Financial language and the evolution of speech recognition technology
By Katy Wigdahl, CEO, Speechmatics
Due to its long heritage and diverse diffusion of legacy technologies, it can be difficult to integrate new technological developments in the financial industry. But by not doing so, many financial service providers may be left behind as more agile, digital-native challengers respond to increasingly sophisticated customer demands, automating workflows and ultimately reducing costs. costs.
One of these technologies has been used for some time by companies in other industries to increase efficiency and improve the customer experience. Recent advances in Automatic Speech Recognition (ASR) mean that the financial services industry can now experience similar benefits across a range of applications. Indeed, besides the obvious business benefits, accurate speech recognition makes businesses more inclusive – by understanding every voice, the finance industry as a whole can do better for society as a whole.
ASR was once the stuff of science fiction. Now, however, many of us use it in our daily lives – asking Siri or Alexa questions, for example, or dealing with automated customer service assistants when calling our energy provider.
The beauty of ASR is that it can be trained. He can add commonly used words or new slangs and jargons to his vocabulary, thus expanding his understanding of speech. Some more sophisticated forms of ASR software, like standalone speech recognition, are even programmed to train themselves – they continually evolve with the world, able to learn, adopt and retain new words.
Historically, however, training data had to be labeled, categorized, or “tagged” manually. As a result, speech recognition engines were trained on narrow datasets, which did not represent the diversity of voices using them and lacked the breadth of vocabulary used in other sociodemographic data. But, by training these engines by exposing them to thousands of voices, using millions of hours of unlabeled and more representative data, there has been a paradigm shift in accuracy, especially when it comes to deals with complex industry-specific terms and jargon.
Indeed, the financial services industry is notoriously loaded with jargon, using complex terms that are either completely unique to the industry or can be confused with commonly used expressions. Acronyms like TVA and SEC can often confuse standard text-to-speech engines, while abbreviations like GAAP (Generally Accepted Accounting Principles) can be confused with other words, like “gap” in this case.
An appreciation of this problem has led to the development of domain-specific technology, which means that ASR solutions are now able to capture voice data in the financial services industry as intended, turning unstructured audio data into transcriptions precise and – above all – immediately usable.
Multiple Use Cases
Capable of identifying financial terminology in verbal conversations, this latest iteration in the evolution of ASR technology can be used in a number of use cases, such as ensuring compliance and identifying fraud. In fact, financial services organizations are already using it to transcribe revenue calls, for example, as well as to help call center analysts and marketers.
Other use cases where ASR can provide benefits for the financial services industry include improving contact center efficiency. Voice data analytics can help contact centers unlock new meaning and value from customer interactions. In the past, only about 3% of call data was evaluated. ASR technology, however, facilitates the archiving and evaluation of every customer interaction, the benefits of which are obvious. Among the top business efficiencies unlocked by using voice recognition, recent research found that 40% of contact centers were able to increase productivity by anticipating the purpose of each call, allowing agents to handle more interactions in a similar time frame.
The proliferation of voice assistants cannot be ignored either. A study by Juniper Research reveals that the value of e-commerce transactions made via Amazon Echo, Siri, Google Assistant and Cortana is expected to increase by 400% between 2021 and 2023. And when more than two-thirds of the world’s population have access to a device mobile, there is absolutely no reason why the financial services industry should not be prepared for voice transactions and interactions.
And, of course, regulatory compliance is, and always will be, a top priority for financial services organizations. FCA COBS 11.8, for example, explicitly requires banks to have a system in place to log interactions across the business to ensure their transparency in the event of a compliance-related issue. Accurate and efficient ASR recognition technology helps organizations automatically monitor and transcribe interactions at scale, reducing costs and protecting them from reputational damage and regulatory fines.
As businesses and consumers around the world reap the benefits of increasingly sophisticated speech recognition technology, the global text-to-speech market is expected to grow 19% to reach $5.8 billion by 2027 .
But until recently, its specific jargon and nuances prevented much of the financial services industry from taking advantage of what technology has to offer. Today, however, industry-specific vocabulary training means organizations are able to use accurate voice data to increase efficiency, improve customer experience and ensure regulatory compliance. In doing so, ASR technology has a vital role to play in the digital transformation of the financial services industry. Financial services have an impact on everyone: the use of new technologies is not only about improving the customer experience, but also about tackling inequalities and widening accessibility to services, ensuring that we all benefit from the best that technology has to offer.