We met up with Jeh Daruvala, CEO of Yactraq, a machine learning company with cutting edge technology that delivers business intelligence using audible or video input. In layman terms, their patent pending technology can be used to accurately search through tens of millions of hours of call center recordings TV shows, movies etc. in a fast and cost effective manner in order to provide actionable insights and intelligence.  Here is what he had to say about one of the most coveted spaces in technology.

Q: Can you please tell us about your company and the specific challenge that you are addressing?

Yactraq empowers SMB & Enterprise clients with machine learning driven insights extracted from any audible media. We deliver omnichannel business intelligence with a next generation platform through large scale customized vocabularies at 40x cost & speed efficiencies over legacy solutions. Legacy speech solutions based on phonetics systems are an expensive and dated technology, and their high price tags in the $1M+ range have priced virtually all SMBs, and many enterprise players as well, out of the market. Yactraq’s answer to this problem is OmniTraq, our omnichannel business intelligence solution that will finally put advanced speech technologies into the hands of businesses that need them.

Using our automated & patent pending technology, we provide critical business insights on customer call operations, web media, video, audio, and text data. By providing accurate, customized audio mining and speech analytics solutions at unprecedentedly low price points, we are democratizing the speech tech industry and making this technology available to businesses of nearly any size.

Yactraq was named as a 2016 Gartner Cool Vendor in Smart Machines, among the first 20 companies showcased in IBM Watson’s Cognitive Gallery, and an IP for Defense partner of Intellectual Ventures.

Q: Please tell us a little about your technology that drives your platform?

OmniTraq is a versatile application layer that leverages the cutting edge capabilities of our core speech technology platform, CoreTraq. OmniTraq offers a multitude of audio mining & speech analytics capabilities that can be utilized across any industry or vertical, with use cases ranging from call center operations to brand sentiment monitoring in social media.

In the world of audio mining & speech analytics, context is king. Without a speech vocabulary that is specifically customized to the nature of a businesses, that business won’t be able to create the context necessary to identify and extract the information needed to solve the problem at hand. CoreTraq, our award winning & patent pending speech based semantic computing platform uses machine learning techniques to build speech vocabularies that are customized to a client’s specific business, consist of tens of thousands of words, and can be built in a matter of weeks.

CoreTraq lies at the heart of our OmniTraq business intelligence solution, and is a truly innovative next generation speech technology platform that approaches speech recognition & audio mining from a new angle, one that far surpasses the capabilities and cost effectiveness of legacy speech tech solutions. CoreTraq is fully developed and proven in the marketplace, having processed over 4 million minutes of customer data in OEM capacities. Yactraq has a pending patent for automating the generation of language models in speech recognition systems, and this process includes web crawling techniques to populate linguistic data within a Natural Language Understanding (NLU) engine.

Q: You’ve developed a next generation machine learning platform for audio-mining and speech analytics; can you give us more insights into your technology?

Beyond the basic functionality offered by legacy audio-mining systems, Yactraq’s OmniTraq audio mining product offers revolutionary machine learning driven capabilities that enable our clients to detect customer sentiment and monitor service quality in new and powerful ways, across a range of verticals. OmniTraq can be viewed as an analytics, reporting, and search layer that leverages CoreTraq’s capabilities as a speech based semantic engine. CoreTraq uses a machine learning driven approach that quickly and cost effectively customizes its vocabulary to include product names and other terms that are unique to a specific client. This helps to deliver meaningful business insights with a high degree of precision.

Q: What markets will you focus on in the near future and what is your plan to conquer them?

Our present area of focus is bringing our OmniTraq business intelligence solution to the call center operations market in the retail, finance, and travel verticals, with a future focus of expanding into the healthcare and government verticals. Additionally, OmniTraq can provide business intelligence around brand & consumer sentiment, competitive intelligence, and media monitoring, as well as providing internal enterprise functionality, such as corporate training.

Our plan to conquer these markets is to both educate the markets on the incredible value that OmniTraq can bring to businesses and continue to prove OmniTraq’s value through a growing portfolio of happy clients. OmniTraq can provide an extremely attractive ROI as it provides intelligence for both operational performance improvement (e.g. improved service levels, compliance, costs savings) and business value improvement (e.g. informed product strategy, data driven decision making, measured brand awareness) for hyper-competitive pricing compared to anything on the market. Yactraq’s solutions will disrupt the stale and privileged status quo of the speech technology industry and allow a multitude of business to actively and aggressively embrace this game changing technology.

Q: What are the key user benefits and features of your platform?

OmniTraq has multiple user benefits and features that adapt to the use case or vertical for which it is deployed, so let’s discuss an example from our current area of focus, customer call operations. Quality assurance for phone based sales and customer service is still in the dark ages.  Just imagine a world where your company operates without computers, without big data analysis, and essentially without any audit trail that is searchable quickly and effectively.  How could you possibly do a good job of managing a sales team if you had no way of comprehensively tracking their success in quantifiable, revenue terms? Is it a surprise then that call operations have a hard time attracting and retaining talent? At present call recordings are analyzed at great cost by a few human quality analysts who cannot get to more than a 2 to 4% random sample of the data.  Managing a call operations team in such an environment can seem capricious, even entirely random! Audio mining and speech analytics software turns recorded phone calls into searchable, trackable, and auditable data. This completely takes the guesswork out of managing call operations and transforms it from a decades old model of inefficiency into a shining new science.

Q: Who are your competitors?

NICE and Verint are the two multi-billion dollar NASDAQ listed players who pioneered audio mining.  Unfortunately, by building expensive products for national security agencies and Fortune 100 corporations with 1000 seat plus call centers, they have limited the growth of this market.  Today audio mining is a roughly $600 million annual marketplace.  Yactraq delivers very high quality, custom vocabulary driven and machine learning enabled capabilities to call operations of any size, even as small as 10 seats.  As a result Yactraq expects to help grow the audio mining market to its full potential which is easily in the billions of dollars annually.

Q: What advantage does your product offer in contrast to your competitors?

Our extraordinary value proposition, our technology, our position in the market, and our diverse team of specialized and seasoned experts sets us well apart from any other players in this industry. There is simply no competition in the speech tech domain that offers Yactraq’s unique blend of relevance, affordability, effectiveness, and expertise. We are a truly singular company in the speech tech market, and Gartner agrees, having selected us as a 2016 Gartner Cool Vendor in Smart Machines.

Legacy phonetic speech systems are unable to keep pace with and benefit from rapid advances in machine learning.  Their highly limited vocabularies do not allow higher-level semantic extraction via natural language processing. These fundamental limitations, combined with their low precision, drives the need for more capable and cost-effective speech-to-text based semantic engines..

Yactraq’s CoreTraq platform can ingest semantic and linguistic training vocabularies of hundreds of thousands of words and millions of sentences in a matter of hours or days, and do this in a seamless, almost fully automated manner.  This degree of automation allows Yactraq to deliver custom vocabulary speech systems at costs that are orders of magnitude below phonetic systems. This reduces manual effort and costs, resulting in far more business value, to the point where almost any business of any size can afford and access audio mining.

Q: What makes your platform stand out?

Once again we’ll focus on our current target area of call center operations in the retail, finance, and travel verticals to show how Yactraq differentiation in the marketplace. Yactraq can index every minute of every customer call, and thereby robotically generate data that can then be used for contact center agent evaluation and customer service management. Yactraq can deliver high quality, custom vocabulary driven audio mining to businesses with call operations with as few as just 10 agents. Providing this kind of speech technology to call centers down to that size is previously unheard of, and this is a market that has not been served by existing audio mining & speech analytics solutions. Additionally, Yactraq can provide tremendous value to enterprise business units that haven’t been able to access and utilize speech technology due to the immense price tags of legacy solutions (usually in the $1M+ range). In contrast to restrictive legacy pricing, Yactraq can provide high impact speech solutions at price points that nearly any SMB or any enterprise business unit budget can afford, and in a fraction of the time. This means virtually any business with a call center can gain the benefit of critical and actionable business intelligence at a very low barrier to entry, and start seeing the positive effect of those benefits in a short amount of time.

Q: Tell us about your team?

Yactraq has an outstanding team with experienced technology entrepreneurs, world class speech scientists and engineers, and experts in machine learning and high technology marketing.  Key team members and advisors have made pioneering contributions in innovation driven fields as diverse as embedded and military speech technology, pattern recognition, networking and semiconductors, in both business and technical roles.

Q: How do you position yourself in the current domain?

We are uniquely positioned in the speech tech industry as an innovator with our next generation technology platform, as a market disruptor through our extremely competitive pricing & customization capabilities, and as a highly stable player through our tactical corporate strategy of partnering with Intellectual Ventures by participating in their IP-for-Defense Program. This program makes Yactraq arguably the best defended speech startup in the world from an IP standpoint, and provides us with an unparalleled freedom to operate in the industry. Additionally, as a With Watson partner of International Business Machines Corp. (NYSE:IBM) Watson, we are operating in good company on the forefront of the speech technology industry.

We are opening up an entirely new market opportunity by aligning our cutting edge technology platform and our application layer business intelligence solution with the needs of a vast market of unserved or underserved businesses that can greatly benefit from audio mining & speech analytics solutions. There are thousands of SMBs, as well as enterprise-level business units, that can now afford these critical and high impact solutions through Yactraq, a first of its kind shift in the speech technology industry.

Q: Tell us about a specific customer success story.

Our OmniTraq business intelligence solution was released in Q1 2016, and during the first half of 2016 it was in beta trials. We have begun production this quarter with a publicly listed player in the travel vertical, with Yactraq audio mining robotically listening to and analyzing all contact center agents’ speech patterns. OmniTraq then delivers quantitative reports on successful speech patterns and which agents are likely to drive higher revenues. On an agent-by-agent basis OmniTraq reporting provides data on how well agents are executing on their advanced sales training, as well as on basic script adherence. Apart from being used for management information purposes, OmniTraq data is also used as a training tool for agents to observe their own performance and learn how they can improve – all based on accurate, objective, and quantitative data.

Q: What is your focus for the next 6-12 months?

Our focus for the next 6-12 months is to grow our clientele base in our primary focus market of customer call operations for our core verticals of retail, finance, and travel. Additionally, we are exploring potential OEM partnering opportunities that will allow us to accelerate bringing OmniTraq to market and benefit existing customer bases with the now affordable audio mining & speech analytics solutions Yactraq can provide.