Vocal Biomarkers for Monitoring Neurological · PDF fileVocal Biomarkers for Monitoring...
Transcript of Vocal Biomarkers for Monitoring Neurological · PDF fileVocal Biomarkers for Monitoring...
Vocal Biomarkers for Monitoring Neurological Disorders
Thomas F. Quatieri
Senior Technical Staff, MIT Lincoln Laboratory Faculty Harvard-MIT Health Science Technology
May 7, 2015
JAC Review- 2 TFQ 02/27/15
MIT Lincoln Laboratory Federally Funded Research and Development Center
Massachusetts Institute of Technology MIT Lincoln Laboratory, Lexington, Massachusetts
Structure: Ten Divisions (e.g., Homeland Protection, Communication Systems, Cyber Security) with about eight groups within each division
Bioengineering Systems and Technology Group: Preserve and enhance human health and performance through monitoring, analysis, and interventions
• New group ~3 years: Highly interdisciplinary • Staff: ~50 scientists, engineers, students, support • Funding sources: DoD, NIH, Internal • Broad technical areas: Biomedical research, synthetic biology, bioinformatics,
biometrics
Speech, hearing, and neuro-cognitive analysis
JAC Review- 3 TFQ 02/27/15
Depression
Traumatic Brain Injury Cognitive Overload
Parkinson’s
Lou Gehrig’s Disease
Alzheimer’s Disease
Post Traumatic Stress Disorder
Fragmented Sleep
Environmental Hot, Cold,
Altitude
Psychological Fear
Danger
Speech, Hearing and Neuro-cognitive Analysis Motivation, Objective, Approach
Objective • Simple, sensitive method to detect and
monitor a condition • Distinguish across conditions
Gait
Approach: Vocal biomarkers!• Reflect underlying
neurophysiological changes that alter speech motor control !
• Reflect coordination changes across speech production components, as well with other modalities!
!
Motivation!• Many conditions that effect
cognitive performance!• Includes neurological and stress
conditions!
!
JAC Review- 4 TFQ 02/27/15
Prediction of cognitive status in elderly
0 0.2 0.4 0.6 0.8 10
0.2
0.4
0.6
0.8
1Imbalanced Data ROC for Averaged Dataset
False Positive Rate
True
Pos
itive
Rat
e
Equal Error Rate(EER) = 18%
Data: audio from 200 elderly
Research in vocal biomarkers
Articulatory coordination
Phonetic timing
MIT Lincoln Research Focus
Cognitive Load
Evolving research areas
Subjects Ages Sport
8 female 14–18
24 male 14–18
Data: Full Season Athlete Collection (Purdue)
Timing
Coordination
Reaction Time
False Alarm 0 0.1 0.2 0.3 0.4 0.5
0.2
0.4
0.6
0.8
1.0
True
Pos
itive
Mild Traumatic Brain Injury
ALS
Parkinson’s
8
10 -
RM
SE
Team Rank
AVEC 2013
9 - MIT LL
1
A
2
B
3
11 Data (2013 AVEC Depression Challenge):
• Audio from 50 train/50 test subjects
Objective:
• Predict BECK depression assessment score from audio
Depression
Vocal Fatigue
Effectiveness of drug treatment: Interest in Apps for depression monitoring
Traumatic brain injury: Piloting Apps for NCAA
Depression: Launching worldwide Apps (with Satra Ghosh, MIT BCS)
From laboratory to mobile device
Objective:
• Detect cognitive impairment
Dementia
Objective: Detect cognitive impairment (using IMPACT)
MIT LL/MIT BCS
JAC Review- 5 TFQ 02/27/15
Data Collections
Modeling
Making an Impact Research Areas
Clinical Acceptance
Advanced Feature
Extraction
JAC Review- 6 TFQ 02/27/15
Data Collections
Modeling
Making an Impact Research Areas
Advanced Feature
Extraction
Scientific Foundation Explain old and guide
new vocal biomarkers
Clinical Acceptance
JAC Review- 7 TFQ 02/27/15
Data Collections
Modeling
Making an Impact Research Areas
Advanced Feature
Extraction
Scientific Foundation Explain old and guide
new vocal biomarkers
Clinical Acceptance
JAC Review- 8 TFQ 02/27/15
Large-scale behavioral collections • Audio databases with on-body platforms
– Option to extract vocal features and remove audio • Collections with related modalities (e.g., robust wireless EEG)
Imaging collections • Brain, vocal tract, and vocal fold imaging
– Improved real-time MRI; ultra high-speed 3D video • Ultimate is simultaneous measurements during speaking
Improved protocols • Speaking tasks that illicit specific parts of the brain and
speech motor processes • Speaking tasks that bring out specific neural and motor
components effected by different neurological conditions
Research Areas Databases
Gait
JAC Review- 9 TFQ 02/27/15
Need for model-based approaches to enhance scientific foundation for use of vocal biomarkers
Computational neural modeling • Basic neural circuitry of speech production • Modulation by non-speech networks (e.g., limbic) • Disturbances in the distressed brain • Directions into Velocities of Articulators (DIVA)
model is one basis
Computational physiological modeling • Understanding of multitude of muscles and their
coordination in speech production • Disorders both in articulatory and laryngeal (vocal
fold) movement
Research Areas Modeling
Speech
Concept
Sentences and words
Syllables and phonemes Prosodics
Phonetic representation: Position/state of articulators/
folds
Timing and coordination of articulators and vocal folds
Neural signaling Muscle activation
Diff
eren
t bra
in r
egio
ns
Simple approximate view of speech production
Aud
itory
and
tact
ile s
elf-
mon
itori
ng
Limbic
Cognitive
JAC Review- 10 TFQ 02/27/15
• Mapping of changes in neural and physiological models
to changes in the acoustic signal • Robust and high-resolution signal processing to reflect
dynamic and subtle aspects of complex changes in neural and physiological systems, beyond standard features
Research Areas Advanced Feature Extraction
JAC Review- 11 TFQ 02/27/15
• Objective measures as an aid, not replacement • Early identification of neurologic disease onset • Prediction of relapse or recovery • Prediction should be specific as well as sensitive
– Many sub-classes of speech disorders common to a variety of neurological disorders
• Monitoring should be personalized with biofeedback
Clinical Acceptance
JAC Review- 12 TFQ 02/27/15
Acknowledgments
Daryush Mehta and Bob Hillman – MGH Voice Rehabilitation Center Jordan Green – MGH Speech and Feeding Disorders Lab Satra Ghosh – MIT Brain and Cognitive Science Dept. Visar Berisha – Arizona State, Speech and Hearing Science
JAC Review- 13 TFQ 02/27/15
Publications
Trevino, A., Quatieri, T. F. and Malyska, N., “Phonologically-based biomarkers for major depressive disorder,” EURASIP Journal on Advances in Signal Processing: Special Issue on Emotion and Mental State Recognition from Speech, 42:2011–2042, 2011. Williamson, J.R., Quatieri, T.F., Helfer, B.S., Horwitz, R., Yu, B., and Mehta, D.D., “Vocal biomarkers of depression based on motor incoordination,” in Proceedings of the 3rd ACM international workshop on Audio/visual emotion challenge, 2013, pp. 41–48. Helfer, B.S., T. F. Quatieri, Williamson, J.R., Mehta, D.D., Horwitz, R ., and B. Yu, “Classification of depression state based on articulatory precision.,” in Interspeech, 2013, pp. 2172–2176. Quatieri, T. F. and Malyska, N., “Vocal-source biomarkers for depression: A link to psychomotor activity,” Proceedings of Interspeech, 2012. Horwitz, R., Quatieri, T.F., Helfer, B.S., Yu, B., Williamson, J.R., and Mundt, J., “On the Relative Importance of Vocal Source, System, and Prosody in Human Depression.” IEEE Body Sensor Network Conference, Cambridge, MA, May 2013. Helfer, B.S., Quatieri, T.F., Williamson, J.R., Keyes, L., Evans, B., Greene, W.N., Vian, T., Lacirignola, J., Shenk, T., Talavage, T., Palmer, J., and Heaton, K., "Articulatory dynamics and coordination in classifying cognitive change in preclinical mTBI," Interspeech 2014. Yu, B., Quatieri, T.F., Williamson, J.R., and Mundt, J., "Prediction of cognitive performance in an animal fluency task based on rate and articulatory markers," Interspeech 2014. L. Keyes, J. Su, T. Quatieri, B. Evans, J. Lacirignola, T. Vian, W. Greene, D. Strom, and A. Dai, “FY12 Line-Supported Bio-Medical Initiative Program: Multi-modal Early Detection Interactive Classifier (MEDIC) for Mild Traumatic Brain Injury (mTBI) Triage,” MIT Lincoln Laboratory Project Report LSP-41, 2012.