no code implementations • 6 Sep 2023 • Mimansa Jaiswal
This research advances robust, practical emotion recognition through multifaceted studies of challenges in datasets, labels, modeling, demographic and membership variable encoding in representations, and evaluation.
no code implementations • 18 Apr 2021 • Mimansa Jaiswal, Emily Mower Provost
We end the paper with a set of recommendations for noise augmentations in speech emotion recognition datasets.
no code implementations • 18 Apr 2021 • Mimansa Jaiswal, Emily Mower Provost
In this paper, we propose an automatic and quantifiable metric that allows us to evaluate humans' perception of a model's ability to preserve privacy with respect to sensitive variables.
no code implementations • LREC 2020 • Mimansa Jaiswal, Cristian-Paul Bara, Yuanhang Luo, Mihai Burzo, Rada Mihalcea, Emily Mower Provost
Endowing automated agents with the ability to provide support, entertainment and interaction with human beings requires sensing of the users{'} affective state.
no code implementations • 29 Oct 2019 • Mimansa Jaiswal, Emily Mower Provost
In this work, we show how multimodal representations trained for a primary task, here emotion recognition, can unintentionally leak demographic information, which could override a selected opt-out option by the user.
no code implementations • 29 Sep 2019 • Zakaria Aldeneh, Mimansa Jaiswal, Michael Picheny, Melvin McInnis, Emily Mower Provost
Bipolar disorder, a severe chronic mental illness characterized by pathological mood swings from depression to mania, requires ongoing symptom severity tracking to both guide and measure treatments that are critical for maintaining long-term health.
no code implementations • 23 Aug 2019 • Mimansa Jaiswal, Zakaria Aldeneh, Emily Mower Provost
Our results show that stress is indeed encoded in trained emotion classifiers and that this encoding varies across levels of emotions and across the lexical and acoustic modalities.
no code implementations • 27 Mar 2019 • Mimansa Jaiswal, Zakaria Aldeneh, Cristian-Paul Bara, Yuanhang Luo, Mihai Burzo, Rada Mihalcea, Emily Mower Provost
As a result, annotations are colored by the manner in which they were collected.
no code implementations • 12 Mar 2019 • Mimansa Jaiswal, Sairam Tabibu, Erik Cambria
In the past few years, social media has risen as a platform where people express and share personal incidences about abuse, violence and mental health issues.
no code implementations • 11 Mar 2019 • Mimansa Jaiswal, Sairam Tabibu, Rajiv Bajpai
We propose a data-driven method for automatic deception detection in real-life trial data using visual and verbal cues.