Perception AI
Perception AI
Sound Engine DOM, which makes 1,000 yen earphones sound like 50,000 yen equipment, and EarEffect, an app for listening on the device in your hand.
Go to Perception AI
Products — In-House Products
Perception AI is Sound Engine DOM, which makes 1,000 yen earphones sound like 50,000 yen equipment. Professional AI is a multi-agent system that drafts reports in the writer's own style and corrects them by itself.
Two domains
Perception AI
Sound Engine DOM, which makes 1,000 yen earphones sound like 50,000 yen equipment, and EarEffect, an app for listening on the device in your hand.
Go to Perception AIProfessional AI
An AI multi-agent system that drafts reports in the prescribed format and corrects itself by checking against the evidence.
Go to Professional AI
Perception AI
A Perception AI that controls sound quality by rebuilding the audio signal sent to a device in software, changing the tone as much as if the hardware had been replaced. It manages sound quality in software without requiring equipment replacement.
Perception AI
This is the AI that handles human hearing. Sound Engine DOM makes a JPY 1,000 earphone sound like a JPY 50,000 device, and it is delivered simply by building it into a device's firmware or installing it as software.
What it is
A sound engine that rebuilds the audio signal sent to a device in software and changes the tone as much as if the hardware had been replaced. As a next-generation Perception AI that manages sound quality in software without replacing equipment, it runs embedded in broadcast playout systems, streaming infrastructure and apps. The method holds international patents in Japan, the United States, Germany and the United Kingdom.
Case study
We present the flow and the finished form in the form of reports. Each one states clearly whether it is based on our actual operations or is an example assumed from how such work is normally done.
Perception AI: broadcasting
This is our own example. In the broadcasting field, in response to a request to change how audio sounds without replacing equipment, we delivered Sound Engine DOM as a plugin.
ReportReport for this case
What it is
An app that delivers the sound of Sound Engine DOM to general users. It is available in a Windows version and an Android Auto version, and the interface supports multiple languages.
Case study
Perception AI: on the device in hand
Here is an example from our own operations. EarEffect reads the song that is playing and selects the sound for that song from 840 presets. It has accumulated 140,000 downloads worldwide.
ReportReport for this case
Perception AI — Products

Delivery and installation testing
A sound engine that rebuilds the sound of equipment in software, from broadcast and streaming to automotive, aviation, and film.
EarEffectNow available
An app for listening to the sound of DOM on your own device.
Professional AI
This is AI for professionals who produce large-scale reports. A coordinating agent assigns the work, and multiple agents with roles of reading, cross-checking, drafting, and sourcing share the tasks. They read across materials, draft in the prescribed format, and keep the supporting evidence. Final approval is made through review by the professional.
Professional AI
This is a multi-agent system for professionals who produce large-scale reports, such as audit departments of listed companies, audit firms, lawyers, judicial scriveners, tax accountants and researchers. It reads the materials, drafts in the prescribed format, keeps the evidence, and leaves final approval to the professional's review. It succeeded in a PoC in audit, the first field, and has begun full-scale product development. Contract development has also started.
What it is
In the work of writing reports, AI handles reading materials, drafting in the required format, and showing the evidence. A central AI coordinates multiple AIs with different roles, handling volumes of materials and formats that a single AI cannot. Passages written by AI are labeled "AI-drafted proposal," and a professional traces them back to the evidence, verifies them, and finalizes them.
Case study
Professional AI: auditing
This is an example of our products. In an audit in the first field, AI drafted working papers in the prescribed format and professionals reviewed and finalized them, and the PoC succeeded.
ReportReport for this case
Operating scale — from system logs
At the foundation of our products is AI that we run every day in our own businesses.
approx. 100,000cases/day
Checks bid notices published by government agencies and others 4 times every day, with AI judging deadlines, participation conditions, and fit with our company
1,108cases
Bidding projects whose deadlines and progress are managed by AI
4,084items
Orders, inventory, pricing, advertising, and finance on one platform
86functions
In-house system functions that can be run directly from AI assistants
8systems
AI systems we actually run in our own business
Values retrieved from each system's records (as of November 9, 2026). "Thousands of people" is a figure we calculated: we converted this workload into the effort it would take people to process it with the same tasks, and took the number of people needed to finish it within twenty-four hours. It is not a measurement by a third party.
View the workload breakdownProfessional AI
The PoC process, features, and fields of deployment are explained on a dedicated page.
Learn More