About Us
Staff
Dr Anil Alexander
Founder, CEO
Dr Anil Alexander is the CEO of Oxford Wave Research and his areas of interest and experience are forensic audio processing, microphone arrays and speaker recognition. He has published widely in international conferences and journals and is an invited speaker at several conferences and workshops. His doctoral research focused on forensic automatic speaker recognition with the Speech Processing and Biometrics Group, at the Swiss Federal Institute of Technology, Lausanne, and the Institut de Police Scientifique, Faculty of Law and Criminal Sciences, University of Lausanne, both in Switzerland. He enjoys teaching audio processing for law enforcement and work involving speaker recognition, audio enhancement, and acoustics. Dr Alexander has also chaired the research committee of the International Association for Forensic Phonetics and Acoustics (IAFPA).
His LinkedIn Profile can be found here.
Oscar Forth
Founder, CTO
Oscar Forth is OWR’s CTO. He has extensive experience in gaming software development on multiple console and PC platforms and has created a unique cross-platform 3D engine. He has led the development of several speaker recognition R&D projects as well as doing R&D into microphone arrays. He is the driving force behind software product development and has a large number of products to his credit ranging from high performance PC applications, console and PC games, and specialist mobile applications.
His LinkedIn Profile can be found here.
Dr Finnian Kelly
Principal Research Scientist
Dr Finnian Kelly is a Principal Research Scientist at Oxford Wave Research. Finnian leads some of our latest R&D developments in automatic speaker recognition, speech and speaker analysis, and audio processing.
Finnian joined Oxford Wave Research in 2016 as a Senior Research Scientist, and since then has made significant contributions to the development of our speaker recognition and audio processing systems. He has successfully led the OWR team in two NIST speaker recognition evaluations. Finnian was with the Sigmedia Research Group at Trinity College, Dublin where he completed his PhD in 2013, and was subsequently a Research Associate with the Center for Robust Speech Systems (CRSS) at The University of Texas at Dallas. Finnian has published in (and acts as a reviewer for) many top-tier international conferences and journals, and has been an invited speaker at research labs in Europe and the US. Finnian is the current chair of the research committee of the International Association for Forensic Phonetics and Acoustics (IAFPA), and an active affiliate member of the NIST OSAC Speaker Recognition subcommittee.
His LinkedIn Profile can be found here.
His published research can be found on Google Scholar and Research Gate.
Dr Amelia Gully
Senior Research Scientist
Dr Amelia Gully is a Senior Research Scientist at Oxford Wave Research.
Amelia joined OWR in 2022 and is part of our R&D team working acoustics, speech and audio signal processing research. She holds a British Academy Postdoctoral Fellowship, which focuses on how vocal tract shape impacts the speech signal, and incorporates novel statistical techniques for shape analysis alongside numerical acoustic modelling and audio signal processing. She has a PhD in Electronic Engineering (York), an MSc in Digital Signal Processing (York), and a BSc (Hons) in Audio Technology (Salford), and has participated in a wide range of research projects in acoustics and signal processing. She is passionate about communicating the importance of forensic audio work and featured on the popular Tom Scott YouTube channel as well as writing an article for young minds about forensic speaker comparison. Amelia is currently a research associate at the University of York. She is a member of the International Speech Communication Association and sits on the Computational Acoustics committee of the UK Acoustics Network.
Amelia’s LinkedIn Profile can be found here.
Dr Ekrem Malkoç
Customer Experience and QA Manager
Dr Ekrem Malkoç is Oxford Wave Research’s Customer Experience and QA Manager.
He is a well-known expert in the field of forensic speech and audio processing, forensic image analysis as well as forensic linguistics. He has a PhD in forensic linguistics from Ankara University (Turkey), MSc and MA degrees in Criminalistics and European Criminology from the Ankara University and Katholieke University of Leuven (Belgium) respectively, and a bachelor’s degree in Electrical and Electronics Engineering. Ekrem started his career in Turkish Gendarmerie Forensics Department (JKDB) as an assistant speech, audio and image analysis expert. Focusing more on linguistics and phonetics in the later years, he did his PhD in Ankara University Linguistics department. He studied speaker specific invariants in speech to determine which acoustic characteristics of Turkish vowels are more speaker specific. Ekrem has been an active member of the European Network of Forensic Science Institutes’ (ENFSI) Forensic Speech and Audio Analysis Working Group and also served in its Steering Committee. During his MA in European Criminology, Ekrem focused on the accreditation of forensic science laboratories and after completing his studies, he became the assistant quality manager at the Turkish Gendarmerie’s Forensics Department and led the quality module of an EU Project at the end of which JKDB became the first Turkish ISO/IEC 17025 accredited forensic science laboratory. Ekrem has retired from the Turkish Gendarmerie in 2015 as a Colonel after having served as the Manager of two regional Gendarmerie Forensic Laboratories.
More about Ekrem can be found here.
For his publications, please click here.
Nikki Conlin
Operations Manager
Nikki Conlin is our Operations Manager, running Oxford Wave Research’s sales, marketing and customer support effort.
Nikki has many years of experience working with law enforcement as well as in the commercial sector. She has worked extensively with law enforcement, government and military customers in the UK and around the world providing software and hardware solutions tailored to their needs in the area of audio and video acquisition and processing. Nikki started her career working with a specialist law enforcement working group to standardise the use of digital media for presenting evidence in UK courts. With her deep background in CD and DVD production she was able to train and help establish ‘best practices’ for data handling, presentation and preservation.
Nikki has previously worked alongside the OWR founders, Anil and Oscar, in audio processing and speaker recognition. She has a wealth of experience in this area having dealt with both research projects and commercial products in this area. In the last few years Nikki has been working on commercial projects for the UK’s leading social media personalisation specialists. As part of the project management team Nikki enjoyed expanding the use of social media platforms for a broad range of clients including Marriott Hotels International, Cancer Research UK, 20th Century Fox, Sky and BBC.
Her LinkedIn Profile is here:
Linda Gerlach
Research Translation and Commercialisation Manager
Linda is the Research Translation and Commercialisation Manager at Oxford Wave Research. She bridges the gap between research and practical applications, ensuring that product standards are met to provide our customers with the best possible experience.
Linda obtained her undergraduate degree in Language and Communication at Philipps University Marburg, Germany, and went on to complete her master’s degree in Speech Science with a focus on phonetics at the same university. For her master’s thesis titled “A study on voice similarity ratings: humans versus machines”, she worked in collaboration with the University of Cambridge during her internship at Oxford Wave Research (2018-2019).
Linda did a research internship at Oxford Wave Research where she designed and completed automatic speaker recognition and profiling experiments with large-scale databases. Her poster titled “More than just identity: speaker recognition and speaker profiling using the GBR-ENG database” (Linda Gerlach, Finnian Kelly, Anil Alexander) presented at the IAFPA (International Association for Forensic Phonetics and Acoustics) conference 2019 held in Istanbul, Turkey, won the best student poster award.
Linda is currently pursuing a PhD of the University of Cambridge, in the area of speaker characteristics and forensic phonetics, using both traditional phonetic and automatic (machine-based) techniques. Her academic profile can be accessed here.
Linda’s LinkedIn profile can be found here.
Jithin Lal
Graphic Designer/Software Tester
Jithin works as a Graphic Designer and Software Tester at Oxford Wave Research. As a graphic designer, he designs visual concepts, by hand or using computer software, to communicate our concepts and ideas that inspire and inform our customers. He helps to develop the overall layout and production design for advertisements, brochures, magazines, and corporate reports, as well as the company website. Additionally, he assists in quality assurance performing automated and manual tests to ensure our software products are working well.
Jithin is proficient in most major computer design software and has hands-on experience with developing designs for print media, websites, video and advertising. Having previously worked as an ‘Intent Analyst’, Jithin acted as mediator between customer input and various AI systems, helping to improve the performance of such systems. He received his Bachelor of Science degree in Computer Application from M. G University, Kerala, India, and is currently pursuing a higher diploma in Visual Effects.
Tom Coy
Senior R&D Software Developer
Tom works with the company’s Research & Development team, most recently focusing on the development of calibration tools for new products as well as performance assessment of OWR voice biometrics solutions. Tom has worked in diverse roles including Expert in Emerging Biometrics at the National Crime Agency, where he established best practices for the newly-formed Voice Analytics department, and Editor at Turtle Canyon Media, where he provided offline postproduction audio and video editing for short films. Tom obtained an undergraduate degree in German and Linguistics from Exeter College, Oxford. Thereafter Tom studied for an MA in Film Studies at King’s College London and more recently an MSc in Forensic Speech Science at the University of York. Tom’s MSc dissertation tested the performance of Long-Term Formant Distribution-based Semi-Automatic Speaker Recognition systems, comparing systems which extracted formants using traditional Linear Predictive Coding methods with systems employing a recently developed formant estimation tool, called DeepFormants, which uses a Deep Neural Network. As such, Tom has extensive experience in audio-visual editing and enhancement, (semi-)automatic speaker recognition system development, forensic phonetics and data analysis.
External Consultants
Dr Alankar Aryal Atreya
External Consultant, Previously Research Engineer at OWR
Alankar Aryal Atreya worked as a research engineer at Oxford Wave Research from 2013 to 2018 and developed many of our latest products in the areas of audio fingerprint analysis, audio processing and speaker recognition. Alankar received his bachelor’s degree in Computer Science and Engineering from Anna University, India in 2009. He brings a wealth of software development experience having previously worked as a software developer in Hitech Valley iNet Ltd. and IT Himalaya, based in Nepal. In 2013 he received his Dipl.-Ing. Degree working on his master’s thesis on “Combining multiple tracking approach to improve performance” at the Institute of Information Technology, Alpen-Adria Universität, Austria. He has won the best student award in EPiCS video contest organised by “European Proprioception in Computing Systems” (EPiCS). His main areas of interest are speaker recognition, audio processing, image processing, object tracking and computer vision.
His LinkedIn profile can be found here.
Dr Bence Halpern
External Consultant
Dr Bence Halpern is an external consultant working on a wide range of deep learning-based speech technology projects. He completed his doctoral thesis titled “Making Speech Technology Accessible for Pathological Speakers” at the University of Amsterdam, TU Delft, and the Netherlands Cancer Institute. In addition, he holds a Biomedical Engineering MEng degree from Imperial College London.
Bence’s primary area of interest lies in understanding what factors contribute to making an audio signal sound natural. With a keen focus on this aspect, he has worked on a diverse range of tasks within the field, including speech enhancement, pathological speech synthesis, pathological speech detection, speech severity evaluation, voice conversion, and automatic speech recognition.
Bence is a recognised expert in his field. He published in numerous top-tier clinical and speech technology conferences and journals, and has been an invited speaker at many research labs in Europe and Japan. He was featured as a speech synthesis expert in the largest Dutch public broadcasting company’s AI song contest webseries.
Sam Kent
Software Developer
Sam Kent joined Oxford Wave Research as an apprentice in 2015 and was responsible for the development of quality assurance and testing of our software releases. He was able to script and automate large parts of the testing as well as data gathering and processing for our various products. He quickly ramped up his testing and development skills and has been instrumental in developing a lot of our web- and cloud-based applications as well as iPhone apps. He is the main developer behind OWR’s Apple watch application known as Watch-Me-Record available on the Apple app-store.
In 2017, Sam successfully completed the apprenticeship scheme and was offered a position of junior developer which he accepted. His areas of speciality are in audio processing, app development, web- and cloud-based coding as well as in quality assurance.
Ian Burton
External Consultant, Audio Processing and Training
Ian Burton is Oxford Wave Research’s audio processing expert, and is responsible for sales and training for law enforcement. He is a retired UK police officer with 30 years service. His area of expertise have been audio and video including both acquisition as well as enhancement.
As a police officer, he had been a regular instructor on technical matters on undercover operations, assisted many UK forces in covert operations and has given evidence at Crown Court in related matters. He has worked for the Greater Manchester Police Technical Support Unit (TSU) from 2001, and provided force-wide technical support to the major crime units. He has been passionately involved in audio enhancement and was also responsible for setting up the audio lab at GMP TSU as a force-wide facility for audio enhancement. Ian has been providing training courses in the UK and around the world. He works with OWR in our audio enhancement team, and is a trainer for forensic and law enforcement audio and OWR’s products.
Alumni
- Alexander Carver (staff, QA and software testing)
- Andrea Fröhlich (internship)
- Bence Halpern (internship)
- Tom Iszatt (staff, QA and customer experience specialist)