Finding the WHO, WHAT & WHEN  in audio

Oxford Wave Research (OWR) is a leading R&D company based in Oxford, UK, specialising in audio and speech processing, voice biometrics and deep learning-related product development. Our team has many years of experience developing solutions for law enforcement, military as well as other agencies both in the UK and around the world.

Oxford Wave Research PhD Studentship at Cambridge

Collaborative PhD studentship between Oxford Wave Research, the University of Cambridge, and the Cambridge Trust



We are delighted that Oxford Wave Research Ltd and the University of Cambridge, in collaboration with the Cambridge Trust, have established a new PhD studentship based at Selwyn College, Cambridge. The award enables a student to undertake a PhD in Theoretical and Applied Linguistics, commencing in October 2020. The studentship was open to UK and EU candidates of outstanding academic potential, and covers tuition fees and maintenance for three years. The studentship is in the area of forensic phonetics, the application of phonetic analysis to criminal cases, often where the identity of a speaker is in question, either due to an incriminating recording (e.g. hoax call, ransom demand, telephone threat, etc.) or due to a witness having heard a speech event at a crime scene. Forensic phonetics uses both traditional phonetic and automatic (machine-based) techniques. The PhD project aims to consider the relationships between traditional phonetic analyses and automatic speaker recognition (computer-based identification and recognition of the identity behind a voice). The studentship will include collaborative opportunities for the student to gain industry experience and to conduct research in conjunction with Oxford Wave Research, an audio processing and voice-biometrics company which specialises in developing solutions for law enforcement agencies in forensic voice comparison. The student’s research will consider both human and machine-based, algorithmic selection of different groups of speakers for various forensic analyses based on different criteria and the implication of the selections of these groups in the evaluation of the strength of evidence. These criteria include voice similarity perceived by human listeners and demographic features such as gender, language, age, regional accent. Further, the research will attempt to evaluate how the human or automatic, machine-based selection of databases can result in algorithmic bias.
“We are delighted to be working with a leading audio-processing and voice biometrics company that has such a strong track record of developing solutions in the forensic speech and audio arena. Cambridge has a well-established tradition of research excellence and innovation in forensic phonetics and the opportunity to bring automatic speaker recognition techniques to complement our acoustic-phonetic and perceptual approaches represents an exciting new line of investigation for our Phonetics Lab.” Dr Kirsty McDougall, University of Cambridge
“This studentship overseen by Dr McDougall at the Phonetics Laboratory in Cambridge represents an incredible opportunity for us to formally collaborate with one of the best-regarded forensic phonetics research groups in the country, with an enduring legacy of fundamental and important research work. We look forward to the exciting research collaboration planned with the laboratory in this studentship that has important implications for how forensic casework involving speech is done in the future and which will help the legal system by providing timely, just and balanced analysis.” Dr Anil Alexander, CEO of Oxford Wave Research
Current award-holder
The recipient of this studentship in 2020 is Ms Linda Gerlach. Linda obtained her undergraduate degree in Language and Communication at Philipps University Marburg, Germany, and went on to complete her masters degree in Speech Science with a focus on phonetics at the same university. For her masters thesis titled “A study on voice similarity ratings: humans versus machines”, she worked in collaboration with the University of Cambridge during an internship at Oxford Wave Research (2018-2019).
About University of Cambridge Phonetics Laboratory
The University of Cambridge Phonetics Laboratory is based in the university’s Theoretical and Applied Linguistics Section, Faculty of Modern and Medieval Languages, and accommodates a strong community of teaching and research staff, research students, a number of affiliated researchers in phonetics, and a lab manager. As well as hosting an extensive programme of research in forensic phonetics, the lab fosters research in phonetics and phonology across a diverse range of topics including speech production and perception, language acquisition, psycholinguistics, prosody, tone, sociophonetics, and language variation and change. Recent funded projects in forensic phonetics include DyViS, VoiceSim and IVIP.
About Oxford Wave Research
Oxford Wave Research (OWR) is a specialised audio R&D company with expertise in voice biometrics, speaker diarization, audio fingerprinting and audio enhancement. The OWR team have contributed to major government projects, nationally and internationally. OWR has been particularly successful in bringing practical applications of state-of-the-art academic research algorithms to usable commercial products for law enforcement, military and other agencies. OWR’s solutions are used by law enforcement and forensic laboratories across the world including the UK, Germany, Netherlands, France, Canada, Switzerland. OWR are the creators of the well-established forensic voice comparison system 'VOCALISE', used in forensic audio labs across the world, as well as ‘WHISPERS’ which is a powerful networked ‘one to many’ voice comparison system.

Oxford Wave Research publications at ODYSSEY 2020

Two of our publications at the ODYSSEY 2020  Speaker and Language Recognition Workshop

Two of our collaborative papers, one on voice spoofing detection, and the other on the effects of device variability on forensic speaker comparison, are appearing at this week’s virtual ODYSSEY 2020 Speaker and Language Recognition Workshop. Video presentations for both papers are now available on the workshop website:

The full papers, along with the rest of the conference proceedings, can be found at: 


In our paper with Bence Halpern (PhD student, University of Amsterdam), “Residual networks for resisting noise: analysis of an embeddings-based spoofing countermeasure,” we propose a new embeddings-based method of spoofed speech detection using Constant Q-Transform (CQT) features and a Dilated ResNet Deep Neural Network (DNN) architecture. The novel CQT-GMM-DNN approach, which uses the DNN embeddings with a Gaussian Mixed Model (GMM) classifier, performs favourably compared to the baseline system in both clean and noisy conditions. We also present some ‘explainable audio’ results, which provide insight into the information the DNN exploits for decision-making. This study shows that reliable detection of spoofed speech is increasingly possible, even in the presence of noise.

See a blog post from Bence (including some explainable audio examples) here:


In our paper with David van der Vloed (from the Netherlands Forensic Institute), “Exploring the effects of device variability on forensic speaker comparison using VOCALISE and NFI-FRIDA, a forensically realistic database,” we investigate the effect of recording device mismatch on forensic speaker comparison with VOCALISE. Using the forensically-realistic NFI-FRIDA database, consisting of speech simultaneously-recorded on multiple devices (e.g. close-mic, far-mic, and telephone intercept, as seen in the data collection image), we demonstrate that while optimal performance is achieved by matching the relevant population recording device to the case data recording device, it is not necessary to match the precise device; broadly matching the device type is sufficient. This study presents a research methodology for how a forensic practitioner can corroborate their subjective judgment of the ‘representativeness’ of the relevant population in forensic speaker comparison casework.

Do face coverings affect identifying voices?

Vlog: Do face coverings affect identifying voices?
A small experiment using VOCALISE and PHONATE

In these recent months of 2020, like many others around the world, we have found ourselves adjusting to the new normal of wearing masks in various places like supermarkets and other public spaces. We found ourselves (minorly) annoyed that some biometric identification, like face recognition, doesn't quite work when wearing masks. This made us wonder how well voice biometric solutions could work when speakers are wearing masks, and we decided to perform a small experiment to analyse this. 

Over the last few weeks, we have been performing some small-scale tests of our VOCALISE and PHONATE software against speech spoken from behind a mask. We have found our systems to be quite robust to masked speech - they are able to recognise speakers across different mask-wearing conditions well.

The video below explains our experiment and discusses our findings. We hope that you find it interesting! 

[embed][/embed] Download Transcript

Speech Communication journal publication on voice similarity – joint work by Cambridge University and Oxford Wave Research

Exploring the relationship between voice similarity estimates by listeners and by an automatic speaker recognition system incorporating phonetic features



We are happy to announce that our latest paper has been accepted for publication in the prestigious 'Speech Communication' journal. This represents joint work between Cambridge University's  'Faculty of Modern and Medieval Languages and Linguistics' and Oxford Wave Research (OWR). 


This paper is titled 'Exploring the relationship between voice similarity estimates by listeners and by an automatic speaker recognition system incorporating phonetic features'  and is authored by Linda Gerlach (OWR, Cambridge), Dr Kirsty McDougall (Cambridge),  Dr Finnian Kelly (OWR), Dr  Anil Alexander (OWR), Prof. Francis Nolan (Cambridge).

Similar-sounding voices is of interest in many areas, be it for voice parades in a forensic setting, voice casting for film-dubbing or voice banking to save one's voice for future synthesis in case of a degenerative disease. However, it is a very time-consuming and expensive task. With the aim of finding an objective method that could speed up the process, we considered an automatic approach to rate voice similarity and explored the relationship between voice similarity ratings made by a total of 106 human listeners – some of whom may have been you – and comparison scores produced by an i-vector-based automatic speaker recognition system that extracts perceptually-relevant phonetic features. Our results showed a significant positive correlation between human and machine, motivating us to continue our developments in this space.

The main highlights of this work are that human judgements of voice similarity are seen to correlate with automatic speaker recognition  assessments (using auto-phonetic features) (this trend was seen with both English and German speakers’ judgements of English voices). These automatic speaker recognition assessments therefore show potential for automatically selecting foil voices for voice parades.

This paper is based on Linda's Gerlach's master's thesis work (University of Marburg, Germany) at Oxford Wave Research last year and uses the phonetic mode of VOCALISE speaker recognition software.

Linda Gerlach

The full paper is available for free download on the Journal's webpage. Please check the following link for the full abstract and paper, available for free using this link before 19th November 2020:

Our Spectrumview app features in BBC 4 documentary - Ocean Autopsy: The Secret Story of Our Seas

We were delighted to see our Spectrumview audio analysis app being used by Dr Helen Czerski , a renowned oceanographer and physicist from University College London, to explore a whole new acoustic world under the waves as part of the BBC 4 documentary - 'Ocean Autopsy: The Secret Story of Our Seas'. Dr Czerski drops a hydrophone into the depths of the ocean and listens to, and visualises the sounds deep under the water using Spectrumview. In this excellent programme they explore how the sounds deep under the water (including man-made sounds) can affect marine life such as porpoises.

So the ocean surface is effectively a barrier for almost all sound, so we have no idea what’s going on down there, and it’s a different acoustic world. But you can listen in with the help of a little bit of technology.

Dr Helen Czerski, Oceanographer

SpectrumView - Frequency Analysis Software