Md. Iftekhar Tanveer

M. Iftekhar Tanveer, Diego Casabuena, Jussi Karlgren et al.

Podcasts are conversational in nature and speaker changes are frequent -- requiring speaker diarization for content understanding. We propose an unsupervised technique for speaker diarization without relying on language-specific components. The algorithm is overlap-aware and does not require information about the number of speakers. Our approach shows 79% improvement on purity scores (34% on F-score) against the Google Cloud Platform solution on podcast data.

Md Iftekhar Tanveer, Md Kamrul Hassan, Daniel Gildea et al.

We use the largest open repository of public speaking---TED Talks---to predict the ratings of the online viewers. Our dataset contains over 2200 TED Talk transcripts (includes over 200 thousand sentences), audio features and the associated meta information including about 5.5 Million ratings from spontaneous visitors of the website. We propose three neural network architectures and compare with statistical machine learning. Our experiments reveal that it is possible to predict all the 14 different ratings with an average AUC of 0.83 using the transcripts and prosody features only. The dataset and the complete source code is available for further analysis.

Shouman Das, Syed A. Haque, Md. Iftekhar Tanveer

\emph{Topological data analysis} (TDA) has recently emerged as a new technique to extract meaningful discriminitve features from high dimensional data. In this paper, we investigate the possibility of applying TDA to improve the classification accuracy of public speaking rating. We calculated \emph{persistence image vectors} for the sentence embeddings of TEDtalk data and feed this vectors as additional inputs to our machine learning models. We have found a negative result that this topological information does not improve the model accuracy significantly. In some cases, it makes the accuracy slightly worse than the original one. From our results, we could not conclude that the topological shapes of the sentence embeddings can help us train a better model for public speaking rating.

Ankani Chattoraj, Rupam Acharyya, Shouman Das et al.

The role of verbal and non-verbal cues towards great public speaking has been a topic of exploration for many decades. We identify a commonality across present theories, the element of "variety or heterogeneity" in channels or modes of communication (e.g. resorting to stories, scientific facts, emotional connections, facial expressions etc.) which is essential for effectively communicating information. We use this observation to formalize a novel HEterogeneity Metric, HEM, that quantifies the quality of a talk both in the verbal and non-verbal domain (transcript and facial gestures). We use TED talks as an input repository of public speeches because it consists of speakers from a diverse community besides having a wide outreach. We show that there is an interesting relationship between HEM and the ratings of TED talks given to speakers by viewers. It emphasizes that HEM inherently and successfully represents the quality of a talk based on "variety or heterogeneity". Further, we also discover that HEM successfully captures the prevalent bias in ratings with respect to race and gender, that we call sensitive attributes (because prediction based on these might result in unfair outcome). We incorporate the HEM metric into the loss function of a neural network with the goal to reduce unfairness in rating predictions with respect to race and gender. Our results show that the modified loss function improves fairness in prediction without considerably affecting prediction accuracy of the neural network. Our work ties together a novel metric for public speeches in both verbal and non-verbal domain with the computational power of a neural network to design a fair prediction system for speakers.

Rupam Acharyya, Shouman Das, Ankani Chattoraj et al.

With the recent trend of applying machine learning in every aspect of human life, it is important to incorporate fairness into the core of the predictive algorithms. We address the problem of predicting the quality of public speeches while being fair with respect to sensitive attributes of the speakers, e.g. gender and race. We use the TED talks as an input repository of public speeches because it consists of speakers from a diverse community and has a wide outreach. Utilizing the theories of Causal Models, Counterfactual Fairness and state-of-the-art neural language models, we propose a mathematical framework for fair prediction of the public speaking quality. We employ grounded assumptions to construct a causal model capturing how different attributes affect public speaking quality. This causal model contributes in generating counterfactual data to train a fair predictive model. Our framework is general enough to utilize any assumption within the causal model. Experimental results show that while prediction accuracy is comparable to recent work on this dataset, our predictions are counterfactually fair with respect to a novel metric when compared to true data labels. The FairyTED setup not only allows organizers to make informed and diverse selection of speakers from the unobserved counterfactual possibilities but it also ensures that viewers and new users are not influenced by unfair and unbalanced ratings from arbitrary visitors to the www.ted.com website when deciding to view a talk.

M. Iftekhar Tanveer

Summarizing Likert scale ratings from human annotators is an important step for collecting human judgments. In this project we study a novel, graph theoretic method for this purpose. We also analyze a few interesting properties for this approach using real annotation datasets.

Iftekhar Naim, M. Iftekhar Tanveer, Daniel Gildea et al.

We present a computational framework for automatically quantifying verbal and nonverbal behaviors in the context of job interviews. The proposed framework is trained by analyzing the videos of 138 interview sessions with 69 internship-seeking undergraduates at the Massachusetts Institute of Technology (MIT). Our automated analysis includes facial expressions (e.g., smiles, head gestures, facial tracking points), language (e.g., word counts, topic modeling), and prosodic information (e.g., pitch, intonation, and pauses) of the interviewees. The ground truth labels are derived by taking a weighted average over the ratings of 9 independent judges. Our framework can automatically predict the ratings for interview traits such as excitement, friendliness, and engagement with correlation coefficients of 0.75 or higher, and can quantify the relative importance of prosody, language, and facial expressions. By analyzing the relative feature weights learned by the regression models, our framework recommends to speak more fluently, use less filler words, speak as "we" (vs. "I"), use more unique words, and smile more. We also find that the students who were rated highly while answering the first interview question were also rated highly overall (i.e., first impression matters). Finally, our MIT Interview dataset will be made available to other researchers to further validate and expand our findings.