Top

About

The Forensic Speech Science Laboratory (FSSL) is part of the Aston Institute for Forensic Linguistics (AIFL) and the Centre for Forensic Data Science (CFDS). The latter is part of the Computer Science Department.

The Laboratory conducts research and development aimed at improving casework capabilities in forensic speech science, particularly casework conducted within the new paradigm for the evaluation of forensic evidence, i.e.:

  • Quantification of strength of evidence as likelihood ratios (the likelihood-ratio framework is the logically correct framework for evaluation of forensic evidence)
  • Likelihood ratios calculated using relevant data, quantitative measurement, and statistical models
  • Validation of system performance under conditions reflecting those of the case under investigation
  • Reduction of the potential for cognitive bias by restricting subjective judgements to matters such as selection of appropriate data to enter into the system and by directly reporting the output of the statistical model as the strength of evidence

The primary focus of the Laboratory is on forensic voice comparison (aka forensic speaker recognition), but Laboratory members have also worked on disputed-utterance analysis and on speaker recognition by earwitnesses.

The Director of the Laboratory is Dr Geoffrey Stewart Morrison. The Laboratory was established in 2017 when Dr Morrison moved to Aston University, and it began to expand as part of the formation of the Aston Institute for Forensic Linguistics in 2019. The latter was funded by a GBP 6M investment that included a GBP 5.4M award from Research England’s Expanding Excellence in England (E3) fund.

People

Directors, Academic and Research Staff
  • Morrison, Geoffrey Stewart Dr
    Director of the Forensic Speech Science Laboratory
    Associate Professor of Forensic Speech Science
    Director of Centre for Forensic Data Science
    Computer Science Department, School of Engineering and Applied Science, Aston University
    Director and Forensic Consultant
    Forensic Evaluation Ltd
  • Zhang, Cuiling Prof
    Visiting Research Fellow
    Director
    Chongquing Institutes of Higher Education Key Forensic Science Laboratory
    Professor and Vice Dean
    School of Criminal Investigation, Southwest University of Political Science and Law
  • Rosas, Claudia Dr
    Visiting Research Fellow
    Associate Professor
    Instituto de Lingüística y Literatura, Universidad Austral de Chile
PhD Research students
  • Aleksandra, Szczekulska Ms
    Research Assistant
    Student
    MA Forensic Linguistics Programme, Aston University

Research

Development of a forensic voice comparison system

We are developing a forensic voice comparison system that can be used for research and casework. We view a system for conducting forensic voice comparison as not simply a collection of tools, but also protocols, databases suitable for training and testing under casework conditions, documentation, validation reports, and well trained practitioners. We aim to develop a system that will meet legal admissibility requirements such as those of Federal Rule of Evidence 702 and the Daubert trilogy of Supreme Court rulings in the United States, and of Criminal Practice Directions 19A in England & Wales.

In forensic voice comparison casework, the relevant population and the recording conditions vary greatly from case to case. Researchers and practitioners need protocols, tools, and data that provide them with the flexibility to deal with this case to case variability. Practitioners need to be able to train (or retrain or optimize) the system for the conditions of the case, and they need to be able to empirically validate the performance of the system under conditions reflecting those of the case. In order to inform practice, researchers need to explore which options and settings give best performance under particular conditions, and explore the robustness of systems to variability in conditions.

Commercially marketed software tools often lack flexibility, and may be too expensive for researchers and practitioners in lower GDP countries. Many researchers and practitioners in the field lack the programming skills to make use of existing open-source automatic speaker recognition toolsets, and licencing restrictions may prevent such toolsets from being used for casework which counts as commercial activity. For different reasons, existing commercial and open-source tools are often insufficiently well documented for end users and others to be able to easily understand what the tools are actually doing. This is in opposition to the transparency that may be required by the courts. Researchers and practitioners therefore need software tools that are low cost, flexible, and easy to use (controllable via GUI or only requiring very limited programming skills), that are very well documented, that are designed to facilitate validation, and that have code that is open to inspection (we envisage open source, but not open distribution).

In the context of this research and development project, we define two groups of end-users: 1. Researchers and practitioners who will (potentially) use the system to do research and to conduct casework. 2. Service users, i.e., organizations that commission practitioners to perform forensic voice comparison analyses. Potential service users include defence lawyers and law-enforcement agencies.

We have established relationships with several collaborators. Collaboration ranges from service users helping with end-user needs assessment, through to researchers collecting and sharing data and actively contributing to research and development. Collaborators include:

  • Chile: 
    Universidad Austral de Chile – Claudia Rosas, Jorge Sommerhoff
    Policia de Investigaciones
  • China: 
    Southwest University of Political Science and Law – Cuiling Zhang
  • Germany: 
    German Federal Police, Bundeskriminalamt (BKA) – Michael Jessen
  • Netherlands: 
    Netherlands Forensic Institute (NFI) – David van der Vloed
  • United Kingdom:
    National Crime Agency (NCA)
  • United States of America:
    Federal Bureau of Investigation (FBI) – David Marks

Progress:

  • 2018–2019 we worked on end-user needs assessments to identify the data that need to be collected, and the tools, protocols, and training programmes that need to be developed.
  • 2018–2019 we began development of prototypes for core software tools. We will be developing a system that uses x-vectors.

Funding:

  • Research England: Expanding Excellence in England (E3) fund
Consensus on validation

The community has made substantial progress on developing procedures, metrics, and graphics for validating forensic voice comparison systems and reporting the results. The Speech Communication virtual special issue on validation of forensic voice comparison systems was completed in 2019. There is also an ongoing effort through the Organization of Scientific Area Committees for Forensic Science (OSAC) to develop a standard for validation of forensic voice comparison systems.

An outstanding question, however, is how good is good enough?

In September 2019 we held a two-day meeting to discuss this issue. The meeting was organized and sponsored by the Forensic Speech Science Laboratory (Aston University), and hosted by the Netherlands Forensic Institute (NFI).

Invited were a group of participants who could potentially produce a document that would be seen as representing what is “generally accepted within the relevant scientific community”. Invitees were individuals who have knowledge and experience of validating forensic voice comparison systems in research and casework contexts, and individuals who have actually presented validation results to courts. Also invited were individuals who could bring a legal perspective on the issue, and individuals with knowledge and experience of validation of forensic science more broadly. 14 individuals attended in person and 1 participated via video conference. Others who could not attend will be asked to comment on drafts of the document we are producing as the output of the meeting.

The issue was discussed:

  • from an admissibility perspective, e.g., in the US with respect to FRE 702 and the Daubert trilogy, and in England & Wales with respect to CPD 19A.
  • with respect to jurisdictions and situations in which formal admissibility criteria do not apply but in which knowledge of validation results should be relevant for the court.
  • from a laboratory procedure or best practice perspective – should the practitioner proceed to analyze the questioned- and known-speaker recordings?

A consensus was reached among those in attendance. A document describing the consensus is now being drafted. It will undergo several rounds of feedback and revision to ensure that it accurately reflects the consensus. The plan is to publish the final version of the document open-access in a reputable forensic science journal.

Funding:

  • Research England: Expanding Excellence in England (E3) fund

Casework

The Forensic Speech Science Laboratory as an entity does not conduct casework; however, members of the Laboratory do. Enquiries regarding casework may be directed to Dr Morrison.