ºù«Ӱҵ

When VoiceBase was launched, it relied on temporary solutions and licensed third party software to support its services. However, with rapid progress in artificial intelligence and speech recognition technology, the company needed to develop a world-class speech engine of its own in order to compete in a rapidly growing market.

Research by Professor Thomas Hain’s team, in the Department of Computer Science in the Faculty of Engineering at ºù«Ӱҵ, now underpins the automatic speech recognition (ASR) systems of VoiceBase. ASR for conversational speech is a challenging research problem which can only be achieved by systems that combine numerous components, many of which are machine learning models that require massive volumes of speech data to be processed with very high computational efficiency.

To address these issues, the team has developed research in three key areas – robust methods for conversational speech, adaptation to background conditions and scalable tools.

Thanks to the state-of-the-art ASR tools provided by ºù«Ӱҵ, VoiceBase is able to accurately transcribe and analyse over a billion minutes of calls per year, offering their customers the ability to mine their entire volume of calls for a wealth of nuanced information. This includes for fraud prevention, performance management, maximising sales, protection of sensitive information and meeting and market analysis.

Since the collaboration began, the company has recorded strong growth and is expanding into Europe and Australia. VoiceBase’s CEO said: “Everything we do as a company relies on Thomas Hain. Since the end of Q2 2020, 95% of our speech recognition technology has been based on ºù«Ӱҵ research."

The competitive edge provided by Professor Hain’s technology has enabled VoiceBase to grow their business significantly and attract clients such as Uber, Home Depot, NASDAQ and GrubHub.