Amsterdam, The Netherlands — April 8, 2019
Today, Aigent, the leading artificial intelligence driven solution for customer call centers, announced it has launched a new speech model, an automatic speech recognition technology that will enable it to transcribe audio to text in a high-quality, efficient way.
Speech recognition is a capability that enables a computer or program to recognize and process human speech into a written format. Aigent’s model is built on open-source software and will serve as the centerpiece in its continued development of tools that enhance call center actions using its artificial intelligence platform. The model works by breaking down spoken words to smaller samples and using algorithms to combine and match the samples to language pronunciation and word formation.
Today’s call centers are growing larger and more complex; they have vast amounts of data. As operations grow, so does the volume of recordings, which are difficult to process without machine help. To improve service, call centers must analyze and understand each customer interaction to identify root causes of issues. With speech model technology, call centers can transform audio to text and analyze it efficiently using natural language processing tools. Supervisors and managers can then extrapolate key themes and words from customer interactions to develop better processes – and index them for future use.
Aigent’s speech model enhances call center operations by facilitating reduced wait times, creating self-service options which cuts the workload for call center agents, and providing opportunities to identify issues and areas for improvement.
“It was clear from the outset that we needed to be able to transcribe audio to text in a high quality and cost-effective way,” said Sebastian Lagemann, Co-Founder and Chief Technology Officer at Aigent. “We have very specific needs with our technology and building this model is key to our ability to launch new features and functionalities that are essential to our platform,” he said.
“By having the right people and generating data we were able to train our speech recognition under our direct supervision, which made it easy to build out best-in-class speech recognition capabilities,” said Lagemann. “With open-source technologies we were able to integrate existing technologies into our real-time processing platform. We now have a model that can be tailored for our customers and give them the best possible transcription quality and ultimately one that produces meaningful and accurate insights for their agents in real-time.”
Aigent is a Live Voice AI Saas platform that quickly and easily connects to most existing premise or cloud-based telephony systems and provides real-time, content-based guidance to call center agents. Detecting opportunities during a live call, Aigent helps agents deepen customer relationships while supporting corporate client objectives to generate new and protect existing revenue. Designed for Inbound and Outbound calls; Customer Service, Support, and Sales, Onsite, and Work From Home. Our platform natively supports English and can be customized to support any language.