# Deeply's Industrial Acoustic AI Solution Solves Connector Engagement Defects in Auto Assembly Lines, Expanding Application in Global Production Lines - Link: https://www.thailand-business-news.com/pr-news/deeplys-industrial-acoustic-ai-solution-solves-connector-engagement-defects-in-auto-assembly-lines-expanding-application-in-global-production-lines - Published: 2026-06-11T20:00:00+07:00 - Author: PR Newswire ◦ Deeply’s ‘Listen AI Industrial’ has already proven to have 99.87% accuracy in global automaker (Company H) production lines in Korea and Mexico. ◦ Foundation model trained on 2.1 million hours of factory noise perfectly identifies subtle ‘engagement sounds’ from the first day of deployment. ◦ Distinguishes 1st and 2nd locking sounds even amidst air gun and metal friction noises, driving North American OEM adoption ◦ Live demo and consultation of connector engagement diagnostic solution at Automate 2026 in Chicago, June 22-25. SEOUL, South Korea, June 11, 2026 /PRNewswire/ — [Deeply Inc.](https://deeplyinc.com/), the developer and operator of the industrial acoustic AI solution ‘Listen AI’, announced on the 11th that it has achieved 99.87% accuracy in connector engagement sound inspection— a chronic issue in global automaker production lines — and has proven the field applicability and reliability of its acoustic AI-based quality inspection technology. Building on this achievement, Deeply plans to actively target the North American automaker and parts manufacturing market by participating in ‘Automate 2026’, North America’s largest robotics and automation exhibition held in Chicago from June 22 to 25. [⌊Deeply's industrial acoustic AI solution, Listen AI, achieves 99.87% accuracy in connector engagement inspection⌉](https://mmx.prnasia.com/media/MS1862070/392855e5a7624d20b1ed5f543e6b5469.jpg?id=OA2697638&p=medium600) Deeply’s industrial acoustic AI solution, Listen AI, achieves 99.87% accuracy in connector engagement inspection As global automakers rapidly transition to Software-Defined Vehicles (SDVs) and electrification systems, the density of electronic components related to in-vehicle infotainment, ADAS, and high-voltage batteries is increasing sharply. Along with this, verifying whether countless invisible wire connectors are perfectly engaged during the assembly process has emerged as a core task for manufacturing quality. In traditional auto assembly lines, workers have relied solely on their ears or the sensation in their fingertips to judge the subtle ‘click’ sound (engagement sound) when inserting connectors. However, this inevitably leads to subjective inspection results depending on the worker’s fatigue level. Furthermore, because inspection histories are not recorded as data, it has been pointed out as a potential risk for future recalls or warranty costs. Deeply is receiving strong interest from global automakers by showcasing inspection quality more accurate than the human ear through its industrial acoustic AI solution,‘ Listen AI Industrial’. **Proven ‘99.87% Accuracy’ in Actual Conglomerate Production Lines Beyond the Pilot Stage** Deeply’s Listen AI solution has already moved past the pilot stage and is ready for immediate deployment in various manufacturing lines. It has been successfully introduced and is operating in the mass production lines of Company H, a global automaker, in its Korea and Mexico plants, where it achieved a connector engagement inspection accuracy of 99.87%, meeting the strict inspection standards of a large conglomerate. The Listen AI solution delivers significantly higher inspection accuracy compared to the traditional method where humans manually judge engagement accuracy by listening to the connector sound. It clearly detects subtle connector engagement sounds even in the harsh noise of manufacturing environments. Accordingly, beyond Company H, successful PoCs (Proof of Concept) have been completed in core processes such as battery assembly lines, electric motor defect inspections, and robotic automated assembly lines of multiple global companies, and the transition to Production Deployment is underway. **Captures Subtle ‘Engagement Sounds’ Amidst Air Gun and Metal Friction Noises… Identifies up to 1st and 2nd Locks via Frequency** The interior of an auto manufacturing plant typically generates extreme noise of over 85dB due to impact wrenches, air guns, metal friction, and conveyor belts. Because of this, it has been nearly impossible to isolate the subtle engagement sounds of target processes using standard microphones or acoustic equipment. Over 8 years of specializing exclusively in manufacturing acoustic data, Deeply has built a proprietary Foundation Model based on over 10 million process event data points and a real-world factory noise database exceeding 2.1 million hours. Through this, a noise-canceling algorithm that precisely removes complex background factory noise is applied, accurately capturing subtle ‘half-clicks’ or soft-connections that are inaudible to the human ear. In addition, through its unrivaled Frequency-band Analysis technology, Listen AI clearly distinguishes the waveform differences between the Primary Lock (3-16 kHz) occurring before the connector is completely locked, and the Secondary Lock (7-16 kHz) which is the final connection. This fundamentally prevents the possibility of intermittent electrical signal errors or malfunctions of safety-critical components like airbags after the vehicle is shipped due to incomplete engagement. Thus, it is being evaluated as practically resolving the connector engagement defect issue, which had remained a long-unsolved challenge in the auto industry. **No Need for Weeks of Data Collection, AI Operates Instantly from Day One** Traditional machine learning solutions required weeks to months of downtime or waiting periods to collect and train on massive amounts of defect data after installing equipment on-site. In contrast, Deeply’s Listen AI is equipped with a pre-trained manufacturing-specific foundation model, allowing it to accurately detect engagement sounds right from the first day (Day 1) the hardware is installed. The fact that there is no need to change existing manufacturing line equipment, tools, or layouts at all is another reason global OEMs choose Deeply. It supports over 20 industrial sensor variations, including fixed directional microphones, wristband microphones worn by workers, and array microphones for high-noise areas, allowing it to operate flexibly even on dynamic lines where worker movement paths change. The detected results (OK/NG) are linked in real-time with the factory’s existing MES (Manufacturing Execution System) or PLC systems, capitalizing them as traceable data. "Connector engagement sound detection was previously considered an area where full automation was impossible, but it is being demonstrated in global production lines that acoustic AI solutions can solve this," said Deeply CEO Suji Lee. "As we are receiving collaboration inquiries from multiple global automakers and parts manufacturers, including those in North America, we will use Automate 2026 as an opportunity to fully enter the North American market, which has complex manufacturing environments, and lead the AI transformation of manufacturing sites." **Meet Deeply at Automate 2026** Deeply’s exhibition booth will be set up in [North Hall #33046](https://www.automateshow.com/exhibitors/deeply-inc). The North American market has a higher demand for factory automation than any other region due to high labor costs and complex manufacturing environments. Deeply plans to showcase a live demo of Listen AI’s connector engagement sound diagnostic solution at this exhibition and kick off collaborations with North American auto OEMs and Tier-1 parts manufacturers. Visitors to the Deeply booth at Automate 2026, which runs for four days starting June 22, can experience the live demo and identify implementation plans tailored to their own environments. **About [Deeply Inc.](https://deeplyinc.com/)** Acoustic AI solution company ‘Deeply’ showcases "Machine Hearing" technology that manages safety in industrial sites and daily life through its independently developed non-verbal AI sound analysis technology. By using AI technology to detect sounds that are difficult to identify with human eyes or ears, its application is gradually expanding in public and industrial safety management fields. ‘Listen AI Industrial’, an industrial AI sound analysis solution developed by Deeply, is a solution that automates product quality inspections that have previously relied on human hearing. By distinguishing even minute differences in component sounds, it is utilized for noise inspection of industrial components such as actuators, motors, and gears, as well as component engagement sound inspection. It is currently being supplied to affiliates of the H Group (an automaker), Hyosung Electric, and Korail. As the physical AI field centered on actuators, such as robotics and e-mobility, becomes more active in the future, the utilization of this solution is expected to increase further. ‘Listen AI Safety’, a public safety AI sound analysis solution, is an AI solution that identifies safety through sound in restrooms, fitting rooms, and blind spots where human vision or CCTV cannot directly intervene. It identifies unseen danger signals such as screams, loud voices, crying, and requests for rescue, enabling immediate response to safety accidents. It is currently in use at the Government Complex Sejong gymnasium, Naejangsan National Park, Incheon Transit Corporation, and Kangwon Land. It is also being exported to global markets such as the Singapore Ministry of Home Affairs, Thailand, and Vietnam. Media Contact: Deeply Inc.Kisun KimHead of Business Development[kisun@deeply.co.kr](https://www.thailand-business-news.com/pr-news/kisun@deeply.co.kr) --- | This article was produced by Cision PR Newswire, our trusted news partner. The views expressed and the content presented here are solely those of the author and may not fully reflect the opinions of Thailand Business News. | --- **Read the original article :** [Deeply's Industrial Acoustic AI Solution Solves Connector Engagement Defects in Auto Assembly Lines, Expanding Application in Global Production Lines ](http://www.prnasia.com/story/archive/4981472_CN81472_0?rand=184833)