PUBLICATIONS
My recent publications were in reputed peer-reviewed conferences that include Speech Prosody, 2020, ACM-IUI, 2020, and ICMI, 2018.
List of Publications
Ward, N., Jodoin, J., Nath, A., Fuentes, O. 2020. Using Prosody to Find Mentions of Urgent Problems in Radio Broadcasts. Proc. 10th International Conference on Speech Prosody 2020, 660-664, DOI: 10.21437/SpeechProsody.2020-135.
This paper examines whether prosodic information is usefully indicative of urgency and related attributes of situations in news broadcasts. We find that, in all 8 languages studied, prosody is informative. We also find some predictive value in cross-language modeling, suggesting the possibility of universal tendencies.
Anindita Nath. 2020. Towards Naturally Responsive Spoken Dialog Systems by Modelling Pragmatic-Prosody Correlations of Discourse Markers. In Proceedings of the 25th International Conference on Intelligent User Interfaces Companion, 2020. Association for Computing Machinery, New York, NY, USA, 128–129. DOI:https://doi.org/10.1145/3379336.3381490
Human speakers in a dialog adapt their responses and the way they convey them to their interlocutors by appropriately tuning their prosody, taking into account the context in which the dialog takes place. Today's spoken dialog systems are incapable of exhibiting such natural responsive behavior. Hence, there is a need for models that enable the selection of better prosody in system responses to make them appropriate to the pragmatic intentions and the dialog context. This submission includes the detailed description of my preliminary study on the prosody of discourse markers, the methods used and my initial findings that corroborate the existence of correlations between prosody and pragmatic intentions of discourse markers in human-human dialogs. These correlations, if modeled accurately, can help dialog systems respond with context-appropriate prosody.
Anindita Nath. 2018. Responding with Sentiment Appropriate for the User's Current Sentiment in Dialog as Inferred from Prosody and Gaze Patterns. In Proceedings of the 20th ACM International Conference on Multimodal Interaction, 2018. Association for Computing Machinery, New York, NY, USA, 529–533. DOI:https://doi.org/10.1145/3242969.3264974
Multi-modal sentiment detection from natural video/audio streams has recently received much attention. I propose to use this multi-modal information to develop a technique, Sentiment Coloring , that utilizes the detected sentiments to generate effective responses. In particular, I aim to produce suggested responses colored with sentiment appropriate for that present in the interlocutor's speech. To achieve this, contextual information pertaining to sentiment, extracted from the past as well as the current speech of both the speakers in a dialog, will be utilized. Sentiment, here, includes the three polarities: positive, neutral and negative, as well as other expressions of stance and attitude. Utilizing only the non-verbal cues, namely, prosody and gaze, I will implement two algorithmic approaches and compare their performance in sentiment detection: a simple machine learning algorithm (neural networks), that will act as the baseline, and a deep learning approach, an end-to-end bidirectional LSTM RNN, which is the state-of-the-art in emotion classification. I will build a responsive spoken dialog system(s) with this Sentiment Coloring technique and evaluate the same with human subjects to measure benefits of the technique in various interactive environments.