Monday, September 7, 2015, 14:30–16:30, Large Hall
Joseph P. Campbell, MIT Lincoln Laboratory, Lexington, MA, U. S. A.
Jean-François Bonastre, Université d’Avignon, France
Other members of the special event organizing committee
Anders Eriksson, Stockholm University, Sweden
Hiro Nakasone, Operational Technology Division, FBI
Reva Schwartz, Forensic Services Division, United States Secret Service
In speaker comparison, speech samples are compared by humans and/or machines for use in investigations or in court to address questions that are of interest to the legal system. Speaker comparison is a high-stakes application that can change people’s lives and it demands the best that science has to offer; however, methods, processes, and practices vary widely. These variations are not necessarily for the better and although recognized, are not generally appreciated and acted upon. Methods, processes, and practices grounded in science are critical for the proper application (and nonapplication) of speaker comparison to a variety of international investigative and forensic applications.
This special event has three main objectives:
- Improve understanding of speaker comparison for investigative and forensic application (e. g., describe what is currently being done and critically analyze performance and lessons learned).
- Improve communications between communities of researchers, legal scholars, and practitioners internationally (e. g., directly address some central legal, policy, and societal questions such as allowing speaker comparisons in court, requirements for examiners and expert witnesses, and requirements for validation of specific automatic and/or human-based methods).
- Present and discuss current practices and how to move to adopting best practices (e. g., method validation, reduction of bias, and presentation of evidence)
An overarching objective is to focus on the international aspects. There are different (best or not) forensic speaker comparison practices throughout the world and differences between legal systems and cultures. It is important to have a good knowledge of these differences in order to try to build common vocabulary, guidance on practice, and scientific validation and positions. We plan to develop a roadmap for progress and produce documented contributions to the field.
Of course, some of these objectives will need multiple sessions to fully achieve success. This special event builds on previous successful special sessions and tutorials in forensic applications of speaker comparison at Interspeech, beginning in 2003. We hope to build on these Dresden discussions with additional events and sessions in future Interspeech conferences.
Organization of the special event
The aim of this special event is to have several structured discussions, where many international experts will present their opinion and participate in the free exchange of ideas. The format of this special event is an invited panel session divided into three parts, each oriented around a given question. For each question, the event organizers will propose a short introduction and up to six opinion promotors will be invited to present their point in 180 seconds. Then, a 10-minute discussion will take place with the opinion promotors, participants, and organizers. Finally, a 20-minute overall discussion will close the event.
1. Case-to-case variation in forensic speaker comparison
2. Possible best practices for analysis methods, including how to state analysis and examination results
3. Existence of physical speaker-specific information in speech samples