Newsroom

<figure class="image"><img style="aspect-ratio:860/554;" src="https://deeply-website-backend.s3.ap-northeast-2.amazonaws.com/deeply/2026-05/c1ab6947-89ca-4fbd-8cb7-80b5724a8fdb.jpg" width="860" height="554"></figure>&nbsp;Deeply CEO Suji Lee recently told Maeil Business Newspaper that manufacturing-focused AI could become one of Korea’s strengths in the AI era. Unlike general-purpose AI that excels at conversation like a chatbot, she said there is a need for AI that can actually be applied on manufacturing production lines. Deeply is targeting the manufacturing AI market with its “Listen AI” solution, which analyzes industrial sounds to inspect quality. The area Deeply is focusing on is the inspection process that previously depended on human ears. In manufacturing sites, workers used to judge defects by listening directly to machine sounds or by placing a stethoscope-like tool against the equipment. Deeply is transforming this hearing-based inspection into AI-based data analysis.The key is learning normal data. Because defective data is difficult to collect in sufficient volume, Deeply first trains on large amounts of sound from normal products and then detects abnormal sounds that fall outside the normal range. Lee explained, “We mainly use anomaly detection methods that define the normal range first and then identify anything outside that range as abnormal.”&nbsp;Deeply’s strategy is to build its own AI models. Industrial sound data does not have as many public general-purpose models as speech AI does. In addition, models that perform well in laboratories or quiet environments often lose accuracy in real production settings because of equipment vibration, background noise, and variations from line to line. Lee said, “Open-source models may perform well in limited environments, but accuracy often drops significantly when they are introduced to mass-production lines. We determined that our own model, which can be continuously adapted to each site, was essential.”&nbsp;Based on this field experience, Deeply is also improving a common acoustic foundation model. The company is working to evolve frequently encountered sound types, such as rotating machinery sounds and the “click” sounds generated during fastening and assembly processes, into a shared sound foundation model. As a result, deployment that once took several months on-site can now be introduced within about a week for the basic product version.&nbsp;This year, Deeply has shifted its business focus toward quality inspection and defect detection on manufacturing lines. The company says that after its solution is introduced at one line, it is increasingly expanded to additional lines. Lee said, “Once our accuracy began reaching the high 99% range last year, customers started making repeat purchases and expanding the solution to other lines. It is rewarding to see that we are being recognized in the field as a proven product.”&nbsp;Deeply is also seeing more contact with global manufacturers, not just domestic ones. The company says that manufacturing AI use cases created first in Korea are now being reported up to global headquarters. Lee said, “In the past, the structure was usually that headquarters’ methods were simply passed down to local subsidiaries. Recently, however, Korean manufacturing AI use cases are being reported back up to global headquarters. There is now a growing perception that Korea is strong in manufacturing AI.”&nbsp;Deeply plans to make next year its starting point for overseas expansion. Rather than only following domestic manufacturers when they build overseas plants, the company is now also seeing cases where foreign companies are directly considering contracts. Deeply is therefore discussing agreements with overseas partners in earnest. Lee said, “Deeply wants to become a company that turns unstructured data such as sound into manufacturing competitiveness.”

Deeply’s Listen AI Achieves 99% Accuracy and Targets the Manufacturing AI Market

관리자

<figure class="image"><img src="https://imgnews.pstatic.net/image/008/2026/04/14/0005343685_001_20260414050014798.jpg?type=w860" alt="이수지 디플리 대표 /사진=디플리"></figure>A KAIST electrical engineering graduate who later studied signal processing and a Seoul National University neuroscience master’s researcher who analyzed human brainwave signals found a new field of interest in the noisy sound of factory machinery. Suji Lee, CEO of Deeply, founded the Sound AI startup in 2017 and has been pioneering industrial acoustic AI solutions.&nbsp;Lee said, “Since I saw brainwaves and sound as the same kind of time-series signal, I started my company with the vision of giving meaning to sound.” In the early years, the company worked in areas such as infant sound analysis and healthcare acoustics, but from 2024 it discovered the scalability of its technology in manufacturing equipment sound analysis and began focusing on that field.&nbsp;Deeply’s core solution is Listen AI, which detects subtle defect sounds in the enormous noise of factories. Even in environments reaching 100 decibels, it can identify defect signals at a level of 1.77 decibels. Lee explained, “Beyond simple frequency analysis, the key technology is to leave only the target sound we want and remove the many surrounding noises through denoising technology.” Listen AI can detect defects in under one second without contact and with 99.78% accuracy.&nbsp;Listen AI is transforming quality inspection that previously relied on skilled workers. In some manufacturing sites, workers listened directly to machine sounds and judged whether there were anomalies or irregular noises. But even with sharp human hearing, repeated work in noisy environments inevitably introduces subjectivity and leads to inconsistent yield. Lee said companies that adopted Deeply’s solution are satisfied with its machine-like consistency and objectivity, and are expanding the number of processes where it is applied. It is also helping reduce labor costs and improve processes through more detailed log management.&nbsp;The solution is also highly effective at detecting hidden internal defects through sound. In welding processes, for example, it can detect irregular, abnormal sounds instead of the consistent sound that should normally occur, and identify internal bubble-related defects in real time. When bubbles form, they may appear harmless on the surface but later develop into critical cracks. In this way, the system prevents problems that are difficult to identify through visual inspection alone.&nbsp;Unlike many smart factory solutions that require large-scale infrastructure work, Deeply’s system is easy to deploy on-site. By installing microphone sensors and a deep learning PC for each process, it can be integrated with existing manufacturing execution systems (MES) or PLCs and connected to the factory’s overall monitoring system. Lee said the integration process is structured like an API, allowing site managers to implement it quickly and as a turnkey solution without complex workloads.&nbsp;Deeply is currently supplying its solution in Korea to automakers’ affiliates, semiconductor lines, and large infrastructure companies producing gas and steel. In the global market, the company plans to prioritize expansion into the U.S. and Japan, where automation is high and labor costs are expensive. Interestingly, some Korean subsidiaries of global companies adopted Deeply’s solution first, and then their headquarters later began asking about deployment.&nbsp;When Korean subsidiaries of companies headquartered in the U.S. or France report innovation use cases to their headquarters after adopting Deeply’s solution, the company is pursuing overseas expansion based on inbound customer inquiries rather than separate marketing campaigns. In Japan, which is considered a conservative market, Deeply plans to expand its customer base by presenting long-term technology reviews and demonstrations. Lee said Japanese companies tend to conduct analysis and inspection over long periods of time, and Deeply has been steadily pursuing business discussions for years.&nbsp;Based on more than 50,000 hours of accumulated acoustic data, Deeply is focusing its research capabilities on building a general-purpose sound foundation model. In the future, the company plans to expand its machine-hearing ecosystem beyond manufacturing assembly processes to welding, machining, aerospace, and defense.&nbsp;Lee said that while sound-based sensor technology used to be led by Germany and Japan, Deeply’s strength lies in combining that hardware base with AI algorithms that can actually be used in the field. She added that the company aims to become the world’s best sound AI company in industrial equipment.

An ‘AI Skilled Worker’ That Picks Out Defects by Sound Draws Overseas Interest

메인관리자

<figure class="image"><img style="aspect-ratio:800/448;" src="https://deeply-website-backend.s3.ap-northeast-2.amazonaws.com/deeply/2026-05/d75ab53b-9982-4742-9093-2c76753a9cec.jpg" width="800" height="448"></figure>Enterprise AI adoption is rapidly expanding across manufacturing, logistics, and construction, but cases that go beyond PoC and deliver tangible results remain limited.The reason is that companies often struggle to collect data properly in the field, or AI models that work in laboratory settings fail to reproduce the same accuracy on real production lines. In other words, the gap between “adopting AI” and “achieving results with AI” is widening.To address these practical challenges and discuss the concrete conditions for successful AI transformation in industrial settings, the AI Convergence Business Development Conference (AI TECH 2026) will be held on May 6 at Hall E, 3rd floor, COEX in Seoul.&nbsp;<figure class="image"><img style="aspect-ratio:800/533;" src="https://deeply-website-backend.s3.ap-northeast-2.amazonaws.com/deeply/2026-05/f2c9e1f8-393a-43b6-aa77-aee8f0fa78f8.jpg" width="800" height="533"></figure>&nbsp;This year’s theme, “Make AI Work for Your Business,” highlights how AI can be made to work in real-world operations.The C Track of AI TECH 2026 is themed “Successful AI Convergence Cases by Industry” and will focus on how AI is creating real change in major industrial sectors such as manufacturing, logistics, and construction.The first presentation will be delivered by Lee Min-hye, Head of the AI Division at VB Company, under the title “AI Agent Adoption Cases and Reality: Conditions for Becoming a Corporate Competitiveness Driver.” Drawing on the experience of a first-generation AI and big data company with the largest number of AI PoC cases, she will explain how AI agent technology is evolving beyond LLM chatbots and RAG-based AI into task-complete “Deep Agents,” and will introduce actual deployment cases in public institutions and financial organizations. She is expected to discuss why corporate AX efforts fail, citing issues such as the confusion between using AI and transforming with AI, AI use that remains tacit knowledge, and the lack of systemization, while also presenting practical action plans to spread AI capabilities across the organization.Next, Lee Jae-min, Head of Business at Superb AI, will present on “Real AX Trends and Application Cases Accelerated by Vision AI in Manufacturing, Logistics, and Construction.” Centered on three pillars—standard operating procedure analysis, safety monitoring via video analytics, and defect detection through an MLOps platform—he will explain how machine vision AI is replacing manual worker logs and establishing real-time risk detection systems in manufacturing, with real-world examples. He will also share methods for continuously improving AI performance, including an MLOps feedback loop in which operator feedback is automatically converted into training data.Following that, Choi Hyeong-jun, Team Lead of AI Execution Planning at M. Cube Solution, will present “Evolution of Manufacturing Systems for the Era of Autonomous Manufacturing: Practical Strategies for Defect Detection and Predictive Maintenance.” As the shift from DX to AX accelerates, he will examine the structural limitations of existing MES and FDC systems and propose a closed-loop digital twin implementation strategy combining agentic AI and physical AI. He will also cover specific field cases, such as the integration of LLM and digital twin in a steel manufacturer and the real-world results of an LLM multi-agent system in a secondary battery EMS environment.The final presentation will be delivered by Suji Lee, CEO of Deeply, under the title “Physical AI Implemented with Sound AI: The Final Piece of the Factory Automation Puzzle.” Starting from the recognition that while vision-based quality inspection has largely been automated by machine vision AI, auditory inspection for motors, speakers, and fastening sounds still depends entirely on human labor, she will present cases where the deep learning-based anomaly sound detection solution Listen AI Industrial achieved more than 60% annual labor cost savings per line and 99% inspection accuracy. She is expected to emphasize that machine hearing, following machine vision, is emerging as the next AI transformation area in manufacturing.An AI Tech representative said, “Corporate AI transformation is not simply about adopting a specific technology; the key is which on-site problem it will solve and how the results will be sustained.” The representative added that this C Track will be a concentrated venue of experience from experts who have directly implemented AI in industrial settings and created measurable outcomes.Meanwhile, AI TECH 2026 will be held on May 6 from 10:00 a.m. to 4:50 p.m. at Hall E 1–4 on the 3rd floor of COEX in Seoul. The morning session will feature an opening keynote with KAIST, Microsoft Korea, Code Fantasia, and M Cloud Bridge, while the afternoon will be divided into four tracks: Agentic AI &amp; Business Innovation (Track A), AI Development to Operations (Track B), Successful AI Convergence Cases by Industry (Track C), and Physical AI Implementation Strategies (Track D). Attendees may move freely between sessions and meet experts on topics of interest.AI Tech is a paid event, and early-bird registration as well as a 30% discount for groups of three or more are currently available. Pre-registration can be completed on the Dubiz website.