S
Sourish Chaudhuri
Researcher at Google
Publications - 36
Citations - 2621
Sourish Chaudhuri is an academic researcher from Google. The author has contributed to research in topics: Collaborative learning & Speaker diarisation. The author has an hindex of 13, co-authored 36 publications receiving 1711 citations. Previous affiliations of Sourish Chaudhuri include Carnegie Mellon University.
Papers
More filters
Book ChapterDOI
It's Not Easy Being Green: Supporting Collaborative Green Design Learning
Sourish Chaudhuri,Rohit Kumar,Mahesh Joshi,Elon J. Terrell,Fred Higgs,Vincent Aleven,Carolyn Penstein Rosé +6 more
TL;DR: A study in which alternative forms of collaborative learning support in the midst of a collaborative design task in which students negotiate between increasing power and increasing environmental friendliness is presented.
Proceedings Article
Unsupervised Structure Discovery for Semantic Analysis of Audio
Sourish Chaudhuri,Bhiksha Raj +1 more
TL;DR: This work presents a generative model that maps acoustics in a hierarchical manner to increasingly higher-level semantics and evaluates this model on a large-scale retrieval task from TRECVID 2011, and reports significant improvements over standard baselines.
Proceedings ArticleDOI
Unsupervised hierarchical structure induction for deeper semantic analysis of audio
Sourish Chaudhuri,Bhiksha Raj +1 more
TL;DR: A model for deeper analysis of the observed acoustics is presented that induces a probabilistic tree structure depending on estimated constituent identities and contexts, and audio characterization using the deeper structure outperforms the standard shallow-feature based characterizations.
Proceedings ArticleDOI
Supplementary Material: AVA-ActiveSpeaker: An Audio-Visual Dataset for Active Speaker Detection
Joseph Roth,Zhonghua Xi,Caroline Pantofaru,Sourish Chaudhuri,Ondrej Klejch,Radhika Marvin,Andrew C. Gallagher,Liat Kaver,Sharadh Ramaswamy,Arkadiusz Stopczynski,Cordelia Schmid +10 more
TL;DR: This paper presents the AVA Active Speaker detection dataset (AVA-ActiveSpeaker) which has been publicly released to facilitate algorithm development and comparison and introduces a state-of-the-art approach for real-time active speaker detection and compares several variants.
Posted Content
AVA-Speech: A Densely Labeled Dataset of Speech Activity in Movies
Sourish Chaudhuri,Joseph Roth,Daniel P. W. Ellis,Andrew C. Gallagher,Liat Kaver,Radhika Marvin,Caroline Pantofaru,Nathan Reale,Loretta Guarino Reid,Kevin W. Wilson,Zhonghua Xi +10 more
TL;DR: A new dataset is described which will be released publicly containing densely labeled speech activity in YouTube videos, with the goal of creating a shared, available dataset for speech activity detection.