Join us in Venice, Italy for BOLD Awards 5th edition
Time's ticking! BOLD V submissions close in
Day
Hr
Min
Sec
Bold Awards

Speechmatics: Financial Language Pack

Speechmatics has revolutionized STT in FinTech, with our new Financial Language Pack. Trained on 200,000 hours of earnings calls, we’ve reduced errors by 40%.
Speechmatics Financial Language Pack-cc087613

Fresh from taking home the BOLDEST AI Award in 2022, Speechmatics, the leading speech recognition technology scaleup, has successfully launched our Financial Language Pack. This first of its kind, English language pack, is specific to the finance industry and massively helps the world of FinTech in terms of accuracy and accessibility. This addition has been built for use cases including compliance, fraud identification, analytics, financial news and earnings calls. The world’s most accurate and inclusive speech-to-text engine can now identify finance terminology in conversation helping to avoid confusion with abbreviations, acronyms and finance-specific terms.  

The financial services sector is notoriously jargon-heavy with industry terms that are either completely unique to the industry or that can be confused with commonly used phrases. Acronyms such as VAT or SEC or abbreviations e.g. Generally Accepted Accounting Principles (GAAP), and the word ‘gap’ can often confuse standard speech-to-text engines. Our breakthrough means we can now capture the speech data as intended, turning unstructured, audio data into usable information.  

Global experts in deep learning and speech recognition, Speechmatics has built the most accurate and inclusive speech-to-text engine available. Historically, training data had to be manually tagged, classified or ‘labelled’. This has resulted in engines trained on narrow datasets, which fail to represent the diversity of voices that use them. In contrast, Speechmatics’ speech-to-text engine is trained through exposure to hundreds of thousands of individual voices using millions of hours of unlabelled, more representative voice data. This has enabled a paradigm shift in accuracy, dramatically reducing both AI bias and errors in speech recognition. Given the broad range of demographics that exist within financial services, Speechmatics’ new offering will be key to supporting and sustaining inclusivity in the sector. 

Katy Wigdahl, CEO, Speechmatics, said, “Our aim is to understand every voice regardless of race, gender or accent and I’m proud that Speechmatics has overcome significant challenges that traditional speech-to-text engines have struggled with.”  

“However, we wanted to go even further and dive into the complexities that specific industries present. Some sectors are known for complex terms and jargon that, if added to our global models, risk making the technology less effective for other users. This led to our approach for domain-specific packs that can directly address the needs of individual sectors. Financial services was an obvious place to start but we hope our language pack will set a blueprint for every high-stakes industry where the financial, reputational and social cost of misunderstanding is high.” 

Customers are already using the finance language pack to transcribe financial news and earnings calls as well as utilising the technology to aid call centre analysts and traders. The pack is the first industry-specific pack and paves the way for industries with equally complex terminology such as medicine and law. 

The introduction of our Financial Language Pack comes at a demanding time for the financial sector. Banks, insurance companies and brokerage firms all face new and existing regulations to protect themselves and their customers from financial fraud and crime. These onerous regulations are extremely complex, and non-compliance can result in reputational damage and huge regulatory fines. In the UK alone, the Financial Conduct Authority levied over £567million of fines in 2021 related to breaches including money laundering, financial crime, and bribery.  

The MiFID II directive, for example, requires that all communication pertaining to a financial trade or transaction, needs to be retained for a period of five years with firms required to conduct surveillance of their employees’ communications to ensure they’re compliant with market rules. 

Our Financial Language Pack lets companies effectively monitor all of their customer calls, video conferences, face-to-face meetings and trading room communications. This improvement for speech-to-text transcription produces usable and searchable speech data to deliver risk and scenario-based insights, and flag any compliance issues. 

Accurate and effective speech-to-text can help organizations meet their regulatory compliance goals by automatically understanding and transcribing voice recordings or live conversations at scale. This automated approach ensures all interactions are monitored (not just a sample), often across a large set of global languages, thereby reducing manual staffing costs, increasing operational effectiveness, and reducing errors.  

Transcription accuracy is of paramount importance to maintain confidence in compliance solutions. For example, here are two transcriptions from the same financial call:  

The first example shows how poor transcription accuracy can result in an unreadable, confusing and false record. In the second example, the call is transcribed correctly with the correct financial jargon and can be used confidently for analysis and accurate record-keeping. In a global market, this needs to be done for a host of languages.  

Until recently, the nuances of financial jargon and finance-specific terms have prevented the financial services industry from taking advantage of what speech technology can offer. After all, if their voices can’t be understood by speech-to-text, how can they be sure of regulatory compliance?  

Making out Financial Language Pack even clearer is our new Entity Formatting feature, which correctly formats numbers, dates, currency and language-specific punctuation (including commas, question marks, and exclamation marks) to improve readability and to understand context.  

With the option of on-premises and SaaS deployment models, we can also ensure organizations are able to use accurate speech data to not just improve customer experiences, but to meet their regulatory obligations too. Wherever and whenever they need it.  

At Speechmatics, we believe accurate speech-to-text is the route to building robust solutions in FinTech. Which is why we deliver best-in-class automatic speech-to-text at scale and at a low cost in as many languages as possible. It also explains why we recently won the FinTech Innovator of the Year award at the UK Business Tech Awards.

Projects evaluation criteria

Level of Impact
40%
Scalability
30%
Transparency
20%
H-Factor
10%

---

VOTES

Surina

10.00

Olga

10.00

Caterina

10.00

Seth Odoi

10.00

Maria

10.00

Alex

10.00

Ravina

10.00

Reggie

10.00

10.00

giorgos

10.00

2 Days / 3 Nights
BOLD VI Edition
WIN A TRIP
TO LISBON
One RT Flight from any European City including hotel accommodation. + 2 seats at the Award Ceremony
NOTE: Participants must be 21 years or older to win, and the drawing will take place on September 25, 2024.

Gala Dinner Tickets are €975 per seat which includes a 3-course dinner and drinks. A €50 deposit is required to reserve your seat(s) at the end of this form. The deposit is refundable if not selected to participate. If accepted, the deposit will be deducted from the ticket price.

To upgrade your existing ticket or transfer your ticket to another name, email sarahj@bold-awards.com.