Data Science

Data science is a rapidly-growing specialist field, combining computer science and statistics to gain insight from (typically lots of) data. We focus on machine learning and pattern recognition, and work with companies that are eager to gain a competitive advantage by leveraging appropriate techniques in data science to gain additional insight from their data. Application areas include the following:


call center speech analytics In partnership with EOH, we are developing a state-of-the-art speech analytics product that will allow clients to improve compliance, efficiency and productivity within the call center.
churn reduction Identifying clients that are likely to churn before they do so, allowing for timely intervention.
product recommendation Our algorithms can predict which products clients are likely to buy, based on their and other customers’ spending behaviour. Advertise these products to maximize your chances of upselling.
customer analysis Gain insight and build customer specific profiles to improve customer experience and value.

About

SAIGEN is part of the Alphawave group, which employs 165+ people, 100+ of which are engineers.

We want to add value to the activities of our partners in industry, by applying expert knowledge in machine learning and data science to gain insight and value from their data. While being well-published academics, we have also collaborated with international partners to solve interesting and challenging problems: we were part of the consortium which won the recent IARPA-sponsored spoken term detection Babel-program, we worked with Google on Voice search for the South African languages and were the first to build speech recognition systems in all 11 of South Africa’s official languages.

Our Team

Jane

Etienne Barnard

CEO & Founder

Etienne obtained his Ph. D. in Electrical and Computer Engineering from Carnegie Mellon University in 1989, writing his thesis on “Neural Networks for Scene Analysis”. He has since then been active in research and development in pattern recognition and speech processing. He has held a number of academic positions, and has also worked in industry. Etienne has co-authored more than 250 refereed scientific publications, on topics including pattern recognition, neural networks, speech recognition and human-computer interaction. He holds a number of international patents in speech processing and is a past Associate Editor of the IEEE Transactions on Neural Networks. Etienne’s research contributions have been recognized in various ways, including Google Research Awards in 2009, 2011 and 2014.

John

Charl van Heerden

CTO & Founder

Charl completed his B. Eng at the University of Pretoria, and started working with Etienne (then his M. Eng supervisor) at the CSIR in 2005. He interned with Google in 2007 (language modeling for GOOG-411), 2008 (language modeling for Voice Search) and 2010 (Voice Search for Afrikaans, English and isiZulu), before returning to South Africa to complete his Ph. D. in Computer Engineering (thesis: “Efficient training of Support Vector Machines and their hyperparameters”), co-authoring 40+ peer-reviewed papers on speech recognition and general pattern recognition. More recently, he was part of the NWU MuST team, which was part of the consortium which won the international IARPA-sponsored Babel competition.

CAREER HIGHLIGHTS (prior to founding SAIGEN)

IARPA Babel Challenge

The US Intelligence Advanced Research Projects Activity (IARPA) sponsored a four-year international competition, with the aim to develop technologies to rapidly build spoken-term detection systems for new, previously under-resourced languages within one week. Four consortiums of top international speech recognition companies and universities competed. Barnard and van Heerden (at the time both part of the MuST research group at  North-West University), together with their colleagues at MuST, formed part of the winning BBN-led Babelon consortium, which also included MIT, JHU, LIMSI and BUT. Read more about the project here.

Google Voice Search

Google launched its voice search functionality for US English in 2008. Barnard and Van Heerden (then part of the HLT research group at the CSIR), worked with Google to build voice search for Afrikaans, South African English and isiZulu. The HLT team assisted Google with collecting hundreds of hours of spoken queries required to build a system ready for launch. They also developed pronunciation dictionaries for the three languages; another vital ingredient for a speech recognition system. In 2010, Voice Search was launched for the three South African languages. Read more about the project and collaboration here.

Contact