Advancements in AI, which is driven by deep learning, are enabling enterprise companies to transform their workflow. In this talk, we will discuss how AI can change the customer contact centers that record millions of calls per day. The Gridspace Sift conversational search system is designed to search through billions of minutes of long-form, conversational speech data. The core technology allows for complex searches that combine semantic and signal information, and a method for executing constraints on time, logical structure, and metadata. The live demo highlighting use cases will be demonstrated. Also, we will introduce our ongoing work for other emerging problems on our journey for for digital-transforming the industry including capturing emotions from conversation and building dialogue systems for human-like interactive voice response(IVR).
Wonkyum Lee is Lead ASR Engineer at Gridspace, working on deep learning for various tasks in speech recognition, speech synthesis and NLP. He likes to write code and to play with GPUs. He studied at Carnegie Mellon University with the focus on automatic speech recognition and deep learning. He also had research on signal processing while he studied at Korea University and KAIST. Previously, he worked at Capio, Samsung Research America, KAIST Institute.