activity
20162022
most citedA New Dataset for Natural Language Inference from Code-mixed Conversations

22 citations · 63 across the 9 of their papers we have counts for

collaborators

15 papers

eess.AS2022

Benchmarking Evaluation Metrics for Code-Switching Automatic Speech Recognition

Injy Hamed, Amir Hussein, Oumnia Chellah +5

Code-switching poses a number of challenges and opportunities for multilingual automatic speech recognition. In this paper, we focus on the question of robust and fair evaluation m…

cs.CL20222 cited

On the Calibration of Massively Multilingual Language Models

Kabir Ahuja, Sunayana Sitaram, Sandipan Dandapat +1

Massively Multilingual Language Models (MMLMs) have recently gained popularity due to their surprising effectiveness in cross-lingual transfer. While there has been much work in ev…

cs.CL2022

A Survey of Multilingual Models for Automatic Speech Recognition

Hemant Yadav, Sunayana Sitaram

Although Automatic Speech Recognition (ASR) systems have achieved human-like performance for a few languages, the majority of the world's languages do not have usable systems due t…

cs.CL2021

Predicting the Performance of Multilingual NLP Models

Anirudh Srinivasan, Sunayana Sitaram, Tanuja Ganu +3

Recent advancements in NLP have given us models like mBERT and XLMR that can serve over 100 languages. The languages that these models are evaluated on, however, are very few in nu…

cs.CL2021

Multilingual and code-switching ASR challenges for low resource Indian languages

Anuj Diwan, Rakesh Vaideeswaran, Sanket Shah +19

Recently, there is increasing interest in multilingual automatic speech recognition (ASR) where a speech recognition system caters to multiple low resource languages by taking adva…

cs.CL20204 cited

Cross-lingual and Multilingual Spoken Term Detection for Low-Resource Indian Languages

Sanket Shah, Satarupa Guha, Simran Khanuja +1

Spoken Term Detection (STD) is the task of searching for words or phrases within audio, given either text or spoken input as a query. In this work, we use state-of-the-art Hindi, T…