Speech and language are integral to human communication. They encode rich linguistic and paralinguistic information of intent and emotions, including implicit cues that are reflective of our internal mental states and traits. In fact, many existing behavioral assessments and clinical diagnoses of neurological and psychiatric disorders rely on experts evaluating the human mental states through systematic manual categorization of relevant speech and language behaviors.
With advances in speech and language processing technologies (e.g., automatic speech recognition, speaker diarization, semantic analysis, information retrieval, etc.) as well as in behavioral signal processing and affective computing alongside the converging capabilities in large-scale human-centric sensing, data collection, and computing, there exists a wide range of possibilities for automatically detecting, recognizing, analysing, and predicting human mental states and traits from speech and language cues, including well-being and aspects of dysfunction, atypicality, and other indicators of illness. Such computational advances in modelling human behavioral signals have made the development of automated speech and language-based decision analytics in a variety of behavioural and mental health domains for enabling screening, diagnostics, and treatment support increasingly desirable because of its potential in achieving high reliability, consistency, and large-scale deployment. Domains of active research range from Autism Spectrum Disorders, major depressive disorders, and suicidality to Alzheimer’s disease, addiction, and relationship issues.
However, realizing end-to-end, real-world speech and language processing-based behavioral and mental health analytics require integrative handling of a wide range of technical challenges. These include deploying robust speech and language technology in clinically-valid and real-life scenarios, handling a variety of contextual and human factor-induced variabilities, uncovering hidden behavioral patterns related to the mental states of interest, and further validating and disseminating the derived speech-language analytics in mental health contexts. Many of these technical advancements have been isolated in the past, so substantial algorithmic and empirical efforts are still required to further enhance the technical capabilities, augmenting experts’ decision support and improving our quantitative understanding of human behaviors.
The objective of this Special Issue on Speech and Language Processing for Behavioral and Mental Health Applications is to bring together and share these advances in order to shape the future of the field. It will focus on technical issues and applications of speech and language processing for behavioral and mental health applications. Original, previously unpublished submissions are encouraged within (not limited to) the following scope:
Analysis of mental and behavioral states in spoken and written language
Technological support for ecologically- and clinically-valid data collection and pre-processing
Robust automatic recognition of behavioral attributes and mental states
Cross-cultural, cross linguistic, cross-domain mathematical approaches and applications
Subjectivity modelling (mental states perception and behavioral annotation)
Multimodal paralinguistics (e.g., voice, face, gesture)
Neural-mechanisms, physiological response, and interplay with expressed behaviours
Databases and resources to support study of speech and language processing for mental health
Applications: scientific mechanisms, clinical screening, diagnostics, & therapy/treatment support
Example Domains: Autism spectrum disorders, addiction, family and relationship studies, major depressive disorders, suicidality, Alzheimer’s disease
Before submission, authors should carefully read over the journal\’s Author Guidelines, which are located at http://www.elsevier.com/wps/find/journaldescription.cws_home/622808/authorinstructions. Authors should follow the Elsevier Computer Speech and Language manuscript format described at the journal site http://www.elsevier.com/wps/find/journaldescription.cws_home/622808/authorinstructions#20000. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at https://www.evise.com/evise/jrnl/CSL. When submitting your papers, authors must select VSI:SLP-Behavior-mHealth as the article type.
Manuscript Due: October 31, 2017
First Round of Reviews: January 15, 2018
Second Round of Reviews: April 15, 2018
Publication Date: June 31, 2018