Recorded speech and written texts are increasingly presented as scientific evidence in legal cases. This is due to the fact that the accessibility and anonymity of mobile phones and the internet mean that they are often exploited for criminal acts, but at the same time they leave records which can then be analysed as forensic evidence. This has led to the rapid growth of forensic voice/text comparison as a field of forensic science.
The theories and techniques, which are necessary to analyse linguistic evidence, are introduced and demonstrated, with a particular focus on voice and text as linguistic evidence, using examples taken from various languages. In this course, we overview the process of forensic voice/text comparison, including extraction of individualising information from speech/text samples; modelling of speakers/authors, experimental procedures; calculation of evidential strength and performance assessment.
Students are expected to demonstrate that they can appropriately apply their acquired skills and knowledge to actual linguistic data extracted from various languages, and then that they can provide an in-depth analysis of the data. They are also expected to critically discuss the results of the analysis by referring to the current issues of forensic voice/text comparison.
Learning Outcomes
Upon successful completion, students will have the knowledge and skills to:
Upon completion of this course, students should be able to:
1. Critically evaluate different methodologies used in forensic voice/text comparisons;
2. Demonstrate high level analytical skills required for forensic voice/text comparisons;
3. Carry out forensic voice/text comparison experiments with a small set of data;
4. Present the outcomes in a written and/or oral format;
5. Critically examine readings on the current issues surrounding forensic voice/text comparisons; and
6. Exercise higher-level critical thinking and judgment in identifying and solving problems related to forensic voice/text comparisons.
Indicative Assessment
A paper summary assignment c.a. 500 10% 1,5,61 x take-home assignment (1) on likelihood ratio and Bayesian theorem c.a. 1000 10% 1,5,6
1 x take-home assignment (2) on forensic text comparison c.a. 1000 15% 2,3,4,6
1 x take-home assignment (3) on forensic voice comparison c.a. 1000 15% 2,3,4,6
Project c.a. 3000 50% 1,2,3,4,5,6
The ANU uses Turnitin to enhance student citation and referencing techniques, and to assess assignment submissions as a component of the University's approach to managing Academic Integrity. While the use of Turnitin is not mandatory, the ANU highly recommends Turnitin is used by both teaching staff and students. For additional information regarding Turnitin please visit the ANU Online website.
Workload
This course has 3 contact hours per week (lectures and tutorials). In addition to the required contact hours (lectures and tutorials), it is expected that students will spend an additional 6-7 hours per week on this course. In lectures, students will learn necessary theories and methodologies using various examples from a variety of Asian and non-Asian languages. In tutorials, students will put what they have learnt in lectures into practice, by working on actual linguistic data by themselves. Extra reading materials are provided for postgraduate students. Extra tasks will be assigned for postgraduate students in some of the assessment items in order to assess their higher-level critical thinking and in-depth and comprehensive understanding of the field.
In the latter half of the course, students need to spend a substantial amount of time for their project using their own target language (e.g. Chinese, Japanese, English).
This course may be offered as a summer/winter course. In this case, the course will be offered in an intensive mode, and the weekly contact hours and the outside-classroom study time will change accordingly.
Requisite and Incompatibility
Preliminary Reading
Posted on wattle prior to the semesterBooks and journal papers used in this course
• Aitken, Colin and Taroni, Franco (2004). Statistics and the Evaluation of Evidence for Forensic Scientists. Wiley.
• Coulthard, Malcolm and Johnson, Alison (2007). An Introduction to Forensic Linguistics: Language in Evidence. Routledge.
• Ishihara, Shunichi (2011). A forensic authorship classification in SMS messages: A likelihood ratio based approach using N-gram. Proceedings of the Australasian Language Technology Workshop 2011, 47-56.
• Ishihara, Shunichi (2012). Probabilistic evaluation of SMS messages as forensic evidence: Likelihood ratio based approach with lexical features. International Journal of Digital Crime and Forensics 4(3), 47-57.
• Kinoshita, Yuko, Ishihara, Shunichi and Rose, Phil (2009). Exploring the discriminatory potential of F0 distribution parameters in traditional forensic speaker recognition. International Journal of Speech Language and the Law 16(10), 91-111.
• Lucy, David (2005). Introduction to Statistics for Forensic Scientists. Wiley.
• Morrison, Geoffrey S. (2009a). Forensic voice comparison and the paradigm shift. Science & Justice 49(4), 298-308.
• Morrison, Geoffrey S. (2009b). Likelihood-ratio forensic voice comparison using parametric representations of the formant trajectories of diphthongs. Journal of the Acoustical Society of America 125(4), 2387-2397.
• Morrison, Geoffrey S. (2011). Measuring the validity and reliability of forensic likelihood-ratio systems. Science & Justice 51(3), 91-98.
• Morrison, Geoffrey S. (2012). The likelihood-ratio framework and forensic evidence in court: A response to R v T. The International Journal of Evidence & Proof 16(1), 1-29.
• Morrison, Geoffrey S. (2013). Tutorial on logistic-regression calibration and fusion: Converting a score to a likelihood ratio. Australian Journal of Forensic Sciences 45(2), 173-197.
• Robertson, Bernard and Vignaux, G. A. (1991). Interpreting Evidence: Evaluating Forensic Science in the Courtroom. Wiley.
• Rose, Phil (2002). Forensic Speaker Identification. Taylor & Francis.
• Rose, Phil (2006). Technical forensic speaker recognition: Evaluation, types and testing of evidence. Computer, Speech and Language 20(2-3), 159-192.
• Rose, Phil and Morrison, Geoffrey S. (2009). A response to the UK position statement on forensic speaker comparison. International Journal of Speech Language and the Law 16(10), 139-163.
Assumed Knowledge
Students should be enrolled in a postgraduate degree.Fees
Tuition fees are for the academic year indicated at the top of the page.
If you are a domestic graduate coursework or international student you will be required to pay tuition fees. Tuition fees are indexed annually. Further information for domestic and international students about tuition and other fees can be found at Fees.
- Student Contribution Band:
- 1
- Unit value:
- 6 units
If you are an undergraduate student and have been offered a Commonwealth supported place, your fees are set by the Australian Government for each course. At ANU 1 EFTSL is 48 units (normally 8 x 6-unit courses). You can find your student contribution amount for each course at Fees. Where there is a unit range displayed for this course, not all unit options below may be available.
| Units | EFTSL |
|---|---|
| 6.00 | 0.12500 |
Course fees
- Domestic fee paying students
| Year | Fee |
|---|---|
| 2017 | $3216 |
- International fee paying students
| Year | Fee |
|---|---|
| 2017 | $4590 |
Offerings, Dates and Class Summary Links
ANU utilises MyTimetable to enable students to view the timetable for their enrolled courses, browse, then self-allocate to small teaching activities / tutorials so they can better plan their time. Find out more on the Timetable webpage.
Class summaries, if available, can be accessed by clicking on the View link for the relevant class number.
Second Semester
| Class number | Class start date | Last day to enrol | Census date | Class end date | Mode Of Delivery | Class Summary |
|---|---|---|---|---|---|---|
| 9682 | 24 Jul 2017 | 31 Jul 2017 | 31 Aug 2017 | 27 Oct 2017 | In Person | N/A |
