Insights into the Challenges and Opportunities of Large Multi-Modal Models for Blind and Low Vision Users: CLIP
PARIKSHA: A Scalable, Democratic, Transparent Evaluation Platform for Assessing Indic Large Language Models
Publication Confidence Estimation, OOV Detection and Language ID Using Phone-to-Word Transduction and Phone-Level Alignments Chris White, Geoffrey Zweig In Proceedings of ICASSP | January 2008 Project
Publication Using Contextual Speller Techniques and Language Modeling for ESL Error Correction Michael Gamon, Jianfeng Gao, Chris Brockett, Alexander Klementiev, Bill Dolan, Dmitriy Belenko, Lucy Vanderwende Proceedings of IJCNLP, Hyderabad, India | January 2008 Project
Publication Empirical Properties of Multilingual Phone-to-Word Transduction Geoffrey Zweig In Proceedings of ICASSP | January 2008 In Proceedings of ICASSP Project Project
Publication Optimal Dialog in Consumer-Rating Systems using a POMDP Framework Zhifei Li, Patrick Nguyen, Geoffrey Zweig In Proceedings of SIGdial | January 2008 Project
Publication An Integrative and Discriminative Technique for Spoken Utterance Classification Ye-Yi Wang, S. Yaman, Li Deng, Dong Yu, Alex Acero, Sibel Yaman IEEE Trans. Audio, Speech, and Language Processing | January 2008, Vol 16: pp. 1207-1214 Project Project Project Project
Publication HMM adaptation using a phase-sensitive acoustic distortion model for environment-robust speech recognition Jinyu Li, Li Deng, Dong Yu, Alex Acero Proc. ICASSP | January 2008 Proc. ICASSP
Publication A Speech Enhancement Approach using Piecewise Linear Approximation of An Explicit Model of Environmental Distortions Jun Du, Qiang Huo Proc. of INTERSPEECH 2008 | January 2008 Proc. of INTERSPEECH 2008
Publication A corpus-based morpho-syntactic analysis of ‘kare’ in Bangla: Theory and applications Priyanka Biswas, , Kalika Bali, Monojit Choudhury Proceedings of the International Conference On NLP (ICON) | January 2008 Proceedings of the International Conference On NLP (ICON)
Publication Some Experiments in Mining Named Entity Transliteration Pairs from Comparable Corpora A Kumaran, K Saravanan The 2nd International Workshop on Crosslingual Information Access, Hyderabad, India | January 2008
Publication Mining named entity transliteration equivalents from comparable corpora Raghavendra Udupa, K. Saravanan, A. Kumaran, Jagadeesh Jagarlamudi 17th ACM Conference on Information and Knowledge Management (CIKM 2008) | January 2008 17th ACM Conference on Information and Knowledge Management (CIKM 2008)