speech recognition
- Speaker separation

Who said what matters on a medical call.

### 3. Correct

- Regional vocabulary
- Context-gated corrections
- Recognition audit

Local names are engineered, not hoped for.

### 4. Extract

- 16-field form
- Structured values

The record is drafted during the call.

### 5. Review

- Operator review
- Corrections
- End-of-call summary
- Saved record

A trained person approves every record.

## The starting position

Emergency medical consultation lines exist for a simple, important reason. Many people who call an ambulance do not need one, and some who need one hesitate to call. A consultation line lets a member of the public describe a situation to a trained operator, who assesses it and advises whether to call an ambulance, go to a hospital or manage at home. It protects ambulances for the people who need them and gives callers expert reassurance.

The contact centre operator in this engagement runs such a line for a regional public sector client in Japan. Each call is recorded in a structured consultation form with sixteen fields, covering who is affected, what is happening, where, since when and what advice was given.

That form was the problem. Operators had to listen carefully to a worried, sometimes panicked caller, ask the right questions, decide on advice and fill in sixteen fields, all at once. Typing competes with listening. Every moment spent finding a field or correcting a typo is a moment taken from the caller, and on a line like this, attention is the most important thing an operator has.

The operator wanted to move the typing to AI without moving any of the judgment.

## What we built

### 01 Phase 1: recorded calls and text

The first production system works on recorded audio and text. A recording or transcript is uploaded, transcribed in Japanese, and structured information is extracted and exported to Excel for the client's reporting. This phase proved that transcription and extraction worked on real consultation calls before anything ran live.

### 02 Phase 2: live call capture

The second production system works during the call. It captures the audio live and produces a running Japanese transcript as the conversation happens.

### 03 Speaker separation

The system separates the operator's voice from the caller's. On a medical call this is essential: a symptom the caller describes and a question the operator asks must never be confused when the record is drafted.

### 04 The sixteen-field form, drafted during the call

An extraction step reads the transcript and fills the sixteen fields of the consultation form as the information is spoken. By the time the caller has described the situation, much of the form is already drafted.

### 05 Operator review and end-of-call summaries

At the end of the call, the operator reviews the drafted form, corrects anything the AI got wrong and saves it. The system also writes an end-of-call summary. The operator remains responsible for every record.

### 06 Regional vocabulary engineering

After deployment, the biggest remaining source of errors was local vocabulary: place names, landmarks and regional terms that general speech models mishear. We added an administrator-managed vocabulary for each region, deterministic corrections that apply only when the surrounding context makes them safe, an audit of recognition results, and automated regression tests so that fixing one term cannot quietly break another. The latest of these enhancements has been verified in our environment and is being validated on the client's servers before it is treated as live.

## A call, step by step

A caller explains that an elderly relative has had a fall and is now confused. As they speak, the transcript appears for the operator, with the caller's words and the operator's questions clearly separated. The draft form begins to fill: the person affected, their age, what happened, when, the symptoms described and where they are.

The caller mentions a district name and a nearby landmark. The regional vocabulary makes sure both are recognized correctly, because a wrong location on an emergency record is unacceptable. The operator asks follow-up questions, gives advice and stays focused on the caller throughout.

When the call ends, the operator checks the draft. One field needs a small correction. They fix it, save the record and move on, with a summary attached. The structured record is complete, accurate and approved by the person who took the call.

## Why human review is the design, not a safeguard

It would be technically possible to save AI-drafted forms automatically. On an emergency medical line, it would be the wrong choice. Speech recognition will occasionally mishear, extraction will occasionally misplace a detail, and an incorrect emergency record can have serious consequences.

So the system is designed around the operator's review. The AI's job is to draft fast and accurately enough that reviewing is quicker than typing. The operator's job is to make sure the record is right. That division keeps the benefits of AI, an operator who can listen instead of type, while keeping accountability where it belongs.

## Why local vocabulary deserves engineering

General speech models are trained on broad data. They handle common words well and struggle with the specific: district names, small landmarks, local abbreviations and terms that rarely appear outside one region. On a consultation line, those are exactly the words that matter most, because they describe where help may be needed.

Treating vocabulary as an engineering problem made the difference. Managed vocabularies let administrators add terms without code changes. Context-gated corrections apply a fix only when the surrounding words confirm it is appropriate, avoiding new errors. The recognition audit shows which terms still cause trouble. Regression tests run whenever rules change, so accuracy only moves in one direction.

## Introducing AI to operators who did not ask for it

Operators on an emergency line are experienced professionals with a well-practised routine. A new system that changes the screen in front of them during a call has to earn its place, and the design took that seriously.

The live system shows the operator a transcript and a draft form, but it never interrupts or prompts them, and nothing is saved without their action. If the draft is wrong, correcting it takes less time than typing it from scratch would have. If the AI misses something, the operator's own notes and judgment still decide the record.

Introducing the recorded-call phase first helped as well. Operators and supervisors saw the transcription and extraction working on real calls before it appeared during their own live conversations, which made the live system familiar instead of surprising.

## How we delivered it, end to end

**Recorded before live.** Phase 1 established quality on recordings before Phase 2 touched live calls.

**Review built in.** Operator review of every record was part of the specification from the start.

**Speaker separation as a requirement.** The system was designed to keep operator and caller apart in the transcript and the extraction.

**Quality engineering after go-live.** Real recognition errors seen in production drove the vocabulary, correction and testing work.

**Honest release status.** Enhancements are verified in our environment and validated on the client's servers before they are called live.

## The decisions that mattered

**Assist the operator, never replace them.** This is what made AI acceptable on an emergency line.

**Phase the risk.** Recorded calls first, live calls second.

**Engineer the vocabulary.** Managed vocabularies, context-gated corrections and regression tests turned recurring errors into solved problems.

## What changed

| Area | Before | After |
| --- | --- | --- |
| Operator attention | Split between listening and typing | Focused on the caller |
| Consultation form | Typed during or after the call | 16 fields drafted live, reviewed by the operator |
| Who said what | Reconstructed from memory | Operator and caller separated in the transcript |
| Call summaries | Written by hand | End-of-call summaries attached |
| Recorded calls | Transcribed manually | Transcription, extraction and Excel export |
| Local place names | Frequently misheard | Managed regional vocabulary with regression tests |

## What we would tell a public service team considering this

Start with the operator's attention and protect it. Let AI take the typing, keep a trained person approving every record, and introduce the system on recordings before live calls. Then invest in the details that general AI gets wrong in your region, because on an emergency line those details are the ones that matter.

## Questions

### Does the AI decide whether someone needs an ambulance?

No. The trained operator assesses the caller and gives the advice. The system only transcribes the call, drafts the form and writes a summary, and the operator reviews and approves the record before it is saved.

### How is accuracy on place names handled?

Through recognition engineering: an administrator-managed vocabulary for each region, deterministic corrections that apply only when the surrounding context makes them safe, an audit of recognition results, and automated regression tests. The latest enhancement has been verified in our environment and is being validated on the client’s servers before it is treated as live.

### What came before the live system?

A first production phase that takes recorded audio or text, transcribes it in Japanese, extracts structured information and exports it to Excel. It proved the transcription and extraction on real calls before anything ran live.

---

SynconAI. https://synconai.com/case-studies/emergency-consultation-live-form-extraction