A variety of neurological and psychiatric conditions can alter a person's behavioural signals. Speech is an attractive signal for use in automated detection of neurological and psychiatric conditions; associated cognitive and physiological alterations influence the process of speech production, affecting the acoustic and linguistic quality of the speech produced in a way that is measurable and possible to objectively assess. However there is a need to address some key research issues which are fundamental to vocal biomarkers for potentially all neurological and psychiatric conditions.
The aim of this session is to provide a focal point for the latest developments within speech-based neurological and psychiatric assessment. Topics covered in the session will include (but are not limited to) speech-based research into detecting depression, post-traumatic stress disorder, traumatic brain injury, suicidality, dementia, Alzheimer's disease, general schizophrenia, Parkinson's disease and autism.
Further the session aims to expose speech-based neurological and psychiatric research to a wider audience and foster new interdisciplinary collaborations. To increase interactions between speech, neuroscience and clinical communities the organisers will be inviting attendees from psychological, neuroscience and medical backgrounds who may not otherwise attend Interspeech.
To address some of the key contemporary issues within this research area, the organisers will encourage interested participants to consider submitting papers into one of the following themes in particular, as they are key challenges that span multiple separate application areas in this growing field of speech research:
Novel clinically-motivated or
neuroscience-motivated vocal features
Features designed to capture speech effects specific to one or more conditions
Nuisance Variability Compensation
Removing effects of comorbid conditions and other forms of acoustic variability that might otherwise limit system performance
Considerations of clinical utility and systems that can self-determine a level of uncertainty associated with detection, as well as detecting the presence of a condition
Analysing the potential similarities and differences in speech patterns between the different conditions or speech samples affected a single condition but recorded under different paradigms
The session will organised around these themes and designed to maximise interactions between participants and attendees. Top rated papers will be given oral presentations, whilst other participants will give a poster. Note, papers submitted outside of these themes will also be considered for acceptance to the session.
Nicholas Cummins – Universität Passau, Germany, UNSW Australia
Julien Epps – UNSW Australia, Data61
Emily Mower Provost – University of Michigan
Thomas Quatieri – MIT Lincoln Laboratory
Stefan Scherer – USC Institute for Creative Technologies
Submission opens: Monday, 1st February 2016
Submission deadline: Wednesday, 23 March 2016
Deadline for final PDF of paper submission to be uploaded: Wednesday, 30 March 2016
Disposition notifications sent: Friday, 10 June 2016
Camera-ready paper due: Friday, 24 June 2016
Note: The session will follow the usual Interspeech paper review and publication process
For full details please visit Interspeech 2016 Call for Papers
Submission now open through Interspeech website: Interspeech 2016 Paper Submission
Note: The session's scientic topic area identifier is [3.12]
Depression: Audio/Visual Emotion and Depression Recognition Database
Traumatic Brain Injury: TBIBank
Alzheimer's disease: Carolina Conversations Collection
Autism: Child Pathological Speech Database
Parkinson's Disease: Parkinson's Speech Database
Cognitive-load with speech and EGG Database: Please Contact Julien Epps