The Mental State Tracker allows the recording and analysis of speech and language to detect expressions of mood. Simply record a speech sample, complete one or two questionnaires and view the results. You can then re-play speech samples in various emotion categories such as "low mood" and "neutral".
Please note that the Mental State Tracker - Starter requires an Internet connection.
The Mental State Tracker - Starter uses the following technology:
1. Language Analysis.
2. Machine Learning.
3. Risk Analysis.
4. Visualisation and Graphs.
5. Questionnaires.
6. Result Logs.
In this version of the Mental State Tracker (Starter), artificial intelligence and machine learning methods are unlocked upon request only. Please email: psychologynetworkptyltd@gmail.com (fees apply).
The Mental State Tracker is the result of an ongoing research project including RMIT University in Melbourne, Australia, as well as the Psychology Network Pty Ltd. The full version offers the following features:
(1) The recording and analysis of speech to detect a number of mental health conditions. (2) The transcription of speech and the analysis of the resulting texts by various methods to determine mental health issues. (3) The analysis includes the determination of suicide risk. (4) Standard questionnaires, the results are compared with speech and text analysis. Finally, (5) an explanation component is used to explain to a user "why" a certain decision was made (e.g. determination of low mood) and "how" it was made.
Disclaimer: Please note that the program does not diagnose mental health problems and does not replace assessment and diagnosis by a qualified health professional. Also please note that the results of machine learning systems are never perfect but the performance of can improve over time. This application is distributed without warranty; without even the implied warranty of merchantability or fitness for a particular purpose.
If you or a loved one is thinking or talking about suicide then you will need to seek urgent medical attention or alternatively call a crisis service such as Lifeline on 13 11 14 or Beyond Blue on 1300 224 636 (Australia). Please consult appropriate health services in your region.
For more details, please visit us at: http://psychologynetwork.org
References
Mohamed, S.,Beckett, P.,Lech, M. (2015). Effect of fixed point computations on anger classification in speech signals In: Proceedings of the 2015 IEEE Symposium on Computer Applications and Industrial Electronics (ISCAIE 2015), Langkawi, Malaysia, 12-14 April 2015.
Fayek, H.,Lech, M.,Cavedon, L. (2015). Towards real-time speech emotion recognition using deep neural networks In: Proceedings of the 9th International Conference on Signal Processing and Communication Systems (ICSPCS 2015), Cairns, Australia, 14-16 December 2015
Stolar, M.,Lech, M.,Burnett, I. (2015). Prediction of emotional states in parent-adolescent conversations using non-linear autoregressive neural networks In: Proceedings of the 9th International Conference on Signal Processing and Communication Systems (ICSPCS 2015), Cairns, Australia, 14-16 December 2015
Hussenbocus, A.,Lech, M.,Allen, N. (2015). Statistical differences in speech acoustics of major depressed and non-depressed adolescents In: Proceedings of the 9th International Conference on Signal Processing and Communication Systems (ICSPCS 2015), Cairns, Australia, 14-16 December 2015.
Lech, M., Song, I., Yellowlees, P., Diederich, J. (Eds.), Mental Health Informatics. Berlin,
Heidelberg, New York: Springer Verlag, 2014. ISBN: 978-3-64238549-0
Song, I., Diederich, J., Speech Analysis for Mental Health Assessment using Support Vector
Machines. In: Lech, M., Song, I., Yellowlees, P., Diederich, J. (Eds.), Mental Health Informatics.
Berlin, Heidelberg, New York: Springer Verlag. 79-106.
9Apps 4.9
