[HelloAI] Deeply Sets a New Standard in Safety with 'Sound Understanding AI'

▲ (From left) Suji Lee, CEO of Deeply, and Myunghoon Ryu, CIO

Interview with Suji Lee, CEO of Deeply

As AI technology moves beyond visual recognition into auditory analysis, it becomes increasingly integrated into daily life and work environments. Deeply, an AI startup focused on sound-based solutions aims to enhance efficiency and create new value across various industries. We spoke with Suji Lee, CEO of Deeply, about the company’s founding, technological evolution, and long-term plans.

Preventing Risks with 'ListenAI'

Deeply, it has gained attention for developing AI solutions that use sound data for emergency detection and industrial applications. Their flagship product, ListenAI, analyzes real-time patterns such as screams, collisions, and machinery noises to address safety issues in industrial and public spaces. With a focus on B2B solutions, Deeply aims to implement predictive maintenance systems that boost efficiency and safety in manufacturing.

What sets ListenAI apart is its ability to analyze complex audio environments and recognize patterns to make real-time assessments, going beyond just detecting volume or vibrations. This capability has been deployed in subways, large shopping centers, and factories, offering precision previously lacking in AI systems. This precision improves industrial safety and enables predictive maintenance, strengthening Deeply's competitive advantage.

ListenAI has demonstrated its capabilities through deployments at various public and private sites.. Notable examples include installations at the Government Sejong Complex, Kangwon Land, and Incheon National University Station. At the Government Sejong Complex Sports Center, over 10 units of ListenAI were installed to monitor blind spots that CCTV cannot cover, ensuring comprehensive emergency detection. At Kangwon Land, the system detects and preempts conflicts between patrons, allowing for immediate intervention. In Incheon, ListenAI identifies sounds such as female screams and violent altercations, promptly alerting control centers. “The system can analyze and trigger warnings within seconds of sound detection, helping prevent real-life threats,” said CEO Lee.

Predictive Maintenance in Manufacturing

Deeply’s sound analysis technology is also making waves in the manufacturing sector through its predictive maintenance applications. Their solution detects potential malfunctions in rotating machinery and motors by analyzing abnormal sound patterns. For instance, ListenAI can identify vibration patterns indicative of potential bearing failures, issuing warnings before breakdowns occur. This approach has earned high praise from manufacturers, outperforming traditional vibration-based monitoring systems in both speed and precision.

“Minor issues in machinery that go undetected can lead to significant accidents. However, current vibration sensors can’t detect all internal noises or abnormal behaviors. Our AI solution comprehensively analyzes sound signals to precisely diagnose machine status,” explained Lee. This technology helps plant operators avoid unexpected equipment failures, reducing downtime and maintenance costs.

“Establishing a Robust Safety Framework with High-Quality Data”

Deeply’s AI solutions prioritize contextual understanding of sound, built on a vast dataset exceeding 50,000 hours. This extensive collection includes not only conventional sound data but also situation-specific and global environmental audio, ensuring high accuracy and reliability. The company’s strong dataset foundation is one of its key strengths. Early in its journey, Deeply enhanced its AI capabilities with sound data collected from home environments during its initial B2C phase.

As it shifted to B2B, Deeply expanded its data collection efforts internationally, including field data from locations like India. Gathering audio from crowded streets with varied noises such as car horns and emergency alerts, Deeply developed models capable of accurately detecting emergencies in complex global environments. This expertise has positioned Deeply in voice recognition and as a comprehensive solution for analyzing and classifying all forms of unstructured sound data.

Today, Deeply offers tailored solutions across industries, customizing models to meet client needs. For example, in manufacturing, the system collects and analyzes data from on-site microphones and servers to detect anomalies and assist with prompt interventions. Integrating with traditional vibration and ultrasonic sensors enhances predictive accuracy, and Deeply’s AI continuously learns to improve its precision. In the safety sector, ListenAI works in tandem with CCTV systems, combining visual and audio data for greater reliability, showcasing Deeply’s multimodal approach.

Looking ahead, Deeply aims to further leverage its sound recognition technology to enhance safety and productivity across industries. “AI has evolved from a supporting tool to one that supplements human senses, like hearing,” said CEO Lee. “We’re advancing toward an AI that can understand and respond to complex sound environments autonomously.” To achieve this, Deeply plans to expand its datasets, develop new algorithms, and strengthen partnerships to provide customized solutions for various sectors.

Deeply is also developing an integrated solution combining hardware and software to accelerate market entry. Beyond offering software, the company supplies custom microphones and servers to ensure optimal performance in diverse environments. For example, high-frequency and vibration-detecting microphones are used in manufacturing settings, while noise-filtering features are incorporated for noisy sites like construction areas or subways, enhancing accuracy.

By providing tailored solutions for different industry needs, Deeply seeks to expand the applications of AI sound recognition technology. “Our ultimate goal is to go beyond just offering sound analysis AI solutions to becoming a comprehensive platform that revolutionizes safety and efficiency across all industries,” concluded CEO Lee.

— Jaechang Seo, HelloT News  

https://www.hellot.net/news/article.html?no=9515