Rada Mihalcea

Rada Mihalcea

Auto-generated profile, based on publicly available information

Rada Mihalcea

University of Michigan, Ann Arbor, MI, USA

Research Focus & Metrics

Academic Career Length

25Years (2002-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
3 June 2023 in Information Fusion
Verified
Journal Article
Closed access
AMAmbuj Mehrish
Ambuj Mehrish
NMNavonil Majumder
Navonil Majumder
RBRishabh Bharadwaj
Rishabh Bharadwaj
RMRada Mihalcea
Rada Mihalcea
SPSoujanya Poria
Soujanya Poria

1 January 2023 in IEEE Transactions on Affective Computing
Verified
Journal Article
Closed access
SPSoujanya Poria
Soujanya Poria
DHDevamanyu Hazarika
Devamanyu Hazarika
NMNavonil Majumder
Navonil Majumder
RMRada Mihalcea
Rada Mihalcea

4 April 2022 in Computational Linguistics
Verified
Journal Article
Open access
PDF file
DJDi Jin
Di Jin
ZJZhijing Jin
Zhijing Jin
ZHZhiting Hu
Zhiting Hu
OVOlga Vechtomova
Olga Vechtomova
RMRada Mihalcea
Rada Mihalcea
Text style transfer is an important task in natural language generation, which aims to control certain attributes in the generated text, such as politeness, emotion, humor, and many others. It has a long history in the field of natural language processing, and recently has re-gained significant attention thanks to the promising performance brought by deep neural models. In this article, we present a systematic survey of the research on neural text style transfer, spanning over 100 representative articles since the first neural text style transfer work in 2017. We discuss the task formulation, existing datasets and subtasks, evaluation, as well as the rich methodologies in the presence of parallel and non-parallel data. We also provide discussions on a variety of important topics regarding the future development of this task.1

13 September 2021 in Cognitive Computation
Verified
Journal Article
Closed access
PDF file
SPSoujanya Poria
Soujanya Poria
NMNavonil Majumder
Navonil Majumder
DHDevamanyu Hazarika
Devamanyu Hazarika
DGDeepanway Ghosal
Deepanway Ghosal
RBRishabh Bhardwaj
Rishabh Bhardwaj
RMRada Mihalcea
Rada Mihalcea

13 December 2016 in IEEE Transactions on Information Forensics and Security
Verified
Journal Article
Open access
MAMohamed Abouelenien
Mohamed Abouelenien
VPVeronica Perez-Rosas
Veronica Perez-Rosas
RMRada Mihalcea
Rada Mihalcea
MBMihai Burzo
Mihai Burzo
Deception detection has received an increasing amount of attention in recent years, due to the significant growth of digital media, as well as increased ethical and security concerns. Earlier approaches to deception detection were mainly focused on law enforcement applications and relied on polygraph tests, which had proved to falsely accuse the innocent and free the guilty in multiple cases. In this paper, we explore a multimodal deception detection approach that relies on a novel data set of 149 multimodal recordings, and integrates multiple physiological, linguistic, and thermal features. We test the system on different domains, to measure its effectiveness and determine its limitations. We also perform feature analysis using a decision tree model, to gain insights into the features that are most effective in detecting deceit. Our experimental results indicate that our multimodal approach is a promising step toward creating a feasible, non-invasive, and fully automated deception detection system.

28 October 2024
Verified
Conference Paper
Open access
NMNavonil Majumder
Navonil Majumder
CHChia-Yu Hung
Chia-Yu Hung
DGDeepanway Ghosal
Deepanway Ghosal
WHWei-Ning Hsu
Wei-Ning Hsu
RMRada Mihalcea
Rada Mihalcea
SPSoujanya Poria
Soujanya Poria
Generative multimodal content is increasingly prevalent in much of the content creation arena, as it has the potential to allow artists and media personnel to create pre-production mockups by quickly bringing their ideas to life. The generation of audio from text prompts is an important aspect of such processes in the music and film industry. Many of the recent diffusion-based text-to-audio models focus on training increasingly sophisticated diffusion models on a large set of datasets of prompt-audio pairs. These models do not explicitly focus on the presence of concepts or events and their temporal ordering in the output audio with respect to the input prompt. Our hypothesis is focusing on how these aspects of audio generation could improve audio generation performance in the presence of limited data. As such, in this work, using an existing text-to-audio model Tango, we synthetically create a preference dataset where each prompt has a winner audio output and some loser audio outputs for the diffusion model to learn from. The loser outputs, in theory, have some concepts from the prompt missing or in an incorrect order. We fine-tune the publicly available Tango text-to-audio model using diffusion-DPO (direct preference optimization) loss on our preference dataset and show that it leads to improved audio output over Tango and AudioLDM2, in terms of both automatic- and manual-evaluation metrics.